@article{behara2023, title={Skin lesion synthesis classification with DCGAN}, author={Behara, K. and others}, journal={Sensors (Basel)}, year={2023} } @inproceedings{fey2019, title={Fast Graph Representation Learning with PyTorch Geometric}, author={Fey, M. and Lenssen, J. E.}, booktitle={ICLR}, year={2019} } @inproceedings{lin2017, title={Focal Loss for Dense Object Detection}, author={Lin, T.-Y. and others}, booktitle={ICCV}, year={2017} } @article{marghoob2013, title={Dermoscopy for the Family Physician}, author={Marghoob, A. A. and others}, journal={AFP}, volume={88}, pages={441--448}, year={2013} } @article{mazhar2023, title={The Role of ML and DL for Skin Cancer Detection}, author={Mazhar, T. and Haq, I. and others}, journal={Diagnostics}, year={2023} } @article{petrie2019, title={Melanoma Early Detection: Big Data, Bigger Picture}, author={Petrie, T. L. and others}, journal={J. Invest. Dermatol.}, year={2019} } @misc{riveraMonroy2022, title={Graph reps for melanoma MELC samples}, author={Rivera Monroy and L. C. and others}, publisher={arXiv}, year={2022} } @article{skandarani2023, title={GANs for Medical Image Synthesis: An Empirical Study}, author={Skandarani, Y. and others}, journal={Front. AI (MDPI)}, year={2023} } @article{zhang2022, title={Multiclass Skin Lesion Classification (Quantum + CNN)}, author={Zhang, X. and others}, journal={Front. Phys.}, year={2022} } @misc{cdcSkinCancer, title={Melanoma of the Skin Statistics - Skin Cancer}, organization={CDC}, url={https://www.cdc.gov/skin-cancer/statistics/index.html} } @article{godinich2024, title={Barriers to malignant melanoma diagnosis in rural areas in the United States: A systematic review}, author={Godinich, Brandon M. and Hensperger, Vince and Guo, William and Patel, Jay and Hugh, Jeremy and Kaufmann, Tara L. and Slutsky, Jordan B.}, journal={JAAD Reviews}, volume={1}, pages={29--41}, year={2024}, url={https://doi.org/10.1016/j.jdrv.2024.06.001} } @misc{wan2019, title={Multi-scale Dynamic Graph Convolutional Network for Hyperspectral Image Classification}, author={Sheng Wan and Chen Gong and Ping Zhong and Bo Du and Lefei Zhang and Jian Yang}, year={2019}, eprint={1905.06133}, archivePrefix={arXiv}, primaryClass={eess.IV}, url={https://arxiv.org/abs/1905.06133}, } @article{scarselli2009, author = {Scarselli, Franco and Gori, Marco and Tsoi, Ah Chung and Hagenbuchner, Markus and Monfardini, Gabriele}, title = {The graph neural network model}, year = {2009}, issue_date = {January 2009}, publisher = {IEEE Press}, volume = {20}, number = {1}, issn = {1045-9227}, url = {https://doi.org/10.1109/TNN.2008.2005605}, doi = {10.1109/TNN.2008.2005605}, abstract = {Many underlying relationships among data in several areas of science and engineering, e.g., computer vision, molecular chemistry, molecular biology, pattern recognition, and data mining, can be represented in terms of graphs. In this paper, we propose a new neural network model, called graph neural network (GNN) model, that extends existing neural network methods for processing the data represented in graph domains. This GNN model, which can directly process most of the practically useful types of graphs, e.g., acyclic, cyclic, directed, and undirected, implements a function τ(G, n) ∈IRm that maps a graph G and one of its nodes n into an m-dimensional Euclidean space. A supervised learning algorithm is derived to estimate the parameters of the proposed GNN model. The computational cost of the proposed algorithm is also considered. Some experimental results are shown to validate the proposed learning algorithm, and to demonstrate its generalization capabilities.}, journal = {Trans. Neur. Netw.}, month = jan, pages = {61–80}, numpages = {20}, keywords = {recursive neural networks, graphical domains, graph processing, graph neural networks (GNNs), Graphical domains} } @misc{marino2016, title={The More You Know: Using Knowledge Graphs for Image Classification}, author={Kenneth Marino and Ruslan Salakhutdinov and Abhinav Gupta}, year={2017}, eprint={1612.04844}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/1612.04844}, } @INPROCEEDINGS{sriram2024, author={Sriram, Arjun and Vatsa, Avimanyou and Kumar, Anvi and Vats, Savya and Kumar, Arav}, booktitle={2024 IEEE Integrated STEM Education Conference (ISEC)}, title={Challenges and Opportunities in Malignant Image Reconstruction Using GAN: A Review}, year={2024}, volume={}, number={}, pages={01-06}, keywords={Training;Shape;Reviews;Melanoma;Generative adversarial networks;Skin;Image preprocessing;Melanoma;Skin Cancer;GFP GAN;GAN;WGAN;cGAN;deep learning;neural networks}, doi={10.1109/ISEC61299.2024.10664911}} @misc{nazir2021surveyimagebasedgraph, title={Survey of Image Based Graph Neural Networks}, author={Usman Nazir and He Wang and Murtaza Taj}, year={2021}, eprint={2106.06307}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2106.06307}, } @INPROCEEDINGS{shoaib2024, author={Asim Shoaib and Mogana Vadiveloo and Seng Poh Lim}, booktitle={ITM Web of Conferences}, title={Comparative Studies of Region-Based Segmentation Algorithms on Natural and Remote Sensing Images}, year={2024}, volume={67}, number={}, pages={01-10}, doi={https://doi.org/10.1051/itmconf/20246701048} } @misc{defferrard2016, title={Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering}, author={Michaël Defferrard and Xavier Bresson and Pierre Vandergheynst}, year={2017}, eprint={1606.09375}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/1606.09375}, } @Article{zhang2023, AUTHOR = {Zhang, Sisi and Li, Fan and Zhang, Tiancheng and Yu, Ge}, TITLE = {Interpreting Deep Graph Convolutional Networks with Spectrum Perspective}, JOURNAL = {Mathematics}, VOLUME = {11}, YEAR = {2023}, NUMBER = {10}, ARTICLE-NUMBER = {2256}, URL = {https://www.mdpi.com/2227-7390/11/10/2256}, ISSN = {2227-7390}, ABSTRACT = {Graph convolutional network (GCN) architecture is the basis of many neural networks and has been widely used in processing graph-structured data. When dealing with large and sparse data, deeper GCN models are often required. However, the models suffer from performance degradation as the number of layers increases. The mainstream attribution of the current research is over-smoothing, and there are also gradient vanishing, training difficulties, etc., so a consensus cannot be reached. In this paper, we theoretically analyze the degradation problem by adopting spectral graph theory to globally consider the propagation and transformation components of the GCN architecture, and conclude that the over-smoothing problem caused by the propagation matrices is not the key factor for performance degradation. Afterwards, in addition to using conventional experimental methods, we proposed an experimental analysis strategy under the guidance of random matrix theory to analyze the singular value distribution of the model weight matrix. We concluded that the key factor leading to the degradation of model performance is the transformation component. In the context of a lack of consensus on the problem of model performance degradation, the paper proposes a systematic analysis strategy, as well as theoretical and empirical evidence.}, DOI = {10.3390/math11102256} } @Article{cinar2023, AUTHOR = {Cinar, Umut and Cetin Atalay, Rengul and Cetin, Yasemin Yardimci}, TITLE = {Human Hepatocellular Carcinoma Classification from H\&E Stained Histopathology Images with 3D Convolutional Neural Networks and Focal Loss Function}, JOURNAL = {Journal of Imaging}, VOLUME = {9}, YEAR = {2023}, NUMBER = {2}, ARTICLE-NUMBER = {25}, URL = {https://www.mdpi.com/2313-433X/9/2/25}, PubMedID = {36826944}, ISSN = {2313-433X}, ABSTRACT = {This paper proposes a new Hepatocellular Carcinoma (HCC) classification method utilizing a hyperspectral imaging system (HSI) integrated with a light microscope. Using our custom imaging system, we have captured 270 bands of hyperspectral images of healthy and cancer tissue samples with HCC diagnosis from a liver microarray slide. Convolutional Neural Networks with 3D convolutions (3D-CNN) have been used to build an accurate classification model. With the help of 3D convolutions, spectral and spatial features within the hyperspectral cube are incorporated to train a strong classifier. Unlike 2D convolutions, 3D convolutions take the spectral dimension into account while automatically collecting distinctive features during the CNN training stage. As a result, we have avoided manual feature engineering on hyperspectral data and proposed a compact method for HSI medical applications. Moreover, the focal loss function, utilized as a CNN cost function, enables our model to tackle the class imbalance problem residing in the dataset effectively. The focal loss function emphasizes the hard examples to learn and prevents overfitting due to the lack of inter-class balancing. Our empirical results demonstrate the superiority of hyperspectral data over RGB data for liver cancer tissue classification. We have observed that increased spectral dimension results in higher classification accuracy. Both spectral and spatial features are essential in training an accurate learner for cancer tissue classification.}, DOI = {10.3390/jimaging9020025} } @misc{brody2021, title={How Attentive are Graph Attention Networks?}, author={Shaked Brody and Uri Alon and Eran Yahav}, year={2022}, eprint={2105.14491}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2105.14491}, } @Article{sharma2024, AUTHOR = {Preeti Sharma and Manoj Kumar and Hitesh Kumar Sharma and Soly Mathew Biju}, TITLE = {Generative adversarial networks (GANs): Introduction, Taxonomy, Variants, Limitations, and Applications}, JOURNAL = {Multimedia Tools and Applications}, VOLUME = {83}, YEAR = {2024}, NUMBER = {}, URL = {https://link.springer.com/article/10.1007/s11042-024-18767-y}, DOI = {https://doi.org/10.1007/s11042-024-18767-y} } @misc{codella2017, title={Skin Lesion Analysis Toward Melanoma Detection: A Challenge at the 2017 International Symposium on Biomedical Imaging (ISBI), Hosted by the International Skin Imaging Collaboration (ISIC)}, author={Noel C. F. Codella and David Gutman and M. Emre Celebi and Brian Helba and Michael A. Marchetti and Stephen W. Dusza and Aadi Kalloo and Konstantinos Liopyris and Nabin Mishra and Harald Kittler and Allan Halpern}, year={2018}, eprint={1710.05006}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/1710.05006}, } @article{hernandezperez2024, author={Hern\acute{a}ndez-P\acute{e}rez, C. and others}, title={BCN20000: Dermoscopic lesions in the wild}, journal={Scientific Data}, volume={11}, number={1}, pages={641}, year={2024} } %%%%%%%%%%%%%%%%%%%%%%%test.bib%%%%%%% from Anvi Kumatr Paper-frontier %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @article{argenziano98, author = {Argenziano, Giuseppe and Fabbrocini, Gabriella and Carli, Paolo and De Giorgi, Vincenzo and Sammarco, Elena and Delfino, Mario}, title = {Epiluminescence Microscopy for the Diagnosis of Doubtful Melanocytic Skin Lesions: Comparison of the ABCD Rule of Dermatoscopy and a New 7-Point Checklist Based on Pattern Analysis}, journal = {Archives of Dermatology}, volume = {134}, number = {12}, pages = {1563-1570}, year = {1998}, month = {12}, abstract = {To compare the reliability of a new 7-point checklist based on simplified epiluminescence microscopy (ELM) pattern analysis with the ABCD rule of dermatoscopy and standard pattern analysis for the diagnosis of clinically doubtful melanocytic skin lesions.In a blind study, ELM images of 342 histologically proven melanocytic skin lesions were evaluated for the presence of 7 standard criteria that we called the "ELM 7-point checklist." For each lesion, "overall" and "ABCD scored" diagnoses were recorded. From a training set of 57 melanomas and 139 atypical non-melanomas, odds ratios were calculated to create a simple diagnostic model based on identification of major and minor criteria for the "7-point scored" diagnosis. A test set of 60 melanomas and 86 atypical non-melanomas was used for model validation and was then presented to 2 less experienced ELM observers, who recorded the ABCD and 7-point scored diagnoses.University medical centers.A sample of patients with excised melanocytic lesions.Sensitivity, specificity, and accuracy of the models for diagnosing melanoma.From the total combined sets, the 7-point checklist gave a sensitivity of 95\% and a specificity of 75\% compared with 85\% sensitivity and 66\% specificity using the ABCD rule and 91\% sensitivity and 90\% specificity using standard pattern analysis (overall ELM diagnosis). Compared with the ABCD rule, the 7-point method allowed less experienced observers to obtain higher diagnostic accuracy values.The ELM 7-point checklist provides a simplification of standard pattern analysis because of the low number of features to identify and the scoring diagnostic system. As with the ABCD rule, it can be easily learned and easily applied and has proven to be reliable in diagnosing melanoma.-->}, issn = {0003-987X}, doi = {10.1001/archderm.134.12.1563}, url = {https://doi.org/10.1001/archderm.134.12.1563}, eprint = {https://jamanetwork.com/journals/jamadermatology/articlepdf/189703/dst8031.pdf}, } @misc{ISIC-dataset, author = "ISIC-Archive", title = "ISIC Archive REST API Documentation", year = "Accessed on January 2021", doi = "", address = "\texttt{https://\-isic-archive.\-com/\-api/\-v1/\-}", URL = "https://isic-archive.com/api/v1/", } @Article{baba2024, AUTHOR = {Baba, Peerzada Umar Farooq and Hassan, Ashfaq ul and Khurshid, Junaid and Wani, Adil Hafeez}, TITLE = {Basal Cell Carcinoma: Diagnosis, Management and Prevention}, JOURNAL = {Journal of Molecular Pathology}, VOLUME = {5}, YEAR = {2024}, NUMBER = {2}, PAGES = {153--170}, URL = {https://www.mdpi.com/2673-5261/5/2/10}, ISSN = {2673-5261}, ABSTRACT = {Basal cell carcinoma (BCC) is a slow-growing, locally aggressive, rarely metastasizing, low-grade cutaneous neoplasm that arises from the epidermal basal layer and invades the adjoining tissues. It is the most common skin cancer. It is fairly common in fair Caucasians and quite uncommon in dark-skinned populations. It contributes to 65–75\% of cutaneous malignancies in whites and 20–30\% in Asian Indians. The most important causal factors appear to be radiation exposure and genetic predisposition. It may present as a nonhealing lesion that occasionally bleeds or as a pruritic lesion with no symptoms. Tumours rarely spread to regional lymph nodes. The clinical appearances and morphology of BCC are diverse. Clinical types include nodular, cystic, superficial, pigmented, morphoeaform, (sclerosing), keratotic and fibroepithelioma of Pinkus. Most of the lesions appear on the head and neck, usually above the line joining the tragus and the angle of the mouth. A biopsy should be performed on all lesions suspected of BCC. The primary aim of treatment is the complete excision of the tumour tissue. Other treatment modalities include cryotherapy, immunomodulatory drugs, laser treatment or locally applicable chemotherapeutic agents. Prevention consists of lifestyle changes such as avoiding sunburn, tanning beds and prolonged direct sun exposure, shade seeking, sunscreen application on the skin, and physical barrier methods such as protective clothing, hats and sunglasses. Regular sunscreen use in childhood and adolescence seems more beneficial than in adulthood.}, DOI = {10.3390/jmp5020010} } @misc{breiman2001, author = "Leo Breiman", title = "Random Forests.", year = "2001", doi = "", URL = "https://www.stat.berkeley.edu/~breiman/randomforest2001.pdf", } @article{brinker2019, title = {A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task}, journal = {European Journal of Cancer}, volume = {111}, pages = {148-154}, year = {2019}, issn = {0959-8049}, doi = {https://doi.org/10.1016/j.ejca.2019.02.005}, url = {https://www.sciencedirect.com/science/article/pii/S0959804919301443}, author = {Titus J. Brinker and Achim Hekler and Alexander H. Enk and Joachim Klode and Axel Hauschild and Carola Berking and Bastian Schilling and Sebastian Haferkamp and Dirk Schadendorf and Stefan Fröhling and Jochen S. Utikal and Christof {von Kalle} and Wiebke Ludwig-Peitsch and Judith Sirokay and Lucie Heinzerling and Magarete Albrecht and Katharina Baratella and Lena Bischof and Eleftheria Chorti and Anna Dith and Christina Drusio and Nina Giese and Emmanouil Gratsias and Klaus Griewank and Sandra Hallasch and Zdenka Hanhart and Saskia Herz and Katja Hohaus and Philipp Jansen and Finja Jockenhöfer and Theodora Kanaki and Sarah Knispel and Katja Leonhard and Anna Martaki and Liliana Matei and Johanna Matull and Alexandra Olischewski and Maximilian Petri and Jan-Malte Placke and Simon Raub and Katrin Salva and Swantje Schlott and Elsa Sody and Nadine Steingrube and Ingo Stoffels and Selma Ugurel and Wiebke Sondermann and Anne Zaremba and Christoffer Gebhardt and Nina Booken and Maria Christolouka and Kristina Buder-Bakhaya and Therezia Bokor-Billmann and Alexander Enk and Patrick Gholam and Holger Hänßle and Martin Salzmann and Sarah Schäfer and Knut Schäkel and Timo Schank and Ann-Sophie Bohne and Sophia Deffaa and Katharina Drerup and Friederike Egberts and Anna-Sophie Erkens and Benjamin Ewald and Sandra Falkvoll and Sascha Gerdes and Viola Harde and Axel Hauschild and Marion Jost and Katja Kosova and Laetitia Messinger and Malte Metzner and Kirsten Morrison and Rogina Motamedi and Anja Pinczker and Anne Rosenthal and Natalie Scheller and Thomas Schwarz and Dora Stölzl and Federieke Thielking and Elena Tomaschewski and Ulrike Wehkamp and Michael Weichenthal and Oliver Wiedow and Claudia Maria Bär and Sophia Bender-Säbelkampf and Marc Horbrügger and Ante Karoglan and Luise Kraas and Jörg Faulhaber and Cyrill Geraud and Ze Guo and Philipp Koch and Miriam Linke and Nolwenn Maurier and Verena Müller and Benjamin Thomas and Jochen Sven Utikal and Ali Saeed M. Alamri and Andrea Baczako and Carola Berking and Matthias Betke and Carolin Haas and Daniela Hartmann and Markus V. Heppt and Katharina Kilian and Sebastian Krammer and Natalie Lidia Lapczynski and Sebastian Mastnik and Suzan Nasifoglu and Cristel Ruini and Elke Sattler and Max Schlaak and Hans Wolff and Birgit Achatz and Astrid Bergbreiter and Konstantin Drexler and Monika Ettinger and Sebastian Haferkamp and Anna Halupczok and Marie Hegemann and Verena Dinauer and Maria Maagk and Marion Mickler and Biance Philipp and Anna Wilm and Constanze Wittmann and Anja Gesierich and Valerie Glutsch and Katrin Kahlert and Andreas Kerstan and Bastian Schilling and Philipp Schrüfer}, keywords = {Melanoma, Artificial intelligence, Diagnostics, Skin cancer}, abstract = {Background Recent studies have demonstrated the use of convolutional neural networks (CNNs) to classify images of melanoma with accuracies comparable to those achieved by board-certified dermatologists. However, the performance of a CNN exclusively trained with dermoscopic images in a clinical image classification task in direct competition with a large number of dermatologists has not been measured to date. This study compares the performance of a convolutional neuronal network trained with dermoscopic images exclusively for identifying melanoma in clinical photographs with the manual grading of the same images by dermatologists. Methods We compared automatic digital melanoma classification with the performance of 145 dermatologists of 12 German university hospitals. We used methods from enhanced deep learning to train a CNN with 12,378 open-source dermoscopic images. We used 100 clinical images to compare the performance of the CNN to that of the dermatologists. Dermatologists were compared with the deep neural network in terms of sensitivity, specificity and receiver operating characteristics. Findings The mean sensitivity and specificity achieved by the dermatologists with clinical images was 89.4\% (range: 55.0\%–100\%) and 64.4\% (range: 22.5\%–92.5\%). At the same sensitivity, the CNN exhibited a mean specificity of 68.2\% (range 47.5\%–86.25\%). Among the dermatologists, the attendings showed the highest mean sensitivity of 92.8\% at a mean specificity of 57.7\%. With the same high sensitivity of 92.8\%, the CNN had a mean specificity of 61.1\%. Interpretation For the first time, dermatologist-level image classification was achieved on a clinical image classification task without training on clinical images. The CNN had a smaller variance of results indicating a higher robustness of computer vision compared with human assessment for dermatologic image classification tasks.} } @techreport{cancer, author = "WHO-Cancer", title = "Cancer", mynote = "", key = "melanoma", institution = "World Health Organization", address = "https://\-www.\-who.\-int/\-health-topics/\-cancer\#tab=tab\_1", URL = "https://www.who.int/health-topics/cancer#tab=tab_1", year = "Accessed on January 2021" } @techreport{cancerStat2022, author = "Cancer.gov", title = "Cancer Statistics", mynote = "", key = "Skin", institution = "", address = "", URL = "https://seer.cancer.gov/statistics-network/explorer/application.html?site=53&data_type=5&graph_type=11&compareBy=sex&chk_sex_3=3&chk_sex_2=2&series=9&age_range=1&advopt_precision=1&hdn_view=0&advopt_show_apc=on&advopt_display=2#resultsRegion0", year = "Accessed on January 2025" } @techreport{cancerORG, author = "American Cancer-Society", title = "Melanoma Skin Cancer", key = "melanoma", mynote = "", institution = "American Cancer Society", address = "\texttt{https://\-www.\-cancer.\-org/\-cancer/\-melanoma-skin-cancer.\-html}", url = "https://www.cancer.org/cancer/melanoma-skin-cancer.html", year = "Accessed on January 2021" } @article{celebi2007, title = {A methodological approach to the classification of dermoscopy images}, journal = {Computerized Medical Imaging and Graphics}, volume = {31}, number = {6}, pages = {362-373}, year = {2007}, issn = {0895-6111}, doi = {https://doi.org/10.1016/j.compmedimag.2007.01.003}, url = {https://www.sciencedirect.com/science/article/pii/S0895611107000146}, author = {M. Emre Celebi and Hassan A. Kingravi and Bakhtiyar Uddin and Hitoshi Iyatomi and Y. Alp Aslandogan and William V. Stoecker and Randy H. Moss}, keywords = {Skin cancer, Dermoscopy, Melanoma, Classification, Support vector machine, Model selection}, abstract = {In this paper a methodological approach to the classification of pigmented skin lesions in dermoscopy images is presented. First, automatic border detection is performed to separate the lesion from the background skin. Shape features are then extracted from this border. For the extraction of color and texture related features, the image is divided into various clinically significant regions using the Euclidean distance transform. This feature data is fed into an optimization framework, which ranks the features using various feature selection algorithms and determines the optimal feature subset size according to the area under the ROC curve measure obtained from support vector machine classification. The issue of class imbalance is addressed using various sampling strategies, and the classifier generalization error is estimated using Monte Carlo cross validation. Experiments on a set of 564 images yielded a specificity of 92.34% and a sensitivity of 93.33%.} } @article{combalia2020, title={Squamous Cell Carcinoma: An Update on Diagnosis and Treatment}, volume={10}, url={https://dpcj.org/index.php/dpc/article/view/dermatol-pract-concept-articleid-dp1003a66}, DOI={10.5826/dpc.1003a66}, abstractNote={Squamous cell carcinoma (SCC) accounts for most nonmelanoma skin cancer–related metastatic disease and deaths. Histopathology and correct surgical excision remain the gold standard for the diagnosis and treatment of SCC; however, new diagnostic imaging techniques such as dermoscopy and reflectance confocal microscopy have increased the diagnostic accuracy in terms of early recognition, better differential diagnosis, more precise selection of areas to biopsy, and noninvasive monitoring of treatments. The therapeutic intervention in patients with severe actinic damage and multiple in situ/low-risk SCC, and the development of innovative treatments such as epidermal growth factor receptor inhibitors and immune checkpoint inhibitors for locally advanced and metastatic SCC, are improving considerably the approach to the disease. This review summarizes the up-to-date knowledge in the field of detection, treatment, and monitoring of cutaneous SCC.}, number={3}, journal={Dermatology Practical and Conceptual}, author={Combalia, Andrea and Carrera, Cristina}, year={2020}, month={Jun.}, pages={e2020066} } @misc{chang2017, title={Skin cancer reorganization and classification with deep neural network}, author={Hao Chang}, year={2017}, eprint={1703.00534}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/1703.00534}, } @InProceedings{chen2016, author = {Tianqi Chen and Carlos Guestrin}, title = {XGBoost: A Scalable Tree Boosting System}, booktitle = {KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining}, year = 2016, publisher = {KDD}, editor = {}, doi = "https://doi.org/10.1145/2939672.2939785", pages = {785-794} } @InProceedings{chen2022, author = {Richard J. Chen and Chengkuan Chen and Yicong Li and Tiffany Y. Chen and Andrew D. Trister and Rahul G. Krishnan and Faisal Mahmood}, title = {Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning}, booktitle = {CVPR, Computer Vision Foundation}, year = 2022, publisher = {CVPR}, editor = {}, doi = "", URL="https://openaccess.thecvf.com/content/CVPR2022/papers/Chen\_Scaling\_Vision\_Transformers\_to\_Gigapixel\_Images\_via\_Hierarchical\_Self-Supervised\_Learning\_CVPR\_2022\_paper.pdf", pages = {16144-16155} } @Article{codella2018, author = "Noel Codella and Veronica Rotemberg and Philipp Tschandl and M. Emre Celebi and Stephen Dusza and David Gutman and Brian Helba and Aadi Kalloo and Konstantinos Liopyris and Michael Marchetti and Harald Kittler and Allan Halpern", title = "Skin Lesion Analysis Toward Melanoma Detection", pages = "1-12 ", year = "2018", address = "\texttt{https://\-arxiv.\-org/\-pdf/1902.\-03368.\-pdf}", URL = "https://arxiv.org/abs/1902.03368", journal = "A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)" } @misc{dataset1, author = "ISIC-Archive", title = "Dataset 1", year = "Accessed on January 2025", doi = "", address = "https://www.kaggle.com/competitions/siim-isic-melanoma-classification/data", URL = "https://www.kaggle.com/competitions/siim-isic-melanoma-classification/data", } @misc{dataset2, author = "ISIC-Archive", title = "Dataset 2", year = "Accessed on January 2025", doi = "", address = "https://www.kaggle.com/datasets/drscarlat/melanoma", URL = "https://www.kaggle.com/datasets/drscarlat/melanoma", } @misc{dataset3, author = "ISIC-Archive", title = "Dataset 3", year = "Accessed on January 2025", doi = "", address = " ", URL = "https://www.kaggle.com/datasets/hasnainjaved/melanoma-skin-cancer-dataset-of-10000-images", } @misc{dataset4, author = "ISIC-Archive", title = "Dataset 4", year = "Accessed on January 2025", doi = "", address = " ", URL = "https://www.kaggle.com/datasets/wanderdust/skin-lesion-analysis-toward-melanoma-detection?select=skin-lesions", } @misc{dataset5, author = "ISIC-Archive", title = "Dataset 5", year = "Accessed on January 2025", doi = "", address = " ", URL = "https://www.kaggle.com/datasets/nodoubttome/skin-cancer9-classesisic", } @misc{dataset6, author = "ISIC-Archive", title = "ISIC Archive REST API Documentation", year = "Accessed on January 2025", doi = "", address = " ", URL = "https://challenge.isic-archive.com/data/", } @Article{deng2014, author = "Li Deng and Dong Yu", title = "Deep Learning: Methods and Applications", volume = "7", number = "3-4", pages = "197-387", year = "2014", doi = "10.1561/2000000039", URL = "https://nowpublishers.com/article/Details/SIG-039", journal = "Foundations and Trends in Signal Processing" } @Article{dietterich2000, author = "T. G. Dietterich", title = "MCS 2000. Lecture Notes in Computer Science", volume = "1857", number = "", pages = "", year = "2000", doi = "https://doi.org/10.1007/3-540-45014-9_1", URL = "", journal = "Ensemble Methods in Machine Learning. In: Multiple Classifier Systems" } @misc{dosovitskiy2021, title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale}, author={Alexey Dosovitskiy and Lucas Beyer and Alexander Kolesnikov and Dirk Weissenborn and Xiaohua Zhai and Thomas Unterthiner and Mostafa Dehghani and Matthias Minderer and Georg Heigold and Sylvain Gelly and Jakob Uszkoreit and Neil Houlsby}, year={2021}, eprint={2010.11929}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2010.11929}, } @misc{fort2019, title={Deep Ensembles: A Loss Landscape Perspective}, author={Stanislav Fort and Clara Huiyi Hu and Balaji Lakshminarayanan}, year={2020}, url={https://openreview.net/forum?id=r1xZAkrFPr} } @Article{guo2019, author = "Yanhui Guo and Amira S. Ashour ", title = "Neutrosophic multiple deep convolutional neural network for skin dermoscopic image classification.", pages = "269-285 ", year = "2019", doi = "10.1016/B978-0-12-818148-5.00013-8", isbn = "9780128181485", journal = "In Book: Neutrosophic Set in Medical Image Analysis" } @Article{hekler2019, author = "Achim Hekler and Jochen S. Utikal and Alexander H. Enk and Axel Hauschild and Michael Weichenthal and Roman C. Maron and Carola Berking and Sebastian Haferkamp and Joachim Klode and Dirk Schadendorf and Bastian Schilling and Tim Holland-Letz and Benjamin Izar and Christof von Kalle and Stefan Fr{\"o}hling and Titus J. Brinker and Collaborators", title = "Superior skin cancer classification by the combination of human and artificial intelligence", volume = "120", pages = "114-121", year = "2019", doi = "10.1016/j.ejca.2019.07.019", URL = "https://www.ejcancer.com/action/showPdf?pii=S0959-8049\%2819\%2930427-7", journal = "European Journal of Cancer" } @Article{esteva2017, author = "Andre Esteva and Brett Kuprel and Roberto A. Novoa and Justin Ko and Susan M. Swetter and Helen M. Blau and Sebastian Thrun", title = "Dermatologist-level classification of skin cancer with deep neural networks", volume = "542", pages = "115-118", year = "2017", doi = "10.1038/nature21056", URL = "https://www.nature.com/articles/nature21056", journal = "Nature" } @Article{ghanem2023, AUTHOR = {Ghanem, Marc and Ghaith, Abdul Karim and El-Hajj, Victor Gabriel and Bhandarkar, Archis and de Giorgio, Andrea and Elmi-Terander, Adrian and Bydon, Mohamad}, TITLE = {Limitations in Evaluating Machine Learning Models for Imbalanced Binary Outcome Classification in Spine Surgery: A Systematic Review}, JOURNAL = {Brain Sciences}, VOLUME = {13}, YEAR = {2023}, NUMBER = {12}, ARTICLE-NUMBER = {1723}, URL = {https://www.mdpi.com/2076-3425/13/12/1723}, PubMedID = {38137171}, ISSN = {2076-3425}, ABSTRACT = {Clinical prediction models for spine surgery applications are on the rise, with an increasing reliance on machine learning (ML) and deep learning (DL). Many of the predicted outcomes are uncommon; therefore, to ensure the models’ effectiveness in clinical practice it is crucial to properly evaluate them. This systematic review aims to identify and evaluate current research-based ML and DL models applied for spine surgery, specifically those predicting binary outcomes with a focus on their evaluation metrics. Overall, 60 papers were included, and the findings were reported according to the PRISMA guidelines. A total of 13 papers focused on lengths of stay (LOS), 12 on readmissions, 12 on non-home discharge, 6 on mortality, and 5 on reoperations. The target outcomes exhibited data imbalances ranging from 0.44\% to 42.4\%. A total of 59 papers reported the model’s area under the receiver operating characteristic (AUROC), 28 mentioned accuracies, 33 provided sensitivity, 29 discussed specificity, 28 addressed positive predictive value (PPV), 24 included the negative predictive value (NPV), 25 indicated the Brier score with 10 providing a null model Brier, and 8 detailed the F1 score. Additionally, data visualization varied among the included papers. This review discusses the use of appropriate evaluation schemes in ML and identifies several common errors and potential bias sources in the literature. Embracing these recommendations as the field advances may facilitate the integration of reliable and effective ML models in clinical settings.}, DOI = {10.3390/brainsci13121723} } @Article{gurung2020, author = "S. Gurung and Y.R. Gao", booktitle="2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)", title = "Classification of Melanoma (Skin Cancer) using Convolutional Neural Network", volume = "", number = "", pages = "1-8", year = "2020", doi = "10.1109/CITISIA50690.2020.9371829", URL = "https://ieeexplore.ieee.org/document/9371829", journal = "2020 5th International Conference on Innovative Technologies in Intelligent Systems and Industrial Applications (CITISIA)" } @Article{haenssle2018, author = "Holger Haenssle and Christine Fink and R Schneiderbauer and Ferdinand Toberer", title = "Man against Machine: Diagnostic performance of a deep learning convolutional neural network for dermoscopic melanoma recognition in comparison to 58 dermatologists", volume = "29", number = "1", pages = "1836-1842", year = "2018", doi = "10.1093/annonc/mdy166", URL = "https://www.researchgate.net/publication/325473733_Man_against_Machine_Diagnostic_performance_of_a_deep_learning_convolutional_neural_network_for_dermoscopic_melanoma_recognition_in_comparison_to_58_dermatologists", journal = "Annals of Oncology" } @INPROCEEDINGS{hatamizadeh2022, author={Ali Hatamizadeh and Yucheng Tang and Vishwesh Nath and Dong Yang and Andriy Myronenko and Bennett Landman and Holger R. Roth and Daguang Xu}, booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, title={UNETR: Transformers for 3D Medical Image Segmentation}, year={2022}, volume={}, number={}, pages={574-584}, keywords={}, doi={}, URL={https://openaccess.thecvf.com/content/WACV2022/papers/Hatamizadeh\_UNETR\_Transformers\_for\_3D\_Medical\_Image\_Segmentation\_WACV\_2022\_paper.pdf} } @Article{holmes2018, author = "G Alden Holmes and Janna M Vassantachart and Brittanya A Limone and Michael Zumwalt and Jane Hirokane and Sharon E Jacob", title = "Using Dermoscopy to Identify Melanoma and Improve Diagnostic Discrimination", volume = "35", number = "4", pages = "S39-S45", year = "2024", doi = "", URL = "https://pmc.ncbi.nlm.nih.gov/articles/PMC6375419/", journal = "Federal Practitioner" } @techreport{kaggle, author = "SIIM & ISIC ", title = "SIIM-ISIC Melanoma Classification", mynote = "", institution = "Kaggle", address = "\texttt{https://\-www.\-kaggle.\-com/\-c/\-siim-isic-melanoma-classification/\-}", url = "https://www.kaggle.com/c/siim-isic-melanoma-classification/", year = "Accessed on January 2021" } @Article{kawahara2016, author = "J. Kawahara and A. Ben-Cohen and G. Hamarneh", title = "Multi-resolution-tract cnn with hybrid pretrained and priori feature for skin lesion segmentation", pages = "1-12 ", year = "2018", address = "\texttt{https://www.cs.sfu.ca/\~hamarneh/ecopy/miccai\_mlmi2016a.pdf}", URL = "https://www.cs.sfu.ca/~hamarneh/ecopy/miccai_mlmi2016a.pdf", journal = "In Deep Learning and Data Labeling for Medical Applications" } @Article{loh2025, author="Loh, De Rong and Hill, Elliot D and Liu, Nan and Dawson, Geraldine and Engelhard, Matthew M", title="Limitations of Binary Classification for Long-Horizon Diagnosis Prediction and Advantages of a Discrete-Time Time-to-Event Approach: Empirical Analysis", journal="JMIR AI", year="2025", month="Mar", day="27", volume="4", pages="e62985", keywords="machine learning; artificial intelligence; deep learning; predictive models; practical models; early detection; electronic health records; right-censoring; survival analysis; distributional shifts", abstract="Background: A major challenge in using electronic health records (EHR) is the inconsistency of patient follow-up, resulting in right-censored outcomes. This becomes particularly problematic in long-horizon event predictions, such as autism and attention-deficit/hyperactivity disorder (ADHD) diagnoses, where a significant number of patients are lost to follow-up before the outcome can be observed. Consequently, fully supervised methods such as binary classification (BC), which are trained to predict observed diagnoses, are substantially affected by the probability of sufficient follow-up, leading to biased results. Objective: This empirical analysis aims to characterize BC's inherent limitations for long-horizon diagnosis prediction from EHR; and quantify the benefits of a specific time-to-event (TTE) approach, the discrete-time neural network (DTNN). Methods: Records within the Duke University Health System EHR were analyzed, extracting features such as ICD-10 (International Classification of Diseases, Tenth Revision) diagnosis codes, medications, laboratories, and procedures. We compared a DTNN to 3 BC approaches and a deep Cox proportional hazards model across 4 clinical conditions to examine distributional patterns across various subgroups. Time-varying area under the receiving operating characteristic curve (AUCt) and time-varying average precision (APt) were our primary evaluation metrics. Results: TTE models consistently had comparable or higher AUCt and APt than BC for all conditions. At clinically relevant operating time points, the area under the receiving operating characteristic curve (AUC) values for DTNNYOB≤2020 (year-of-birth) and DCPHYOB≤2020 (deep Cox proportional hazard) were 0.70 (95{\%} CI 0.66‐0.77) and 0.72 (95{\%} CI 0.66‐0.78) at t=5 for autism, 0.72 (95{\%} CI 0.65‐0.76) and 0.68 (95{\%} CI 0.62‐0.74) at t=7 for ADHD, 0.72 (95{\%} CI 0.70‐0.75) and 0.71 (95{\%} CI 0.69‐0.74) at t=1 for recurrent otitis media, and 0.74 (95{\%} CI 0.68‐0.82) and 0.71 (95{\%} CI 0.63‐0.77) at t=1 for food allergy, compared to 0.6 (95{\%} CI 0.55‐0.66), 0.47 (95{\%} CI 0.40‐0.54), 0.73 (95{\%} CI 0.70‐0.75), and 0.77 (95{\%} CI 0.71‐0.82) for BCYOB≤2020, respectively. The probabilities predicted by BC models were positively correlated with censoring times, particularly for autism and ADHD prediction. Filtering strategies based on YOB or length of follow-up only partially corrected these biases. In subgroup analyses, only DTNN predicted diagnosis probabilities that accurately reflect actual clinical prevalence and temporal trends. Conclusions: BC models substantially underpredicted diagnosis likelihood and inappropriately assigned lower probability scores to individuals with earlier censoring. Common filtering strategies did not adequately address this limitation. TTE approaches, particularly DTNN, effectively mitigated bias from the censoring distribution, resulting in superior discrimination and calibration performance and more accurate prediction of clinical prevalence. Machine learning practitioners should recognize the limitations of BC for long-horizon diagnosis prediction and adopt TTE approaches. The DTNN in particular is well-suited to mitigate the effects of right-censoring and maximize prediction performance in this setting. ", issn="2817-1705", doi="10.2196/62985", url="https://ai.jmir.org/2025/1/e62985", url="https://doi.org/10.2196/62985" } @Article{massone2021, AUTHOR = {Massone, Cesare and Hofman-Wellenhof, Rainer and Chiodi, Stefano and Sola, Simona}, TITLE = {Dermoscopic Criteria, Histopathological Correlates and Genetic Findings of Thin Melanoma on Non-Volar Skin}, JOURNAL = {Genes}, VOLUME = {12}, YEAR = {2021}, NUMBER = {8}, ARTICLE-NUMBER = {1288}, URL = {https://www.mdpi.com/2073-4425/12/8/1288}, PubMedID = {34440462}, ISSN = {2073-4425}, ABSTRACT = {Dermoscopy is a non-invasive, in vivo technique that allows the visualization of subsurface skin structures in the epidermis, at the dermoepidermal junction, and in the upper dermis. Dermoscopy brought a new dimension in evaluating melanocytic skin neoplasms (MSN) also representing a link between clinical and pathologic examination of any MSN. However, histopathology remains the gold standard in diagnosing MSN. Dermoscopic–pathologic correlation enhances the level of quality of MSN diagnosis and increases the level of confidence of pathologists. Melanoma is one of the most genetically predisposed among all cancers in humans. The genetic landscape of melanoma has been described in the last years but is still a field in continuous evolution. Melanoma genetic markers play a role not only in melanoma susceptibility, initiation, and progression but also in prognosis and therapeutic decisions. Several studies described the dermoscopic specific criteria and predictors for melanoma and their histopathologic correlates, but only a few studies investigated the correlation among dermoscopy, pathology, and genetic of MSN. The aim of this work is to review the published data about dermoscopic features of melanoma, their histopathological correlates with regards also to genetic alterations. Particularly, this review will focus on low-CSD (cumulative sun damage) melanoma or superficial spreading melanoma, high-CSD melanoma, and nevus-associated melanoma.}, DOI = {10.3390/genes12081288} } @article{li2023, title = {Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives}, journal = {Medical Image Analysis}, volume = {85}, pages = {102762}, year = {2023}, issn = {1361-8415}, doi = {https://doi.org/10.1016/j.media.2023.102762}, url = {https://www.sciencedirect.com/science/article/pii/S1361841523000233}, author = {Jun Li and Junyu Chen and Yucheng Tang and Ce Wang and Bennett A. Landman and S. Kevin Zhou}, keywords = {Transformer, Medical imaging, Survey}, abstract = {Transformer, one of the latest technological advances of deep learning, has gained prevalence in natural language processing or computer vision. Since medical imaging bear some resemblance to computer vision, it is natural to inquire about the status quo of Transformers in medical imaging and ask the question: can the Transformer models transform medical imaging? In this paper, we attempt to make a response to the inquiry. After a brief introduction of the fundamentals of Transformers, especially in comparison with convolutional neural networks (CNNs), and highlighting key defining properties that characterize the Transformers, we offer a comprehensive review of the state-of-the-art Transformer-based approaches for medical imaging and exhibit current research progresses made in the areas of medical image segmentation, recognition, detection, registration, reconstruction, enhancement, etc. In particular, what distinguishes our review lies in its organization based on the Transformer’s key defining properties, which are mostly derived from comparing the Transformer and CNN, and its type of architecture, which specifies the manner in which the Transformer and CNN are combined, all helping the readers to best understand the rationale behind the reviewed approaches. We conclude with discussions of future perspectives.} } @ARTICLE{omiye2023, AUTHOR={Omiye, Jesutofunmi A. and Gui, Haiwen and Daneshjou, Roxana and Cai, Zhuo Ran and Muralidharan, Vijaytha }, TITLE={Principles, applications, and future of artificial intelligence in dermatology}, JOURNAL={Frontiers in Medicine}, VOLUME={Volume 10 - 2023}, YEAR={2023}, URL={https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2023.1278232}, DOI={10.3389/fmed.2023.1278232}, ISSN={2296-858X}, ABSTRACT={This paper provides an overview of artificial-intelligence (AI), as applied to dermatology. We focus our discussion on methodology, AI applications for various skin diseases, limitations, and future opportunities. We review how the current image-based models are being implemented in dermatology across disease subsets, and highlight the challenges facing widespread adoption.Additionally, we discuss how the future of AI in dermatology might evolve and the emerging paradigm of large language, and multi-modal models to emphasize the importance of developing responsible, fair, and equitable models in dermatology.} } @Article{oztel2024, author = "Gozde Yolcu Oztel", title = "Vision transformer and CNN-based skin lesion analysis: classification of monkeypox", pages = "71909–71923 ", year = "2024", address = "", URL = "https://link.springer.com/article/10.1007/s11042-024-19757-w", journal = "Spriger Nature: Multimedia Tools and Applications" } @Article{radhika2023, author = "Vankayalapati Radhika and B Sai Chandana", title = "MSCDNet-based multi-class classification of skin cancer using dermoscopy images", volume = "", number = "", pages = "", year = "2023", doi = "10.7717/peerj-cs.1520", URL = "https://peerj.com/articles/cs-1520/", journal = "PeerJ Computer Science" } @techreport{radiation, author = "WHO", title = "Radiation: Ultraviolet (UV) radiation and skin cancer", mynote = "", institution = "World Health Organization", address = "\texttt{https://\-www.\-who.\-int/\-news-room/\-questions-and-answers/\-item/\-radiation-ultraviolet-(uv)-radiation-and-skin-cancer}", url = "https://www.who.int/news-room/questions-and-answers/item/radiation-ultraviolet-(uv)-radiation-and-skin-cancer", year = "Accessed on January 2021" } @Article{rigel2013, author = "Darrell S. Rigel and Linda F. Stein", title = "The importance of early diagnosis and treatment of actinic keratosis", volume = "68", number = "1", pages = "", year = "2013", doi = "https://doi.org/10.1016/j.jaad.2012.10.001", URL = "https://www.jaad.org/article/S0190-9622(12)01063-8/abstract", journal = "Journal of the American Academy of Dermatology" } @INPROCEEDINGS{mahmud2024, author={Al Mahmud and Hanieh Ajami and Md Sami Ul Hoque and Roshan Silwal and Mahdi Kargar Nigjeh and and Scott E. Umbaugh}, booktitle={Proc. SPIE 13137, Applications of Digital Image Processing XLVII, 1313705}, title={Comparison of performance of two deep learning models for classification of skin lesions using image resampling technique for data augmentation}, year={2024}, volume={}, number={}, pages={}, keywords={}, doi={https://doi.org/10.1117/12.3027916}} @Article{milton2018, author = "M. A. A. Milton", title = "Automated skin Lesion classification using ensemble of deep neural networks. In Isic 2018: Skin Lesion ANALYSIS Towards melanoma Detection Challenge", volume = " ", number = " ", pages = "225 - 228 ", year = "2018", doi = "arXiv:1901.10802", URL = "https://arxiv.org/abs/1901.10802", journal = "In ISIC 2018" } @techreport{moolayil2019, author = "J.J. Moolayil ", title = "A Layman's Guide to Deep Neural Networks", mynote = "July 24, 2019", institution = "Deep Learning Foundations", address = "\texttt{https://\-towardsdatascience.\-com/\-a-laymans-guide-to-deep-neural-networks-ddcea24847fb}", url = "https://towardsdatascience.com/a-laymans-guide-to-deep-neural-networks-ddcea24847fb", year = "Accessed on July 2021" } @Article{muhammad2024, author = "Muhammad Zawad Mahmud and Md Shihab Reza and Shahran Rahman Alve and Samiha Islam and and Nafis Fahmid", title = "Advance Transfer Learning Approach for Identification of Multiclass Skin Disease with LIME Explainable AI Technique", volume = "", number = "", pages = "", year = "2024", doi = "https://doi.org/10.1101/2024.12.02.24318311", URL = "https://www.medrxiv.org/content/10.1101/2024.12.02.24318311v2", journal = "IEEE International Conference on Computer and Information Technology (ICCIT 2024)" } @techreport{nci, author = "NCI", title = "National Cancer Institute", mynote = "", key = "Skin", institution = "National Cancer Institute", address = "", URL = "https://www.cancer.gov/types/skin", year = "Accessed on January 2025" } @Article{pande2025, author = "Yadnyesh Pande and Savita S. Wagre and Somesh Alone and Pratik Papanwar", title = "Skin Lesion Classification Using Deep Learning", volume = "13", number = "6", pages = "", year = "2025", doi = "https://doi.org/10.22214/ijraset.2025.72450", URL = "https://www.ijraset.com/best-journal/skin-lesion-classification-using-deep-learning", journal = "International Journal for Research in Applied Science and Engineering Technology (IJRASET)" } @techreport{saha2018, author = "Sumit Saha", title = "A Comprehensive Guide to Convolutional Neural Networks — the ELI5 way", mynote = "", institution = "Towarda Data Science", address = "\texttt{https://\-towardsdatascience.\-com/\-a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53}", url = "https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53", year = "Accessed on July 2021" } @Article{salam2024, author = "Arisha Salam and Abhineesh N", title = "Revolutionizing dermatology: The role of artificial intelligence in clinical practice", volume = "10", number = "2", pages = "107-112", year = "2024", doi = "10.18231/j.ijced.2024.021", URL = "https://ijced.org/archive/volume/10/issue/2/article/7921", journal = "IP Indian Journal of Clinical and Experimental Dermatology" } @Article{tahir2023, AUTHOR = {Tahir, Maryam and Naeem, Ahmad and Malik, Hassaan and Tanveer, Jawad and Naqvi, Rizwan Ali and Lee, Seung-Won}, TITLE = {DSCC\_Net: Multi-Classification Deep Learning Models for Diagnosing of Skin Cancer Using Dermoscopic Images}, JOURNAL = {Cancers}, VOLUME = {15}, YEAR = {2023}, NUMBER = {7}, ARTICLE-NUMBER = {2179}, URL = {https://www.mdpi.com/2072-6694/15/7/2179}, PubMedID = {37046840}, ISSN = {2072-6694}, ABSTRACT = {Skin cancer is one of the most lethal kinds of human illness. In the present state of the health care system, skin cancer identification is a time-consuming procedure and if it is not diagnosed initially then it can be threatening to human life. To attain a high prospect of complete recovery, early detection of skin cancer is crucial. In the last several years, the application of deep learning (DL) algorithms for the detection of skin cancer has grown in popularity. Based on a DL model, this work intended to build a multi-classification technique for diagnosing skin cancers such as melanoma (MEL), basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanocytic nevi (MN). In this paper, we have proposed a novel model, a deep learning-based skin cancer classification network (DSCC_Net) that is based on a convolutional neural network (CNN), and evaluated it on three publicly available benchmark datasets (i.e., ISIC 2020, HAM10000, and DermIS). For the skin cancer diagnosis, the classification performance of the proposed DSCC_Net model is compared with six baseline deep networks, including ResNet-152, Vgg-16, Vgg-19, Inception-V3, EfficientNet-B0, and MobileNet. In addition, we used SMOTE Tomek to handle the minority classes issue that exists in this dataset. The proposed DSCC_Net obtained a 99.43\% AUC, along with a 94.17\%, accuracy, a recall of 93.76\%, a precision of 94.28\%, and an F1-score of 93.93\% in categorizing the four distinct types of skin cancer diseases. The rates of accuracy for ResNet-152, Vgg-19, MobileNet, Vgg-16, EfficientNet-B0, and Inception-V3 are 89.32\%, 91.68\%, 92.51\%, 91.12\%, 89.46\% and 91.82\%, respectively. The results showed that our proposed DSCC_Net model performs better as compared to baseline models, thus offering significant support to dermatologists and health experts to diagnose skin cancer.}, DOI = {10.3390/cancers15072179} } @misc{tan2021, title={EfficientNetV2: Smaller Models and Faster Training}, author={Mingxing Tan and Quoc V. Le}, year={2021}, eprint={2104.00298}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2104.00298}, } @techreport{timm, author = "PyTorch", title = "PyTorch Image Models", mynote = "", institution = "PyTorch", address = "", url = "https://pypi.org/project/timm/", year = "Accessed on July 2021" } @Article{tschandl2018, author = "P. Tschandl and C. Rosendahl and H. Kittler", title = "The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions", volume = "5", number = "180161", pages = "1-9", year = "2018", doi = "10.1038/sdata.2018.161", URL = "https://www.nature.com/articles/sdata2018161", journal = "Scientific Data" } @Article{ratul2019, author = "A.R. Ratul and M.H. Mozaffari and W.-S. Lee and E. Parimbelli", title = "Skin Lesions Classification Using Deep Learning Based on Dilated Convolution", volume = "2020", pages = "1-11", year = "2019", doi = "10.1101/860700", URL = "https://www.biorxiv.org/content/10.1101/860700v3", journal = "bioRxiv" } @Article{polonen2019, author = "Ilkka P{\"o}l{\"o}nen and Samuli Rahkonen and Leevi Aleksi Annala and Noora Neittaanm{\"a}ki", title = "Convolutional neural networks in skin cancer detection using spatial and spectral domain", pages = "302-309", year = "2019", doi = "10.1117/12.2509871", URL = "https://www.researchgate.net/publication/331361258_Convolutional_neural_networks_in_skin_cancer_detection_using_spatial_and_spectral_domain", journal = "Photonics in Dermatology and Plastic Surgery 2019" } @Article{kosary2014, author = "Carol L Kosary and Sean F Altekruse and Jennifer Ruhl and Richard Lee and Lois Dickie", title = "Clinical and prognostic factors for melanoma of the skin using SEER registries: collaborative stage data collection system, version 1 and version 2", volume = "PMID: 25412392", number = "", pages = "3807-3814", year = "2014", doi = "10.1002/cncr.29050", URL = "https://pubmed.ncbi.nlm.nih.gov/25412392/", journal = "Wiley Online Library" } @Article{kreouzi2024, AUTHOR = {Kreouzi, Magdalini and Theodorakis, Nikolaos and Feretzakis, Georgios and Paxinou, Evgenia and Sakagianni, Aikaterini and Kalles, Dimitris and Anastasiou, Athanasios and Verykios, Vassilios S. and Nikolaou, Maria}, TITLE = {Deep Learning for Melanoma Detection: A Deep Learning Approach to Differentiating Malignant Melanoma from Benign Melanocytic Nevi}, JOURNAL = {Cancers}, VOLUME = {17}, YEAR = {2025}, NUMBER = {1}, ARTICLE-NUMBER = {28}, URL = {https://www.mdpi.com/2072-6694/17/1/28}, PubMedID = {39796659}, ISSN = {2072-6694}, ABSTRACT = {Background/Objectives: Melanoma, an aggressive form of skin cancer, accounts for a significant proportion of skin-cancer-related deaths worldwide. Early and accurate differentiation between melanoma and benign melanocytic nevi is critical for improving survival rates but remains challenging because of diagnostic variability. Convolutional neural networks (CNNs) have shown promise in automating melanoma detection with accuracy comparable to expert dermatologists. This study evaluates and compares the performance of four CNN architectures—DenseNet121, ResNet50V2, NASNetMobile, and MobileNetV2—for the binary classification of dermoscopic images. Methods: A dataset of 8825 dermoscopic images from DermNet was standardized and divided into training (80\%), validation (10\%), and testing (10\%) subsets. Image augmentation techniques were applied to enhance model generalizability. The CNN architectures were pre-trained on ImageNet and customized for binary classification. Models were trained using the Adam optimizer and evaluated based on accuracy, area under the receiver operating characteristic curve (AUC-ROC), inference time, and model size. The statistical significance of the differences was assessed using McNemar’s test. Results: DenseNet121 achieved the highest accuracy (92.30\%) and an AUC of 0.951, while ResNet50V2 recorded the highest AUC (0.957). MobileNetV2 combined efficiency with competitive performance, achieving a 92.19\% accuracy, the smallest model size (9.89 MB), and the fastest inference time (23.46 ms). NASNetMobile, despite its compact size, had a slower inference time (108.67 ms), and slightly lower accuracy (90.94\%). Performance differences among the models were statistically significant (p < 0.0001). Conclusions: DenseNet121 demonstrated a superior diagnostic performance, while MobileNetV2 provided the most efficient solution for deployment in resource-constrained settings. The CNNs show substantial potential for improving melanoma detection in clinical and mobile applications.}, DOI = {10.3390/cancers17010028} } @book{oshea2015, author = {Keiron O'Shea and Ryan Nash}, title = {An Introduction to Convolutional Neural Networks}, publisher = {arXiv}, address = {https://arxiv.org/abs/1511.08458}, year = 2015, } @INPROCEEDINGS{guo2018, author={Guo, Yanhui and Ashour, Amira S. and Si, Lei and Mandalaywala, Deep P}, booktitle={2018 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)}, title={Multiple Convolutional Neural Network for Skin Dermoscopic Image Classification}, year={2018}, volume={}, number={}, pages={365-369}, keywords={Lesions;Skin;Training;Melanoma;Testing;Deep learning;Predictive models;Conventional neural network;deep learning;dermoscopic images;multiple model;skin cancer}, doi={10.1109/ISSPIT.2018.8642669}} @Article{venugopal2021, author = "Vipin Venugopal and Malaya Kumar Nath and Sreejith Vidyadharan and Nikhil Francis Giji and Adithya Ramesh and Meera M.", title = "Detection of Melanoma using Deep Learning Techniques: A Review", volume = "", number = "", pages = "1--8", year = "2021", doi = "10.1109/ICCISc52257.2021.9484861", URL = "https://ijonest.net/index.php/ijonest/article/view/31", journal = "International Conference on Communication, Control and Information Sciences (ICCISc)" } @article{vestergaard2008, author = {Vestergaard, M.E. and Macaskill, P. and Holt, P.E. and Menzies, S.W.}, title = {Dermoscopy compared with naked eye examination for the diagnosis of primary melanoma: a meta‐analysis of studies performed in a clinical setting}, journal = {British Journal of Dermatology}, volume = {159}, number = {3}, pages = {669-676}, year = {2008}, month = {09}, abstract = {Background Dermoscopy is a noninvasive technique that enables the clinician to perform direct microscopic examination of diagnostic features, not seen by the naked eye, in pigmented skin lesions. Diagnostic accuracy of dermoscopy has previously been assessed in meta‐analyses including studies performed in experimental and clinical settings.Objectives To assess the diagnostic accuracy of dermoscopy for the diagnosis of melanoma compared with naked eye examination by performing a meta‐analysis exclusively on studies performed in a clinical setting.Methods We searched for publications from 1987 to January 2008 and found nine eligible studies. The selected studies compare diagnostic accuracy of dermoscopy with naked eye examination using a valid reference test on consecutive patients with a defined clinical presentation, performed in a clinical setting. Hierarchical summary receiver operator curve analysis was used to estimate the relative diagnostic accuracy for clinical examination with, and without, the use of dermoscopy.Results We found the relative diagnostic odds ratio for melanoma, for dermoscopy compared with naked eye examination, to be 15·6 [95\% confidence interval (CI) 2·9–83·7, P = 0·016]; removal of two outlier studies changed this to 9·0 (95\% CI 1·5–54·6, P = 0·03).Conclusions Dermoscopy is more accurate than naked eye examination for the diagnosis of cutaneous melanoma in suspicious skin lesions when performed in the clinical setting.}, issn = {0007-0963}, doi = {10.1111/j.1365-2133.2008.08713.x}, url = {https://doi.org/10.1111/j.1365-2133.2008.08713.x}, eprint = {https://academic.oup.com/bjd/article-pdf/159/3/669/47497540/bjd0669.pdf}, } @article{ye2024, title = {Deep learning algorithms for melanoma detection using dermoscopic images: A systematic review and meta-analysis}, journal = {Artificial Intelligence in Medicine}, volume = {155}, pages = {102934}, year = {2024}, issn = {0933-3657}, doi = {https://doi.org/10.1016/j.artmed.2024.102934}, url = {https://www.sciencedirect.com/science/article/pii/S0933365724001763}, author = {Zichen Ye and Daqian Zhang and Yuankai Zhao and Mingyang Chen and Huike Wang and Samuel Seery and Yimin Qu and Peng Xue and Yu Jiang}, keywords = {Deep learning, Melanoma, Human-machine comparison, Human-machine cooperation, Systematic review}, abstract = {Background Melanoma is a serious risk to human health and early identification is vital for treatment success. Deep learning (DL) has the potential to detect cancer using imaging technologies and many studies provide evidence that DL algorithms can achieve high accuracy in melanoma diagnostics. Objectives To critically assess different DL performances in diagnosing melanoma using dermatoscopic images and discuss the relationship between dermatologists and DL. Methods Ovid-Medline, Embase, IEEE Xplore, and the Cochrane Library were systematically searched from inception until 7th December 2021. Studies that reported diagnostic DL model performances in detecting melanoma using dermatoscopic images were included if they had specific outcomes and histopathologic confirmation. Binary diagnostic accuracy data and contingency tables were extracted to analyze outcomes of interest, which included sensitivity (SEN), specificity (SPE), and area under the curve (AUC). Subgroup analyses were performed according to human-machine comparison and cooperation. The study was registered in PROSPERO, CRD42022367824. Results 2309 records were initially retrieved, of which 37 studies met our inclusion criteria, and 27 provided sufficient data for meta-analytical synthesis. The pooled SEN was 82 \% (range 77–86), SPE was 87 \% (range 84–90), with an AUC of 0.92 (range 0.89–0.94). Human-machine comparison had pooled AUCs of 0.87 (0.84–0.90) and 0.83 (0.79–0.86) for DL and dermatologists, respectively. Pooled AUCs were 0.90 (0.87–0.93), 0.80 (0.76–0.83), and 0.88 (0.85–0.91) for DL, and junior and senior dermatologists, respectively. Analyses of human-machine cooperation were 0.88 (0.85–0.91) for DL, 0.76 (0.72–0.79) for unassisted, and 0.87 (0.84–0.90) for DL-assisted dermatologists. Conclusions Evidence suggests that DL algorithms are as accurate as senior dermatologists in melanoma diagnostics. Therefore, DL could be used to support dermatologists in diagnostic decision-making. Although, further high-quality, large-scale multicenter studies are required to address the specific challenges associated with medical AI-based diagnostics.} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% @article{kelly2016a, author = {Kelly, Derek and Vatsa, Avimanyou and Mayham, Wade and Ng\^{o}, Linh and Thompson, Addie and Kazic, Toni}, title = {An opinion on imaging challenges in phenotyping field crops}, year = {2016}, issue_date = {July 2016}, publisher = {Springer-Verlag}, address = {Berlin, Heidelberg}, volume = {27}, number = {5}, issn = {0932-8092}, url = {https://doi.org/10.1007/s00138-015-0728-4}, doi = {10.1007/s00138-015-0728-4}, abstract = {Almost all the world's food is grown in open fields, where plant phenotypes can be very different from those observed in greenhouses. Geneticists and agronomists studying food crops routinely detect, measure, and classify a wide variety of phenotypes in fields that contain many visually distinct types of a single crop. Augmenting humans in these tasks by automatically interpreting images raises some important and nontrivial challenges for research in computer vision. Nonetheless, the rewards for overcoming these obstacles could be exceptionally high for today's 7 billion people, let alone the 9.6 billion projected by 2050 (United Nations Department of Economic and Social Affairs, Population Division, World Population Prospects: The 2012 Revision). To stimulate dialog between researchers in computer vision and those in genetics and agronomy, we offer our views on three computational challenges that are central to many phenotyping tasks. These are disambiguating one plant from another; assigning an individual plant's organs to it; and identifying field phenotypes from those shown in archival images. We illustrate these challenges with annotated photographs of maize highlighting the regions of interest. We also describe some of the experimental, logistical, and photographic constraints on image collection and processing. While collecting the data sets needed for algorithmic experiments requires sustained collaboration and funding, the images we show and have posted should allow one to consider the problems, think of possible approaches, and decide on the next steps.}, journal = {Mach. Vision Appl.}, month = jul, pages = {681–694}, numpages = {14}, keywords = {Field phenotyping, Maize phenotypes, Organ assignment, Phenotype identification, Plant disambiguation, Registration, Segmentation, Species recognition} } @article{kelly2016, author = {Kelly, Derek and Vatsa, Avimanyou and Mayham, Wade and Kazic, Toni}, title = {Extracting complex lesion phenotypes in Zea mays}, year = {2016}, issue_date = {January 2016}, publisher = {Springer-Verlag}, address = {Berlin, Heidelberg}, volume = {27}, number = {1}, issn = {0932-8092}, url = {https://doi.org/10.1007/s00138-015-0718-6}, doi = {10.1007/s00138-015-0718-6}, abstract = {Complex phenotypes are of growing importance in agriculture and medicine. In Zea mays, the most widely produced crop in the world (United States Department of Agriculture. World Agricultural Production. United States Department of Agriculture, Foreign Agricultural Service, Washington, 2015), the disease lesion mimic mutants produce regions of discolored or necrotic tissue in otherwise healthy plants. These mutants are of particular interest due to their apparent action on immune response pathways, providing insight into how plants protect against infectious agents. These phenotypes vary considerably as a function of genotype and environmental conditions, making them a rich, though challenging, phenotypic problem. To segment and quantitate these lesions, we present a novel cascade of adaptive algorithms able to accurately segment the diversity of Z. mays lesions. First, multiresolution analysis of the image allows for salient features to be detected at multiple scales. Next, gradient vector diffusion enhances relevant gradient vectors while suppressing noise. Finally, an active contour algorithm refines the lesion boundary, producing a final segmentation for each lesion. We compare the results from this cascade with manual segmentations from human observers, demonstrating that our algorithm is comparable to humans while having the potential to speed analysis by several orders of magnitude.}, journal = {Mach. Vision Appl.}, month = jan, pages = {145–156}, numpages = {12}, keywords = {Multiresolution analysis (MRA), Maize lesions, Gradient vector diffusion, Complex phenotypes, Active contours} } @INPROCEEDINGS{kumar2021, author={Kumar, Ayushi and Kapelyan, Ari and Vatsa, Avimanyou K}, booktitle={2021 IEEE Integrated STEM Education Conference (ISEC)}, title={Classification of Skin Phenotype: Melanoma Skin Cancer}, year={2021}, volume={}, number={}, pages={247-247}, keywords={Visualization;Recurrent neural networks;Shape;Melanoma;Prediction algorithms;Skin;Classification algorithms}, doi={10.1109/ISEC52395.2021.9763999}} @book{vatsa2015, author = {A. Vatsa}, title = {Characterizing low-dimensional phenotypes by clustering}, publisher = {University of Missouri—Columbia}, address = {MO, USA}, year = 2015 } @book{vatsa2017, author = {A. Vatsa}, title = {An approach to clustering biological phenotypes}, publisher = {University of Missouri—Columbia}, address = {MO, USA}, year = 2017 } @Article{vatsa2021, author = "Avimanyou Vatsa", title = "SDFS: A Standardization Technique for Nonparametric Analysis", volume = "3", number = "1", pages = "30-43", year = "2021", doi = "", URL = "https://ijonest.net/index.php/ijonest/article/view/31", journal = "International Journal on Engineering, Science and Technology (IJonEST)" } @ARTICLE{kumarVatsa2022, AUTHOR={Ayushi Kumar and Avimanyou Vatsa}, TITLE={Untangling Classification Methods for Melanoma Skin Cancer}, JOURNAL={Frontiers in Big Data}, VOLUME={Volume 5 - 2022}, YEAR={2022}, URL={https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2022.848614}, DOI={10.3389/fdata.2022.848614}, ISSN={2624-909X}, ABSTRACT={Skin cancer is most common cancer in United State of America (USA). Skin cancer can affect anyone, regardless of skin color, race, gender, and age. The characteristics of skin lesion has an arbitrary shape, size, uneven and rough edge, and cannot be divided in half. Further, it is a leading cause of deaths worldwide. Every year, more than 5 million patients are newly diagnosed in USA. The deadliest and serious form of skin cancer is called melanoma. The diagnosis of melanoma has been done by visual examination and manual techniques by skilled doctors. It is time consuming process and highly prone to error. The skin images captured by dermoscopy eliminates the surface reflection of skin and gives better visualization of deeper levels of skin. In spite of these, image of skin lesion has many artifacts, noises, complex nature of lesion structure. Due to these complex natures of images, the border detection, feature extraction, and classification process is a complex problem. In order to identify and predict melanoma in early stage, there is need to classify images using better classification methods. Therefore, there is need to make an efficient, effective, and accurate melanoma identification, classification, and prediction such that it may be identified and classified in very early stage. The goal of this paper is to review and analyze the various deep neural network-based classification algorithms on skin images (ISIC dataset). Also, the performance algorithms are compared using five different parameters including ROC.}} @INPROCEEDINGS{kumar2022, author={Kumar, Ayushi and Vatsa, Avimanyou}, booktitle={2022 IEEE Integrated STEM Education Conference (ISEC)}, title={Influence of GFP GAN on Melanoma Classification}, year={2022}, volume={}, number={}, pages={334-339}, keywords={Measurement;Humanities;Veins;Optimization methods;Melanoma;Metadata;Generative adversarial networks;Melanoma;Skin Cancer;GFP GAN;CNN;RNN;XG-Boost.}, doi={10.1109/ISEC54952.2022.10025075}} @INPROCEEDINGS{vatsa2023, author={Vatsa, Avimanyou and Kumar, Arav and Vats, Savya and Kumar, Anvi}, booktitle={2023 IEEE Integrated STEM Education Conference (ISEC)}, title={Comparing the Performance of Classification Algorithms for Melanoma Skin Cancer}, year={2023}, volume={}, number={}, pages={375-380}, keywords={Support vector machines;Logistic regression;Melanoma;Boosting;Classification algorithms;Regression tree analysis;Random forests;Melanoma Skin Cancer;Machine Learning;Regression;Light Gradient Boosting Regression;Random Forest Regression}, doi={10.1109/ISEC57711.2023.10402205}} @INPROCEEDINGS{vatsa2023a, author={Vatsa, Avimanyou and Lee, Dohyun and Sullivan, Benen and Hogan, Daniel and Mittal, Amishi and Morton, Elise R. and Parzer, Harald F.}, booktitle={2023 IEEE Integrated STEM Education Conference (ISEC)}, title={Enumeration of Birds using Video Segmentation for a Better Understanding of Bird Behaviors}, year={2023}, volume={}, number={}, pages={179-186}, keywords={YOLO;Training;Tracking;Birds;Behavioral sciences;Statistics;Videos;Video Segmentation;YOLO;HOG;SSD;R-CNN;Bird Behavior;Climate Change;Sustainability;Ecology}, doi={10.1109/ISEC57711.2023.10402158}} @INPROCEEDINGS{kumar2023, author={Kumar, Arav and Vats, Savya and Kumar, Anvi and Vatsa, Avimanyou}, booktitle={2023 IEEE Integrated STEM Education Conference (ISEC)}, title={Challenges and Applications of AI in Healthcare: A Review}, year={2023}, volume={}, number={}, pages={174-178}, keywords={Costs;Hospitals;Computer viruses;Medical services;Artificial intelligence;Statistics;Medical diagnostic imaging;Healthcare;Artificial Intelligence (AI);Infectious Diseases;Skin Cancer}, doi={10.1109/ISEC57711.2023.10402195}} @INPROCEEDINGS{miller2022, author={Miller, Ava and Jan, Tyler R and Small, Q’Andre and Kumar, Ayushi and Vatsa, Avimanyou K}, booktitle={2022 IEEE Integrated STEM Education Conference (ISEC)}, title={GAN Assistance in Diagnosis of Melanoma}, year={2022}, volume={}, number={}, pages={232-232}, keywords={Melanoma;Generative adversarial networks;Prediction algorithms;Skin;Loss measurement;Generators;Classification algorithms}, doi={10.1109/ISEC54952.2022.10025328}} @INPROCEEDINGS{jan2022, author={Jan, Tyler R and Miller, Ava and Small, Q’Andre and Kumar, Ayushi and Vatsa, Avimanyou K}, booktitle={2022 IEEE Integrated STEM Education Conference (ISEC)}, title={Effect of Cycle GAN in Melanoma Classification}, year={2022}, volume={}, number={}, pages={195-195}, keywords={Hair;Measurement;Deep learning;Melanoma;Medical services;Skin;Planning}, doi={10.1109/ISEC54952.2022.10025273}} @INPROCEEDINGS{small2022, author={Small, Q’Andre and Vatsa, Avimanyou K and Jan, Tyler R and Miller, Ava and Kumar, Ayushi}, booktitle={2022 IEEE Integrated STEM Education Conference (ISEC)}, title={Unsupervised GAN for Melanoma}, year={2022}, volume={}, number={}, pages={357-357}, keywords={Recurrent neural networks;Image recognition;Melanoma;Medical services;Generative adversarial networks;Loss measurement;Skin}, doi={10.1109/ISEC54952.2022.10025272}} @Article{han2020, author = "Seung Seog Han and Ilwoo Park and Sung {Eun Chang} and Woohyung Lim and Myoung Shin Kim and Gyeong Hun Park and Je Byeong Chae and Chang Hun Huh and Jung-Im Na", title = "Augmented Intelligence Dermatology: Deep Neural Networks Empower Medical Professionals in Diagnosing Skin Cancer and Predicting Treatment Options for 134 Skin Disorders", volume = "140", number = "9", pages = "1753-1761", year = "2020", doi = "https://doi.org/10.1016/j.jid.2020.01.019", URL = " ", journal = "Journal of Investigative Dermatology" } @Article{vieira2025, author = "Jonathan Vieira and F\'abio Mendonca and Fernando Morgado-Dias", title = "Deep Learning Approaches for Skin Lesion Detection", volume = "14", number = "14", pages = "2785-2785", year = "2025", doi = "10.3390/electronics14142785", URL = "", journal = "Electronics" } @Article{ali2019, author = "R. Ali and R. C. Hardie and B. Narayanan Narayanan and S. De Silva", title = "Deep Learning Ensemble Methods for Skin Lesion Analysis towards Melanoma Detection", volume = "", number = "", pages = "311-316", year = "2019", doi = "10.1109/NAECON46414.2019.9058245", URL = "", journal = "2019 IEEE National Aerospace and Electronics Conference (NAECON), Dayton, OH, USA" } @article{huang2017, author = "Gao Huang and Yixuan Li and Geoff Pleiss and Zhuang Liu and John Hopcroft and Kilian Weinberger", year = "2017", month = "03", pages = "", title = "Snapshot Ensembles: Train 1, get M for free", doi = "10.48550/arXiv.1704.00109" } @Article{yuan2019, author = "Tze-An Yuan and Yunxia Lu and Karen Edwards and James Jakowatz and Frank L. Meyskens and Feng Liu-Smith", title = "Race-, Age-, and Anatomic Site-Specific Gender Differences in Cutaneous Melanoma Suggest Differential Mechanisms of Early- and Late-Onset Melanoma", volume = "", number = "", pages = "", year = "2019", doi = "10.3390/ijerph16060908", URL = "", journal = "Int. J. Environ. Res. Public Health" } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% ****start here %%%%%%%%%%%%%%%%%%%%%%% Our citations - Daksh - Meet - Laura %%%%%%%%%% @Article{anthony2025, journal={International Journal of Latest Technology in Engineering, Management \& Applied Science}, author={Umerah Anthony Tochukwu and Azaka Maduabuchuku and Osita Miracle Nwakeze and Obaze Caleb Akachukwu and Ibeh Sylvarine Chinasa}, title={AI-Driven Diagnostic Imaging: Hybrid CNN-GNN Models for Early Detection of Cancer from Pathological Images}, year={2025}, month={September}, pages={579-588}, volume={14}, number={9}, abstract={The early and accurate detection of cancer from histopathological images is crucial for the improvement patient outcomes in precision oncology because conventional diagnostic methods usually suffer from subjectivity and high variability, while traditional deep learning approaches, though effective, are limited in capturing both local morphological details and global tissue context simultaneously. In order to address this challenge, this study proposes a hybrid Convolutional Neural Network–Graph Neural Network (CNN–GNN) framework that integrates patch-level visual feature extraction with graph-based relational learning for cancer detection. The study adhered to the Agile approach and publicly available datasets, CAMELYON16 and CAMELYON17, were used, which consist of Whole-Slide Images (WSIs) and professional annotations of normal and metastatic tissue areas. Stain normalization, patch extraction, data augmentation, and graph construction were used as preprocessing steps, which provided both CNN and GNN pipelines with high-quality inputs. DenseNet121 was used in place of CNN backbone to extract patch embedding whereas Graph Convolutional Network (GCN) was used to learn the spatial and contextual relationship among patches. The last distinction came by combining CNN and GNN embedding by a multilayer perceptron classifier. The effectiveness of the given architecture was proven by experiment results. CNN model reached an accuracy of 88.9\% with an F1-score of 89.2\% and GNN model reached a higher accuracy of 90.7\% and F1-score of 91.0\%. The hybrid CNNGNN model notably outdid the two baselines, achieving a test accuracy of 95.4\%, precision of 94.7\%, recall of 95.9\%, F1-score of 95.3\% and AUC of 96.4\%. Therefore, the hybrid CNNGNN model that is suggested provides a scalable, trustworthy, and clinically feasible solution to computational pathology. Along with attention mechanisms, enhanced GNN variants, and data on multiple institutions, future extensions could help to ex}, keywords={}, doi={None}, url={https://ideas.repec.org/a/bjb/journl/v14y2025i9p579-588.html}, } @article{wu2021, author = {Zonghan Wu and Shirui Pan and Fengwen Chen and Guodong Long and Chengqi Zhang and Philip S. Yu}, title = {A Comprehensive Survey on Graph Neural Networks}, journal = {IEEE Trans. Neural Netw. Learn. Syst.}, year = {2021}, volume = {32}, number = {1}, pages = {4--24}, doi = {10.1109/TNNLS.2020.2978386}, pmid = {32217482}, month = jan } @misc{kipf2017, title={Semi-Supervised Classification with Graph Convolutional Networks}, author={Thomas N. Kipf and Max Welling}, year={2017}, eprint={1609.02907}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/1609.02907}, } @misc{velickovic2018, title={Graph Attention Networks}, author={Petar Veličković and Guillem Cucurull and Arantxa Casanova and Adriana Romero and Pietro Liò and Yoshua Bengio}, year={2018}, eprint={1710.10903}, archivePrefix={arXiv}, primaryClass={stat.ML}, url={https://arxiv.org/abs/1710.10903}, } @misc{hamilton2018, title={Inductive Representation Learning on Large Graphs}, author={William L. Hamilton and Rex Ying and Jure Leskovec}, year={2018}, eprint={1706.02216}, archivePrefix={arXiv}, primaryClass={cs.SI}, url={https://arxiv.org/abs/1706.02216}, } @misc{shabani2024, title={A Comprehensive Survey on Graph Summarization with Graph Neural Networks}, author={Nasrin Shabani and Jia Wu and Amin Beheshti and Quan Z. Sheng and Jin Foo and Venus Haghighi and Ambreen Hanif and Maryam Shahabikargar}, year={2024}, eprint={2302.06114}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2302.06114}, } @misc{xu2019, title={How Powerful are Graph Neural Networks?}, author={Keyulu Xu and Weihua Hu and Jure Leskovec and Stefanie Jegelka}, year={2019}, eprint={1810.00826}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/1810.00826}, } @misc{ying2019, title={Hierarchical Graph Representation Learning with Differentiable Pooling}, author={Rex Ying and Jiaxuan You and Christopher Morris and Xiang Ren and William L. Hamilton and Jure Leskovec}, year={2019}, eprint={1806.08804}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/1806.08804}, } @misc{cai2018, title={A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications}, author={Hongyun Cai and Vincent W. Zheng and Kevin Chen-Chuan Chang}, year={2018}, eprint={1709.07604}, archivePrefix={arXiv}, primaryClass={cs.AI}, url={https://arxiv.org/abs/1709.07604}, } @misc{nazir2021, title={Survey of Image Based Graph Neural Networks}, author={Usman Nazir and He Wang and Murtaza Taj}, year={2021}, eprint={2106.06307}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2106.06307}, } @ARTICLE{xie2025, author={Xie, Xinlin and Fan, Jing and Xu, Xinying and Xie, Gang}, journal={IEEE Transactions on Big Data}, title={Adaptive Superpixel Segmentation With Non-Uniform Seed Initialization}, year={2025}, volume={11}, number={2}, pages={620-634}, keywords={Image segmentation;Clustering algorithms;Image color analysis;Computational complexity;Lattices;Big Data;Weight measurement;Superpixels;non-uniform;pre-processing;small objects;disconnected regions}, doi={10.1109/TBDATA.2024.3423719} } @article{tochukwu2025, author = {Tochukwu, Umerah and Maduabuchuku, Azaka and Nwakeze, Osita and Obaze, Caleb Akachukwu}, year = {2025}, month = {10}, pages = {579-588}, title = {AI-Driven Diagnostic Imaging: Hybrid CNN-GNN Models for Early Detection of Cancer from Pathological Images}, volume = {14}, journal = {International Journal of Latest Technology in Engineering Management & Applied Science}, doi = {10.51583/IJLTEMAS.2025.1409000070} } @article{vasudevan2022, author = {Varun Vasudevan and Maxime Bassenne and Md Tauhidul Islam and Lei Xing}, title = {Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels}, journal = {CoRR}, volume = {abs/2201.12633}, year = {2022}, url = {https://arxiv.org/abs/2201.12633}, eprinttype = {arXiv}, eprint = {2201.12633} } @INPROCEEDINGS{trivedy2023, author={Trivedy, Vivek and Latecki, Longin Jan}, booktitle={2023 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, title={CNN2Graph: Building Graphs for Image Classification}, year={2023}, volume={}, number={}, pages={1-11}, doi={10.1109/WACV56688.2023.00009} } @InProceedings{han2023, author = {Han, Yan and Wang, Peihao and Kundu, Souvik and Ding, Ying and Wang, Zhangyang}, title = {Vision HGNN: An Image is More than a Graph of Nodes}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {19878-19888} } @article{mbiaya2024, title = {Knowledge graph-based image classification}, journal = {Data and Knowledge Engineering}, volume = {151}, pages = {102285}, year = {2024}, issn = {0169-023X}, doi = {https://doi.org/10.1016/j.datak.2024.102285}, url = {https://www.sciencedirect.com/science/article/pii/S0169023X24000090}, author = {Franck Anaël Mbiaya and Christel Vrain and Frédéric Ros and Thi-Bich-Hanh Dao and Yves Lucas}, keywords = {Deep learning, Image classification, Knowledge graph}, abstract = {This paper introduces a deep learning method for image classification that leverages knowledge formalized as a graph created from information represented by pairs attribute/value. The proposed method investigates a loss function that adaptively combines the classical cross-entropy commonly used in deep learning with a novel penalty function. The novel loss function is derived from the representation of nodes after embedding the knowledge graph and incorporates the proximity between class and image nodes. Its formulation enables the model to focus on identifying the boundary between the most challenging classes to distinguish. Experimental results on several image databases demonstrate improved performance compared to state-of-the-art methods, including classical deep learning algorithms and recent algorithms that incorporate knowledge represented by a graph.} } @article{lim2025, title = {A review of few-shot image classification: Approaches, datasets and research trends}, journal = {Neurocomputing}, volume = {649}, pages = {130774}, year = {2025}, issn = {0925-2312}, doi = {https://doi.org/10.1016/j.neucom.2025.130774}, url = {https://www.sciencedirect.com/science/article/pii/S0925231225014468}, author = {Jit Yan Lim and Kian Ming Lim and Chin Poo Lee and Yong Xuan Tan}, keywords = {Few-shot image classification, Few-shot learning, Meta-learning, Transfer learning, Computer vision, Survey}, abstract = {Over the past decade, deep learning has made significant advancements in image classification. However, these models struggle with data scarcity and distribution shifts, commonly referred to as the few-shot image classification (FSIC) problem. FSIC aims to recognize novel classes using only a limited number of labeled samples, posing challenges for conventional deep learning models that rely on large datasets for optimal performance. This paper provides a comprehensive review of FSIC methodologies, categorizing them into five main approaches: meta-learning, transfer learning, data augmentation, attribute-related, and vision-language foundation model adaptation. Meta-learning approaches are further classified into metric-based, model-based, and optimization-based methods, while transfer learning approaches are divided into hybrid and non-hybrid methods. Vision-language foundation model adaptation approaches are grouped into few-shot parameter tuning, dynamic or unsupervised tuning, and training-free adaptation methods. Beyond general FSIC, this paper also explores specialized FSIC methods in fine-grained classification, cross-domain classification, and class-incremental learning. Additionally, it reviews commonly used few-shot image datasets and compares the performance of representative methods through experimental results. Practical applications of FSIC across various domains are also discussed, highlighting its potential to address real-world challenges. Finally, the research trends of FSIC are identified, offering insights into the state-of-the-art FSIC methods and guiding future advancements in this field.} } @misc{yuan2024, title={Graph Attention Transformer Network for Multi-Label Image Classification}, author={Jin Yuan and Shikai Chen and Yao Zhang and Zhongchao Shi and Xin Geng and Jianping Fan and Yong Rui}, year={2024}, eprint={2203.04049}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2203.04049}, } @misc{zhang2018, title={GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs}, author={Jiani Zhang and Xingjian Shi and Junyuan Xie and Hao Ma and Irwin King and Dit-Yan Yeung}, year={2018}, eprint={1803.07294}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/1803.07294}, } @Article{li2020, AUTHOR = {Li, Shuohao and Tang, Min and Zhang, Jun and Jiang, Lincheng}, TITLE = {Attentive Gated Graph Neural Network for Image Scene Graph Generation}, JOURNAL = {Symmetry}, VOLUME = {12}, YEAR = {2020}, NUMBER = {4}, ARTICLE-NUMBER = {511}, URL = {https://www.mdpi.com/2073-8994/12/4/511}, ISSN = {2073-8994}, ABSTRACT = {Image scene graph is a semantic structural representation which can not only show what objects are in the image, but also infer the relationships and interactions among them. Despite the recent success in object detection using deep neural networks, automatically recognizing social relations of objects in images remains a challenging task due to the significant gap between the domains of visual content and social relation. In this work, we translate the scene graph into an Attentive Gated Graph Neural Network which can propagate a message by visual relationship embedding. More specifically, nodes in gated neural networks can represent objects in the image, and edges can be regarded as relationships among objects. In this network, an attention mechanism is applied to measure the strength of the relationship between objects. It can increase the accuracy of object classification and reduce the complexity of relationship classification. Extensive experiments on the widely adopted Visual Genome Dataset show the effectiveness of the proposed method.}, DOI = {10.3390/sym12040511} } @Article{chen2025, AUTHOR = {Chen, Jieli and Seng, Kah Phooi and Ang, Li Minn and Smith, Jeremy and Xu, Hanyue}, TITLE = {Towards a Gated Graph Neural Network with an Attention Mechanism for Audio Features with a Situation Awareness Application}, JOURNAL = {Electronics}, VOLUME = {14}, YEAR = {2025}, NUMBER = {13}, ARTICLE-NUMBER = {2621}, URL = {https://www.mdpi.com/2079-9292/14/13/2621}, ISSN = {2079-9292}, ABSTRACT = {Situation awareness (SA) involves analyzing sensory data, such as audio signals, to identify anomalies. While acoustic features are widely used in audio analysis, existing methods face critical limitations; they often overlook the relevance of SA audio segments, failing to capture the complex relational patterns in audio data that are essential for SA. In this study, we first propose a graph neural network (GNN) with an attention mechanism that models SA audio features through graph structures, capturing both node attributes and their relationships for richer representations than traditional methods. Our analysis identifies suitable audio feature combinations and graph constructions for SA tasks. Building on this, we introduce a situation awareness gated-attention GNN (SAGA-GNN), which dynamically filters irrelevant nodes through max-relevance neighbor sampling to reduce redundant connections, and a learnable edge gated-attention mechanism that suppresses noise while amplifying critical events. The proposed method employs sigmoid-activated attention weights conditioned on both node features and temporal relationships, enabling adaptive node emphasizing for different acoustic environments. Experiments reveal that the proposed graph-based audio features demonstrate superior representation capacity compared to traditional methods. Additionally, both proposed graph-based methods outperform existing approaches. Specifically, owing to the combination of graph-based audio features and dynamic selection of audio nodes based on gated-attention, SAGA-GNN achieved superior results on two real datasets. This work underscores the importance and potential value of graph-based audio features and attention mechanism-based GNNs, particularly in situational awareness applications.}, DOI = {10.3390/electronics14132621} } @ARTICLE{guo2024, author={Guo, Xiangyu and Gao, Mingliang and Zou, Guofeng and Bruno, Alessandro and Chehri, Abdellah and Jeon, Gwanggil}, journal={IEEE Transactions on Neural Networks and Learning Systems}, title={Object Counting via Group and Graph Attention Network}, year={2024}, volume={35}, number={9}, pages={11884-11895}, keywords={Feature extraction;Background noise;Task analysis;Interference;Videos;Transformers;Convolution neural network (CNN);deep learning;graph neural network (GNN);object counting}, doi={10.1109/TNNLS.2023.3336894} } @article{tang2025, author = {Tang, Jiayin and Miao, Yonghao and Xia, Yu and Zhou, Qiuyang and yi, Cai}, year = {2025}, month = {01}, pages = {1-1}, title = {A Multiscale Pooling Attention-Based Graph Attention Network for Remaining Useful Life Prediction}, volume = {PP}, journal = {IEEE Transactions on Instrumentation and Measurement}, doi = {10.1109/TIM.2025.3557109} } @misc{vaswani2023, title={Attention Is All You Need}, author={Ashish Vaswani and Noam Shazeer and Niki Parmar and Jakob Uszkoreit and Llion Jones and Aidan N. Gomez and Lukasz Kaiser and Illia Polosukhin}, year={2023}, eprint={1706.03762}, archivePrefix={arXiv}, primaryClass={cs.CL}, url={https://arxiv.org/abs/1706.03762}, } @article{sikdar2025, title = {Interweaving Insights: High-Order Feature Interaction for Fine-Grained Visual Recognition}, author = {Sikdar, Arindam and Liu, Yonghuai and Kedarisetty, Siddhardha and Zhao, Yitian and Ahmed, Amr and Behera, Ardhendu}, journal = {International Journal of Computer Vision}, year = {2025}, volume = {133}, number = {4}, pages = {1755--1779}, doi = {10.1007/s11263-024-02260-y}, pmid = {40160952}, pmcid = {PMC11953118}, note = {Epub 2024 Oct 20} } @article{wang2026, author = {Wang, Min and Yang, Chengyu and Sha, Lin and Li, Jiaqi and Tang, Shikai}, year = {2026}, month = {01}, pages = {95}, title = {FC-SBAAT: A Few-Shot Image Classification Approach Based on Feature Collaboration and Sparse Bias-Aware Attention in Transformers}, volume = {18}, journal = {Symmetry}, doi = {10.3390/sym18010095} } @article{dogga2026, author = {Dogga, Aswani and R., Sivasubramanian and S., Shanthi}, year = {2026}, month = {02}, pages = {}, title = {Hybrid vision transformer and graph neural network model with region-adaptive attention for enhanced skin cancer prediction}, volume = {16}, journal = {Scientific Reports}, doi = {10.1038/s41598-025-32502-z} } @misc{v2025, title={A Hybrid CNN-ViT-GNN Framework with GAN-Based Augmentation for Intelligent Weed Detection in Precision Agriculture}, author={Pandiyaraju V and Abishek Karthik and Sreya Mynampati and Poovarasan L and D. Saraswathi}, year={2025}, eprint={2511.15535}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2511.15535}, } @article{liu2024, AUTHOR = {Liu, Shudong and Zhong, Wenlong and Guo, Furong and Cong, Jia and Gu, Boyu}, TITLE = {Fine-Grained Few-Shot Image Classification Based on Feature Dual Reconstruction}, JOURNAL = {Electronics}, VOLUME = {13}, YEAR = {2024}, NUMBER = {14}, ARTICLE-NUMBER = {2751}, URL = {https://www.mdpi.com/2079-9292/13/14/2751}, ISSN = {2079-9292}, ABSTRACT = {Fine-grained few-shot image classification is a popular research area in deep learning. The main goal is to identify subcategories within a broader category using a limited number of samples. The challenge stems from the high intra-class variability and low inter-class variability of fine-grained images, which often hamper classification performance. To overcome this, we propose a fine-grained few-shot image classification algorithm based on bidirectional feature reconstruction. This algorithm introduces a Mixed Residual Attention Block (MRA Block), combining channel attention and window-based self-attention to capture local details in images. Additionally, the Dual Reconstruction Feature Fusion (DRFF) module is designed to enhance the model’s adaptability to both inter-class and intra-class variations by integrating features of different scales across layers. Cosine similarity networks are employed for similarity measurement, enabling precise predictions. The experiments demonstrate that the proposed method achieves classification accuracies of 96.99\%, 98.53\%, and 89.78\% on the CUB-200-2011, Stanford Cars, and Stanford Dogs datasets, respectively, confirming the method’s efficacy in fine-grained classification tasks.}, DOI = {10.3390/electronics13142751} } @misc{bui2024, title={Leveraging Graph Neural Networks to Boost Fine-Grained Image Classification}, author={Bao Quoc Bui and Duy Minh Le and Cong Tran and Anh Tuan Tran and Cuong Pham}, year={2024}, url={https://openreview.net/forum?id=NJ6nyv3XWH} } @misc{defferrard2017, title={Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering}, author={Michaël Defferrard and Xavier Bresson and Pierre Vandergheynst}, year={2017}, eprint={1606.09375}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/1606.09375}, } @Article{wang2024, AUTHOR = {Wang, Jiale and Lu, Jin and Yang, Junpo and Wang, Meijia and Zhang, Weichuan}, TITLE = {An Unbiased Feature Estimation Network for Few-Shot Fine-Grained Image Classification}, JOURNAL = {Sensors}, VOLUME = {24}, YEAR = {2024}, NUMBER = {23}, ARTICLE-NUMBER = {7737}, URL = {https://www.mdpi.com/1424-8220/24/23/7737}, PubMedID = {39686274}, ISSN = {1424-8220}, ABSTRACT = {Few-shot fine-grained image classification (FSFGIC) aims to classify subspecies with similar appearances under conditions of very limited data. In this paper, we observe an interesting phenomenon: different types of image data augmentation techniques have varying effects on the performance of FSFGIC methods. This indicates that there may be biases in the features extracted from the input images. The bias of the acquired feature may cause deviation in the calculation of similarity, which is particularly detrimental to FSFGIC tasks characterized by low inter-class variation and high intra-class variation, thus affecting the classification accuracy. To address the problems mentioned, we propose an unbiased feature estimation network. The designed network has the capability to significantly optimize the quality of the obtained feature representations and effectively reduce the feature bias from input images. Furthermore, our proposed architecture can be easily integrated into any contextual training mechanism. Extensive experiments on the FSFGIC tasks demonstrate the effectiveness of the proposed algorithm, showing a notable improvement in classification accuracy.}, DOI = {10.3390/s24237737} } @InProceedings{zhao2021, author = {Zhao, Yifan and Yan, Ke and Huang, Feiyue and Li, Jia}, title = {Graph-Based High-Order Relation Discovery for Fine-Grained Recognition}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2021}, pages = {15079-15088} } @article{long2021, author = {Long, Jianwu and yan, Zeran and chen, Hongfa}, year = {2021}, month = {04}, pages = {012071}, title = {A Graph Neural Network for superpixel image classification}, volume = {1871}, journal = {Journal of Physics: Conference Series}, doi = {10.1088/1742-6596/1871/1/012071} } @Article{sun2026, AUTHOR = {Sun, Le and Ding, Mingxuan and Ye, Qiaolin and Zheng, Yuhui and Wu, Zebin and Lu, Wen}, TITLE = {EIMGDNet: An Edge-Induced and Multi-Dimensional Grouped Difference Network for Remote Sensing Image Change Detection}, JOURNAL = {Remote Sensing}, VOLUME = {18}, YEAR = {2026}, NUMBER = {4}, ARTICLE-NUMBER = {649}, URL = {https://www.mdpi.com/2072-4292/18/4/649}, ISSN = {2072-4292}, ABSTRACT = {Change detection in remote sensing imagery is crucial for monitoring temporal variations in surface characteristics; nevertheless, it presents significant challenges owing to indistinct boundaries, limited semantic differentiation, and inadequate incorporation of multi-scale contextual information. To solve these problems, we propose EIMDGNet (Edge-Induced and Multi-Dimensional Grouped Difference Network), a novel architecture that enhances boundary representation and cross-scale feature interaction for accurate and robust change detection. EIMDGNet adopts a dual-branch ResNet18 backbone to extract multi-scale features from bi-temporal images, capturing both fine spatial detail and high-level semantic context. To improve boundary awareness and reduce pseudo-change interference, we introduce the Edge-Induced Differential Multi-Dimensional Group Enhancement Module (EID-MDGEM). This module enriches fine-grained spatial features through grouped pooling across spatial and channel dimensions, enabling precise localization of change contours. Within EID-MDGEM, the Edge Feature Enhancement Module (EFEM) integrates a parameter-free attention mechanism to generate edge-saliency maps, highlighting true change regions while suppressing background noise and irrelevant variations. To further enhance semantic consistency across feature scales, we design the Multi-Scale Hierarchical Progressive Fusion Module (MSHPM). This component employs a bottom-up progressive strategy to hierarchically integrate low-level spatial details with high-level semantic abstractions, thus increasing the continuity and completeness of detected change regions. By tightly coupling edge-aware enhancement with multi-scale hierarchical fusion, EIMDGNet effectively addresses major obstacles in change detection, including boundary ambiguity, inconsistent scale information, and feature misalignment. We evaluated EIMDGNet on five remote sensing change detection datasets: LEVIR-CD, DSIFN-CD, S2Looking, CLCD-CD and GVLM-CD. Our method consistently outperformed state-of-the-art approaches, achieving 91.49\% F1 and 82.93\% IoU on LEVIR-CD, 77.32\% F1 and 69.39\% IoU on DSIFN-CD, the highest 49.19\% IoU and 99.20\% OA on S2Looking, 81.65\% F1 and 72.91\% IoU on CLCD-CD, and 85.49\% F1 and 76.08\% IoU on GVLM-CD. These results demonstrate the superior accuracy and robustness of EIMDGNet across diverse change detection scenarios.}, DOI = {10.3390/rs18040649} } @Article{kavran2023, AUTHOR = {Domen and Mongus, Domen and Žalik, Borut and Lukač, Niko}, TITLE = {Graph Neural Network-Based Method of Spatiotemporal Land Cover Mapping Using Satellite Imagery}, JOURNAL = {Sensors}, VOLUME = {23}, YEAR = {2023}, NUMBER = {14}, ARTICLE-NUMBER = {6648}, URL = {https://www.mdpi.com/1424-8220/23/14/6648}, PubMedID = {37514942}, ISSN = {1424-8220}, ABSTRACT = {Multispectral satellite imagery offers a new perspective for spatial modelling, change detection and land cover classification. The increased demand for accurate classification of geographically diverse regions led to advances in object-based methods. A novel spatiotemporal method is presented for object-based land cover classification of satellite imagery using a Graph Neural Network. This paper introduces innovative representation of sequential satellite images as a directed graph by connecting segmented land region through time. The method’s novel modular node classification pipeline utilises the Convolutional Neural Network as a multispectral image feature extraction network, and the Graph Neural Network as a node classification model. To evaluate the performance of the proposed method, we utilised EfficientNetV2-S for feature extraction and the GraphSAGE algorithm with Long Short-Term Memory aggregation for node classification. This innovative application on Sentinel-2 L2A imagery produced complete 4-year intermonthly land cover classification maps for two regions: Graz in Austria, and the region of Portorož, Izola and Koper in Slovenia. The regions were classified with Corine Land Cover classes. In the level 2 classification of the Graz region, the method outperformed the state-of-the-art UNet model, achieving an average F1-score of 0.841 and an accuracy of 0.831, as opposed to UNet’s 0.824 and 0.818, respectively. Similarly, the method demonstrated superior performance over UNet in both regions under the level 1 classification, which contains fewer classes. Individual classes have been classified with accuracies up to 99.17\%.}, DOI = {10.3390/s23146648} } @article{samir2026, author = {Mohamed Samir and Naglaa Fathy and Walaa Gad}, title = {Knowledge-based question answering using graph neural networks and contextual language representations}, journal = {Scientific Reports}, year = {2026}, volume = {16}, number = {1}, pages = {2640}, doi = {10.1038/s41598-025-33854-2}, pmid = {41559152}, pmcid = {PMC12824272}, publisher = {Nature Publishing Group} } @misc{munir2024, title={GreedyViG: Dynamic Axial Graph Construction for Efficient Vision GNNs}, author={Mustafa Munir and William Avery and Md Mostafijur Rahman and Radu Marculescu}, year={2024}, eprint={2405.06849}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2405.06849}, } @inproceedings{zhang2025, title={SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration}, author={Zhang, Jintao and Wei, Jia and Zhang, Pengle and Zhu, Jun and Chen, Jianfei}, booktitle={International Conference on Learning Representations (ICLR)}, year={2025}, url={https://arxiv.org/abs/2410.02367} } @inproceedings{rodrigues2024, title={Graph Convolutional Networks for Image Classification: Comparing Approaches for Building Graphs from Images}, author={J{\'u}lia Rodrigues and Joel Lu{\'i}s Carbonera}, booktitle={International Conference on Enterprise Information Systems}, year={2024}, url={https://api.semanticscholar.org/CorpusID:269552841} } @INPROCEEDINGS{ren2003, author={Ren and Malik}, booktitle={Proceedings Ninth IEEE International Conference on Computer Vision}, title={Learning a classification model for segmentation}, year={2003}, volume={}, number={}, pages={10-17 vol.1}, keywords={Image segmentation;Humans;Brightness;Image databases;Computer science;Information analysis;Partitioning algorithms;Design optimization;Computer vision;Logistics}, doi={10.1109/ICCV.2003.1238308} } @article{kocak2025, title = {Bias in artificial intelligence for medical imaging: fundamentals, detection, avoidance, mitigation, challenges, ethics, and prospects}, author = {Koçak, Burak and Ponsiglione, Andrea and Stanzione, Arnaldo and Bluethgen, Christian and Santinha, Jo{\~a}o and Ugga, Lorenzo and Huisman, Merel and Klontzas, Michail E. and Cannella, Roberto and Cuocolo, Renato}, journal = {Diagnostic and Interventional Radiology}, year = {2025}, volume = {31}, number = {2}, pages = {75--88}, doi = {10.4274/dir.2024.242854}, note = {Epub 2024 Jul 2} } @article{dai2024, title={A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability}, volume={21}, ISSN={2731-5398}, url={http://dx.doi.org/10.1007/s11633-024-1510-8}, DOI={10.1007/s11633-024-1510-8}, number={6}, journal={Machine Intelligence Research}, publisher={Springer Science and Business Media LLC}, author={Dai, Enyan and Zhao, Tianxiang and Zhu, Huaisheng and Xu, Junjie and Guo, Zhimeng and Liu, Hui and Tang, Jiliang and Wang, Suhang}, year={2024}, month=sep, pages={1011–1061} } @inproceedings{jin2021, title={Universal Graph Convolutional Networks}, author={Di Jin and Zhizhi Yu and Cuiying Huo and Rui Wang and Xiao Wang and Dongxiao He and Jiawei Han}, booktitle={Neural Information Processing Systems}, year={2021}, url={https://api.semanticscholar.org/CorpusID:247359006} } @inproceedings{khurana2026, title={Role of GNN in Skin Cancer Classification}, author={Daksh Khurana and Meet Patel and Laura Mancinelli and Avimanyou Vatsa }, booktitle={Proceding - 16th IEEE Integrated STEM Education Conference 2026}, year={2026}, url={https://ieee-isec.info/day/1} } @inproceedings{khurana2026a, title={Empirical Analysis of Video Segmentation for Sustainability}, author={Daksh Khurana and Hemang Mittal and Othoniel Joseph and Avimanyou Vatsa }, booktitle={Proceding - 16th IEEE Integrated STEM Education Conference 2026}, year={2026}, url={https://ieee-isec.info/day/1} } @inproceedings{gautam2026, title={Meta-Analysis of Image Classification Using Graph Neural Networks (GNNs)}, author={Rohit Ranjan Gautam and Avimanyou Vatsa}, booktitle={Proceding - 16th IEEE Integrated STEM Education Conference 2026}, year={2026}, url={https://ieee-isec.info/day/1} } @misc{pei2020, title={Geom-GCN: Geometric Graph Convolutional Networks}, author={Hongbin Pei and Bingzhe Wei and Kevin Chen-Chuan Chang and Yu Lei and Bo Yang}, year={2020}, eprint={2002.05287}, archivePrefix={arXiv}, primaryClass={cs.LG}, url={https://arxiv.org/abs/2002.05287}, } @article{sen2008, title={Collective Classification in Network Data}, volume={29}, url={https://ojs.aaai.org/aimagazine/index.php/aimagazine/article/view/2157}, DOI={10.1609/aimag.v29i3.2157}, abstractNote={Many real-world applications produce networked data such as the world-wide web (hypertext documents connected via hyperlinks), social networks (for example, people connected by friendship links), communication networks (computers connected via communication links) and biological networks (for example, protein interaction networks). A recent focus in machine learning research has been to extend traditional machine learning classification techniques to classify nodes in such networks. In this article, we provide a brief introduction to this area of research and how it has progressed during the past decade. We introduce four of the most widely used inference algorithms for classifying networked data and empirically compare them on both synthetic and real-world data.}, number={3}, journal={AI Magazine}, author={Sen, Prithviraj and Namata, Galileo and Bilgic, Mustafa and Getoor, Lise and Galligher, Brian and Eliassi-Rad, Tina}, year={2008}, month={Sep.}, pages={93} } @article{welinder2010, author = { Peter Welinder and Steve Branson and Takeshi Mita and Catherine Wah and Florian Schroff and Serge Belongie and Pietro Perona}, year = {2010}, month = {09}, pages = {}, title = {Caltech-UCSD Birds 200} } @misc{hamilton2018a, title={Inductive Representation Learning on Large Graphs}, author={William L. Hamilton and Rex Ying and Jure Leskovec}, year={2018}, eprint={1706.02216}, archivePrefix={arXiv}, primaryClass={cs.SI}, url={https://arxiv.org/abs/1706.02216}, } @article{tochukwu2025, author = {Tochukwu, Umerah and Maduabuchuku, Azaka and Nwakeze, Osita and Obaze, Caleb Akachukwu}, year = {2025}, month = {10}, pages = {579-588}, title = {AI-Driven Diagnostic Imaging: Hybrid CNN-GNN Models for Early Detection of Cancer from Pathological Images}, volume = {14}, journal = {International Journal of Latest Technology in Engineering Management & Applied Science}, doi = {10.51583/IJLTEMAS.2025.1409000070} } @ARTICLE{achanta2012, author={Achanta, Radhakrishna and Shaji, Appu and Smith, Kevin and Lucchi, Aurelien and Fua, Pascal and Süsstrunk, Sabine}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, title={SLIC Superpixels Compared to State-of-the-Art Superpixel Methods}, year={2012}, volume={34}, number={11}, pages={2274-2282}, keywords={Clustering algorithms;Image segmentation;Complexity theory;Image color analysis;Image edge detection;Measurement uncertainty;Approximation algorithms;Superpixels;segmentation;clustering;k-means}, doi={10.1109/TPAMI.2012.120} } @inproceedings{vedaldi2008, author = {Andrea Vedaldi and Stefano Soatto}, title = {Quick Shift and Kernel Methods for Mode Seeking}, booktitle = {Computer Vision -- ECCV 2008}, editor = {David Forsyth and Philip Torr and Andrew Zisserman}, series = {Lecture Notes in Computer Science}, volume = {5305}, pages = {705--718}, year = {2008}, publisher = {Springer}, address = {Berlin, Heidelberg}, doi = {10.1007/978-3-540-88693-8_52} } @article{felzenszwalb2004, author = {Pedro F. Felzenszwalb and Daniel P. Huttenlocher}, title = {Efficient Graph-Based Image Segmentation}, journal = {International Journal of Computer Vision}, volume = {59}, number = {2}, pages = {167--181}, year = {2004}, publisher = {Springer}, doi = {10.1023/B:VISI.0000022288.19776.77}, url = {https://doi.org/10.1023/B:VISI.0000022288.19776.77} } @INPROCEEDINGS{he2016, author={He, Kaiming and Zhang, Xiangyu and Ren, Shaoqing and Sun, Jian}, booktitle={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)}, title={Deep Residual Learning for Image Recognition}, year={2016}, volume={}, number={}, pages={770-778}, keywords={Training;Degradation;Complexity theory;Image recognition;Neural networks;Visualization;Image segmentation}, doi={10.1109/CVPR.2016.90}} @ARTICLE{tremeau2000, author={Tremeau, A. and Colantoni, P.}, journal={IEEE Transactions on Image Processing}, title={Regions adjacency graph applied to color image segmentation}, year={2000}, volume={9}, number={4}, pages={735-744}, keywords={Image segmentation;Image color analysis;Clustering algorithms;Iterative algorithms;Region 8;Large Hadron Collider;Automatic testing;Robustness;Algorithm design and analysis}, doi={10.1109/83.841950}} %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%Risk management-healthcare %%%%%%%%%%% ****start here @article{aami2017, author = {Advancing Safety in Healthcare Technology}, title = {Health IT Risk Management A practical Tool to Help Hospitals and Medical Devices Stay Secure in a Complex World}, isbn = {978-1-57020-649-8} } @article{adebayo2012, author = {Adewale O Adebayo}, title = {A Foundation for Breach Data Analysis}, volume = {2}, No = {4}, url = {https://d1wqtxts1xzle7.cloudfront.net/29441343/Foundation-for-Breach-Data-Analysis-libre.pdf?1390876360=&response-content-disposition=inline\%3B+filename\%3DIISTE\_Journal_Publication\_May\_2012.pdf&Expires=1774135947&Signature=dH2jBOdUaN6bQjASpESGQ4tFpqWW1AOWOYu7ufVWShdB1aBZoAt0BPAKP5dwT9fnAoCXnVdrbQPqFH-SSWCXK3yoTh0yyvyYvm4MmxOZa8s2QP8LsFB8EguxjtFuVMwsl00WUv63n0NrbHRpg~dNbgydfGRRbu3zHrxBr8qbwJ0Eh-r~LyBQDY8lAtMe7j7GzpPZr2N~rPuNeBBNvkMX8x7lTmZM5TCrK2Vziq2zd9Oy9OIaXMwGr8pCRK0MDUTpLXRQ3is9mrMb~jr3Wn1ZIvg-yoLfC-D0JSMVPgQep8z~czm5mfeSqNbNthNqY280tqDe97APahAn24o0AipfKA__&Key-Pair-Id=APKAJLOHF5GGSLRBV4ZA}, DOI = {}, year = {2012}, pages = {2225–0506}, journal = {Journal of Information Engineering and Applications} } @article{ali2024, title = {NAVIGATING COMPLEXITY: STRATEGIES FOR EFFECTIVE HEALTH RISK MANAGEMENT IN HEALTHCARE ORGANIZATIONS}, author = {Ali Akbar and Danish Khilani and Pranitha Shanthi and Lobo and Aslam Rizwan and Saddiqua Ayesha and Salamat Moazzam and Rafique Tariq and Tariq Naseem}, year = {2024}, month = {06}, pages = {505-515}, volume = {31}, journal = {Journal of Population Therapeutics and Clinical Pharmacology}, DOI = {10.53555/jptcp.v31i6.6527}, url = {https://www.jptcp.com/index.php/jptcp/article/view/6527?articlesBySameAuthorPage=4} } @article{alzahrani2022, title={Understanding and Improving Current Risk Management Practices in Hospital Settings}, volume={2}, url={https://ijpbms.com/index.php/ijpbms/article/view/151}, DOI={10.47191/ijpbms/v2-i10-13}, abstractNote={A large number of patients in the healthcare industry have adverse events. Risk management has been implemented in hospitals to ensure patient safety. However, there is still a lot of room for improvement in current risk management practices. As a result, the purpose of this research is to better understand risk management practices in hospital settings and to make recommendations to improve them. While a questionnaire survey was created to understand current risk management applications, risk management literature was reviewed in order to comprehend and improve these risk management applications. The findings show that over 70\% of practitioners and managers regard risk management as defining threats to patients, while only a minority agree on the ISO definition of risk. Furthermore, nearly half of practitioners and managers agree that risk assessment is more important than risk mitigation. To manage risks, participants mostly used Failure Mode and Effect Analysis (FMEA), brainstorming, and risk matrix techniques. Based on the results of the questionnaire and the literature review, risk management practices could be advanced by emphasizing safety culture, staff involvement, safety training, risk reporting systems, and risk management tools.&lt;/p&gt;}, number={10}, journal={International Journal of Pharmaceutical and Bio Medical Science}, author={Alzahrani, Mohammed Mastour and Alsubai, Nourh Abdalrhman and Albaejy, Raha Mohammed and Alanazi, Fahdah Nawaf and Aldosari, Ayed Abdullah and Alsannallh, Sulaiman Ahmed and Alqithami, Haifa Mansour Mohammmed and AlShammari, Montaha Ali Shatti and Nagei, Sharifah Hadi Ahmed}, year={2022}, month={Oct.}, pages={449–455} } @article{ashrm2020a, author = {American Society for Healthcare Risk Management}, year = {2020}, title = {Healthcare Risk Management: The Path Forward}, url = {https://www.ashrm.org/sites/default/files/ashrm/Executive-Summary_Risks-Rewards-Healthcare-Reform_FINAL2.pdf} } @article{ashrm2020, author = {American Society for Healthcare Risk Management}, year = {2020}, title = {Enterprise Risk Management for Health Care Boards: Leveraging the Value}, url = {https://www.ashrm.org/system/files/media/file/2020/11/ERM_A\%20Primer\%20for\%20Health\%20Care\%20Boards\_2020\_final.pdf} } @article{bozic2023, author = {Bozic, Velibor}, year = {2023}, month = {12}, pages = {63-80}, title = {Integrated Risk Management and Artificial Intelligence in Hospital}, volume = {7}, journal = {Journal of AI}, url = {https://dergipark.org.tr/en/pub/jai/article/1329224}, DOI = {10.61969/jai.1329224} } @article{cagliano2011, author = {Cagliano, Anna Corinna and Grimaldi, Sabrina and Rafele, C.}, year = {2011}, month = {06}, pages = {695-708}, title = {A systemic methodology for risk management in healthcare sector}, volume = {49}, journal = {Safety Science - SAF SCI}, DOI = {10.1016/j.ssci.2011.01.006}, url = {https://www.sciencedirect.com/science/article/abs/pii/S0925753511000087} } @article{capocchi2018, author = {Capocchi, Alessandro and Orlandini, Paola and Mariarita, Pierotti and Luzzi, Loredana and Lorenzo, Minetti}, year = {2018}, month = {12}, pages = {180-180}, title = {Risk Management in the Healthcare Sector and the Important Role of Education and Training Activities: The Case of Regione Lombardia}, volume = {14}, journal = {International Journal of Business and Management}, DOI = {10.5539/ijbm.v14n1p180}, url = {https://ccsenet.org/journal/index.php/ijbm/article/view/0/37898} } @article{centre2024, author = {National Health Systems Resrouce Centre}, year = {2024}, title = {Risk Management Framework Manual for District Hospitals}, isbn = {978-93-82655-36-7}, url = {https://qps.nhsrcindia.org/sites/default/files/2024-07/Risk\%20Management\_0.pdf} } @article{chililov2024, author = {Chililov, Abdula M.}, title = {Financial Risk Management in Healthcare in the Provision of High-Tech Medical Assistance for Sustainable Development: Evidence from Russia}, journal = {Risks}, volume = {12}, year = {2024}, number = {9}, url = {https://www.mdpi.com/2227-9091/12/9/134}, abstractNote = {The research determines the level of financial risk in the Russian healthcare system and identifies prospects for improving the current Russian practice of financial risk management in healthcare when providing high-tech medical care for sustainable development (using Russia as an example). The author summarizes the advanced experience of the top 20 largest healthcare organizations in Russia by revenue in 2022. Based on this experience, the author developed an SEM model of the financial risks in healthcare during the provision of high-tech medical care in Russia from a sustainable development perspective. The theoretical si gnificance of the developed model lies in uncovering the previously unknown causal relationships between the implementation of the ICT, sustainable development support, and financial risks in healthcare. T he model reveals a new market dimension of financial risks for healthcare organizations in Russia. The main conclusion is that implementing the ICT and support for sustainable development helps to reduce the financial risks in healthcare. The identified potential for reducing financial risks in providing high-tech medical care in Russia until 2026 is practically significant. This prospect can be practically applied as a roadmap for the digital modernization and sustainable development of healthcare until 2026, enhancing the state healthcare policy in Russia. The established systemic relationship between ICT implementation, sustainable development support, and financial risks in healthcare is of managerial importance because it will increase the predictability of the financial risks in the market dimension of healthcare in Russia. The newly developed approach to risk management in healthcare during the provision of high-tech medical care in Russia has expanded the instrumental framework of risk management for healthcare organizations in Russia and revealed further opportunities for improving its efficiency.}, DOI = {10.3390/risks12090134} } @article{doherty2018, title = {Critical Risks Facing the Healthcare Industry}, url = {https://www.chubb.com/content/dam/chubb-sites/chubb-com/microsites/healthcare-portal/chubb-advisories/documents/pdf/chubb-healthcarecriticalriskwhitepaper_2018.pdf}, author = {Diane Doherty and Renee Carino}, year = {2018} } @article{elliethey2021, author = {Elliethey, Nancy and Ashour, Heba}, year = {2021}, month = {03}, pages = {1281-1298}, title = {Clinical Risk Management in Healthcare Organization as Perceived by Staff Nurses}, volume = {12}, journal = {Egyptian Journal of Health Care}, DOI = {10.21608/ejhc.2021.193389}, url = {https://www.researchgate.net/publication/354888255_Clinical_Risk_Management_in_Healthcare_Organization_as_Perceived_by_Staff_Nurses} } @article{ennaaoui2021, author = {En-Naaoui, Amine}, year = {2021}, month = {04}, pages = {930-936}, title = {Risk Management in Moroccan Healthcare Organizations: An Overview}, volume = {12}, journal = {Turkish Journal of Computer and Mathematics Education (TURCOMAT)}, DOI = {10.17762/turcomat.v12i5.1735}, url = {https://turcomat.org/index.php/turkbilmat/article/view/1735} } @article{estates97, author = {NHS Estates an Executive Agnecy of the Department of Health}, year = {1997}, title = {An Exemplar Operational Risk Management Strategy}, isbn = {0-11-322072-3}, url = {https://www.england.nhs.uk/wp-content/uploads/2021/05/An_exemplar_operational_risk_management_strategy.pdf} } @article{ferdosi2024, author = {Ferdosi, Masoud and Rezayatmand, Reza and Taleghani, Yasamin}, year = {2020}, month = {03}, pages = {215-243}, title = {Risk Management in Executive Levels of Healthcare Organizations: Insights from a Scoping Review (2018)}, volume = {13}, journal = {Risk Management and Healthcare Policy}, DOI = {10.2147/RMHP.S231712}, url = {https://pubmed.ncbi.nlm.nih.gov/32256134/} } @article{guerra2024, author = {Guerra, Ranieri}, year = {2024}, month = {04}, pages = {}, title = {Enhancing risk management in hospitals: leveraging artificial intelligence for improved outcomes}, volume = {18}, journal = {Italian Journal of Medicine}, DOI = {10.4081/itjm.2024.1721}, No = {2}, abstractNote={In hospital settings, effective risk management is critical to ensuring patient safety, regulatory compliance, and operational effectiveness. Conventional approaches to risk assessment and mitigation frequently rely on manual procedures and retroactive analysis, which might not be sufficient to recognize and respond to new risks as they arise. This study examines how artificial intelligence (AI) technologies can improve risk management procedures in healthcare facilities, fortifying patient safety precautions and guidelines while improving the standard of care overall. Hospitals can proactively identify and mitigate risks, optimize resource allocation, and improve clinical outcomes by utilizing AI-driven predictive analytics, natural language processing, and machine learning algorithms. The different applications of AI in risk management are discussed in this paper, along with opportunities, problems, and suggestions for their effective use in hospital settings.}, url = {https://www.italjmed.org/ijm/article/view/1721} } @article{heinzova2021, title = {Risk Management in Health Care Organizations in the Czech Republic}, volume = {86}, url={https://www.cetjournal.it/index.php/cet/article/view/CET2186046}, DOI = {10.3303/CET2186046}, journal = {Chemical Engineering Transactions}, author = {Heinzova, Romana and Peterek, Kamil and Hoke, Eva}, year = {2021}, month = {05}, pages = {271-276} } @article{seh2020, author = {Seh, Adil H. and Zarour, Mohammad and Alenezi, Mamdouh and Sarkar, Amal and Agrawal, Alka and Kumar, Rajeev and Khan, Prof. Raees}, year = {2020}, month = {05}, pages = {133}, title = {Healthcare Data Breaches: Insights and Implications}, volume = {8}, journal = {Healthcare}, DOI = {10.3390/healthcare8020133}, url = {https://www.mdpi.com/2227-9032/8/2/133} } @article{hyatt2020, title = {Should a Good Risk Manager Worry About Cost and Price Transparency in Health Care?}, url = {https://journalofethics.ama-assn.org/article/should-good-risk-manager-worry-about-cost-and-price-transparency-health-care/2020-11}, DOI = {10.1001/amajethics.2020.924}, journal = {AMA Jounrla of Ethics}, author = {Hyatt, Josh Charles and Newman, Stephan L}, year = {2020}, month = {11}, } @article{le2023, author = {Le, Duc Phong and Isah, Haruna and Dadkhah, Sajjad and Yadollahi, Mohammad Mehdi and Zhang, Xichen and Ghorbani, Ali}, year = {2023}, month = {01}, pages = {1}, title = {Data Breach: Analysis, Countermeasures, and Challenges}, volume = {1}, journal = {International Journal of Information and Computer Security}, DOI = {10.1504/IJICS.2023.10050154}, url = {https://www.researchgate.net/publication/366761866_Data_Breach_Analysis_Countermeasures_and_Challenges} } @article{lechtman2021, title = {INTEGRATED RISK MANAGEMENT: WHY HIGH-PERFORMING HEALTHCARE ORGANIZATIONS ARE TAKING THE LEAP}, url = {https://go.riskonnect.com/hubfs/Riskonnect/_Ebook__Integrated_Risk_Management_Why_High_Performing_Healthcare.pdf}, author = {Lechtman, Jay}, year = {2021}, } @article{liu2022, author = {Liu, Yiliu}, year = {2022}, month = {05}, title = {Risk management of smart healthcare systems: Delimitation, state-of-arts, process, and perspectives}, volume = {27}, journal = {Journal of Patient Safety and Risk Management}, DOI = {10.1177/25160435221102242}, url = {https://journals.sagepub.com/doi/10.1177/25160435221102242} } @article{messano2014, author = {Messano, Giuseppe and Bono, Virgilio and Folco, Francesco and Marsella, Luigi}, year = {2014}, month = {07}, pages = {423-30}, title = {Past and present of risk management in healthcare}, volume = {70}, journal = {Igiene e sanità pubblica}, url = {https://pubmed.ncbi.nlm.nih.gov/25353272/}, pmid = {25353272} } @article{park2019, author = {Park, Stacy and Sharp, Adam}, year = {2019}, month = {05}, pages = {9-9}, title = {Improving health and health care efficiency through risk management}, volume = {3}, journal = {Journal of Hospital Management and Health Policy}, DOI = {10.21037/jhmhp.2019.04.02}, url = {https://jhmhp.amegroups.org/article/view/5054/html} } @article{pascarella2021, author = {Pascarella, Giacomo and Rossi, Matteo and Montella, Emma and Capasso, Arturo and Feo, Gianfranco and Botti, Gerardo and Nardone, Antonio and Montuori, Paolo and Triassi, Maria and D'Auria, Stefania and Morabito, Alessandro}, year = {2021}, month = {07}, pages = {2897-2911}, title = {Risk Analysis in Healthcare Organizations: Methodological Framework and Critical Variables}, volume = {Volume 14}, journal = {Risk Management and Healthcare Policy}, DOI = {10.2147/RMHP.S309098}, url = {https://www.dovepress.com/risk-analysis-in-healthcare-organizations-methodological-framework-and-peer-reviewed-fulltext-article-RMHP} } @article{ranjbar2024, author = {Ranjbar, Arian and Mork, Eilin and Ravn, Jesper and Brøgger, Helga and Myrseth, Per and Østrem, Hans and Hallock, Harry}, year = {2024}, month = {04}, pages = {877-882}, title = {Managing Risk and Quality of AI in Healthcare: Are Hospitals Ready for Implementation?}, volume = {17}, journal = {Risk Management and Healthcare Policy}, DOI = {10.2147/RMHP.S452337}, url = {https://www.dovepress.com/managing-risk-and-quality-of-ai-in-healthcare-are-hospitals-ready-for--peer-reviewed-fulltext-article-RMHP} } @article{saelim2024, author = {Sae-Lim, Patipan and Ayudhaya, Sirintata}, year = {2024}, month = {03}, pages = {1-11}, title = {Beyond Patient Safety Goal Towards Hospital Sustainable Risk: A Systematic Review on the Evolution of Hospital Risk Management}, volume = {17}, journal = {The Open Public Health Journal}, DOI = {10.2174/0118749445284229240313062944}, url = {https://openpublichealthjournal.com/VOLUME/17/ELOCATOR/e18749445284229/} } @article{strametz2017, author = {Strametz, Reinhard}, year = {2017}, month = {03}, journal = {German Coalition on Patient Safety}, title = {Requirements on Clinical Risk Management Systems in Hospitals}, DOI = {10.21960/201707/E}, url = {https://www.researchgate.net/publication/315698763_Requirements_on_Clinical_Risk_Management_Systems_in_Hospitals/} } @article{turk2021, author = {Türk, Murat and Eroğlu, İlhan}, year = {2021}, month = {03}, pages = {113-121}, title = {Financial Risk Assessment in Healthcare Organizations}, volume = {23}, journal = {Düzce Tıp Fakültesi Dergisi}, DOI = {10.18678/dtfd.862323}, url = {https://dergipark.org.tr/en/pub/dtfd/article/862323} } @article{who2019, author = {World Health Organization}, year = {2019}, title = {Health emergency and disaster risk management framework}, url = {https://iris.who.int/server/api/core/bitstreams/219a1a08-9ec5-4f2d-9aff-54c713fcfa7c/content}, isbn = {978-92-4-151618-1} } @article{who2022, author = {World Health Organization}, year = {2022}, title = { Risk Management Strategy: Reducing Uncertainty Around the Achievement of WHO’s Objectives and Outcomes, Office of Compliance, Risk Management and Ethics}, url = {https://cdn.who.int/media/docs/default-source/documents/ethics/who-risk-management-strategy.pdf?sfvrsn=12563c32_4&download=true} } @article{zhang2022, author = {Zhang, Xichen and Yadollahi, Mohammad Mehdi and Dadkhah, Sajjad and Isah, Haruna and Le, Duc-Phong and Ghorbani, Ali A.}, title = {Data breach: analysis, countermeasures and challenges}, year = {2022}, issue_date = {2022}, publisher = {Inderscience Publishers}, address = {Geneva 15, CHE}, volume = {19}, number = {3–4}, issn = {1744-1765}, url = {https://doi.org/10.1504/ijics.2022.127169}, doi = {10.1504/ijics.2022.127169}, abstract = {The increasing use or abuse of online personal data leads to a big data breach challenge for individuals, businesses, and even the government. Due to the scale of online data and the uncertainty of human factors, it is not feasible to build a practical prevention approach for data breach incidents in a real-time manner. In addition, despite the existing research on protecting users' data, a little systematic survey has been published to guide researchers and industrial participants to address the data breach issues. In this paper, we perform a comprehensive review and analysis of typical data breach incidents. We investigate threat actors, security flaws, and vulnerabilities that often lead to data breaches. The paper also includes the consequences of the information disclosures and lessons learned from each incident. Finally, we discuss countermeasures and challenges in preventing potential data breaches.}, journal = {Int. J. Inf. Comput. Secur.}, month = jan, pages = {402–442}, numpages = {40}, keywords = {data breaches, data privacy, protection, threat actors, cyber-attacks, countermeasures} } @article{leithy2021, author = {Nancy Sabry Elliethey and Heba Mohamed Al Anwer Ashour}, title = {Clinical Risk Management in Healthcare Organization as Perceived by Staff Nurses}, year = {2021}, address = {Geneva 15, CHE}, volume = {12}, number = {1}, pages = {1281–1298}, doi = {10.21608/ejhc.2021.193389}, journal = {Egyptian Journal of Health Care}, keywords = {data breaches, data privacy, protection, threat actors, cyber-attacks, countermeasures} } @Techreport{ASHRM, author = "ASHRM", year = 2025, title = "Healthcare Risk Management: The Path Forward", institution = "American Society for Healthcare Risk Management", type = "Technical Report", number = "", address = "Chicago, IL", url = "https://www.ashrm.org/whitepapers" } @Techreport{brown2021, author = "Trapper Brown", year = 2021, title = "From Risk Analysis to Risk Reduction: A Step-by-Step Approach", institution = "Clearwater", type = "Technical Report", number = "", address = "Chicago IL", url = "https://clearwatersecurity.com/white-papers/from-risk-analysis-to-risk-reduction-a-step-by-step-approach/" } @INPROCEEDINGS{kumar2023, author={Kumar, Arav and Vats, Savya and Kumar, Anvi and Vatsa, Avimanyou}, booktitle={2023 IEEE Integrated STEM Education Conference (ISEC)}, title={Challenges and Applications of AI in Healthcare: A Review}, year={2023}, volume={}, number={}, pages={174-178}, keywords={Costs;Hospitals;Computer viruses;Medical services;Artificial intelligence;Statistics;Medical diagnostic imaging;Healthcare;Artificial Intelligence (AI);Infectious Diseases;Skin Cancer}, doi={10.1109/ISEC57711.2023.10402195}} @ARTICLE{kumarVatsa2022, AUTHOR={Ayushi Kumar and Avimanyou Vatsa}, TITLE={Untangling Classification Methods for Melanoma Skin Cancer}, JOURNAL={Frontiers in Big Data}, VOLUME={Volume 5 - 2022}, YEAR={2022}, URL={https://www.frontiersin.org/journals/big-data/articles/10.3389/fdata.2022.848614}, DOI={10.3389/fdata.2022.848614}, ISSN={2624-909X}, ABSTRACT={Skin cancer is most common cancer in United State of America (USA). Skin cancer can affect anyone, regardless of skin color, race, gender, and age. The characteristics of skin lesion has an arbitrary shape, size, uneven and rough edge, and cannot be divided in half. Further, it is a leading cause of deaths worldwide. Every year, more than 5 million patients are newly diagnosed in USA. The deadliest and serious form of skin cancer is called melanoma. The diagnosis of melanoma has been done by visual examination and manual techniques by skilled doctors. It is time consuming process and highly prone to error. The skin images captured by dermoscopy eliminates the surface reflection of skin and gives better visualization of deeper levels of skin. In spite of these, image of skin lesion has many artifacts, noises, complex nature of lesion structure. Due to these complex natures of images, the border detection, feature extraction, and classification process is a complex problem. In order to identify and predict melanoma in early stage, there is need to classify images using better classification methods. Therefore, there is need to make an efficient, effective, and accurate melanoma identification, classification, and prediction such that it may be identified and classified in very early stage. The goal of this paper is to review and analyze the various deep neural network-based classification algorithms on skin images (ISIC dataset). Also, the performance algorithms are compared using five different parameters including ROC.}} @inproceedings{salej2026, title={Effectiveness, Failure, and Mitigation of Risk in Healthcare}, author={Jaiden Salej and Nithin Sirikonda and Ronald Treier and Medina Iljazi and Avimanyou Vatsa }, booktitle={Proceding - 16th IEEE Integrated STEM Education Conference 2026}, year={2026}, url={https://ieee-isec.info/day/1} } %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% %% Journal article @article{bib1, author = "Campbell, S. L. and Gear, C. W.", title = "The index of general nonlinear {D}{A}{E}{S}", journal = "Numer. {M}ath.", volume = "72", number = "2", pages = "173--196", year = "1995" } %% Journal article with DOI @article{bib2, author = "Slifka, M. K. and Whitton, J. L.", title = "Clinical implications of dysregulated cytokine production", journal = "J. {M}ol. {M}ed.", volume = "78", pages = "74--80", year = "2000", doi = "10.1007/s001090000086" } %% Journal article @article{bib3, author = "Hamburger, C.", title = "Quasimonotonicity, regularity and duality for nonlinear systems of partial differential equations", journal = "Ann. Mat. Pura. Appl.", volume = "169", number = "2", pages = "321--354", year = "1995" } %% book, authored @book{bib4, author = "Geddes, K. O. and Czapor, S. R. and Labahn, G.", title = "Algorithms for {C}omputer {A}lgebra", address = "Boston", publisher = "Kluwer", year = "1992" } %% Item 8. Book, chapter @incollection{bib5, author = "Broy, M.", title = "Software engineering---from auxiliary to key technologies", editor = "Broy, M. and Denert, E.", booktitle = "Software Pioneers", pages = "10--13", address = "New {Y}ork", publisher = "Springer", year = "1992" } %% Book, edited @book{bib6, editor = "Seymour, R. S.", title = "Conductive {P}olymers", address = "New {Y}ork", publisher = "Plenum", year = "1981" } %% Chapter in a book in a series with volume titles @inproceedings{bib7, author = "Smith, S. E.", title = "Neuromuscular blocking drugs in man", editor = "Zaimis, E.", volume = "42", booktitle = "Neuromuscular junction. {H}andbook of experimental pharmacology", pages = "593--660", address = "Heidelberg", publisher = "Springer", year = "1976" } %% Paper presented at a conference @misc{bib8, author = "Chung, S. T. and Morris, R. L.", title = "Isolation and characterization of plasmid deoxyribonucleic acid from Streptomyces fradiae", year = "1978", note = "Paper presented at the 3rd international symposium on the genetics of industrial microorganisms, University of {W}isconsin, {M}adison, 4--9 June 1978" } %% Data citation example @misc{bib9, author = "Hao, Z. and AghaKouchak, A. and Nakhjiri, N. and Farahmand, A.", title = "Global integrated drought monitoring and prediction system (GIDMaPS) data sets", year = "2014", note = "figshare \url{https://doi.org/10.6084/m9.figshare.853801}" } %% Preprint citation example @misc{bib10, author = "Babichev, S. A. and Ries, J. and Lvovsky, A. I.", title = "Quantum scissors: teleportation of single-mode optical states by means of a nonlocal single photon", year = "2002", note = "Preprint at \url{https://arxiv.org/abs/quant-ph/0208066v1}" } @article{bib11, author = "Beneke, M. and Buchalla, G. and Dunietz, I.", title = "Mixing induced {CP} asymmetries in inclusive {B} decays", journal = "Phys. {L}ett.", volume = "B393", year = "1997", pages = "132-142", archivePrefix = "arXiv", eprint = "0707.3168", primaryClass = "gr-gc" } @softmisc{bib12, author = "Stahl, B.", title = "deep{SIP}: deep learning of {S}upernova {I}a {P}arameters", version = "0.42", keywords = "Software", howpublished = "Astrophysics {S}ource {C}ode {L}ibrary", year = "2020", month = "Jun", eid = "ascl:2006.023", pages = "ascl:2006.023", archivePrefix = "ascl", eprint = "2006.023", adsurl = "{https://ui.adsabs.harvard.edu/abs/2020ascl.soft06023S}", adsnote = "Provided by the SAO/NASA Astrophysics Data System" } @article{bib13, author = "Abbott, T. M. C. and others", collaboration = "DES", title = "{Dark Energy Survey Year 1 Results: Constraints on Extended Cosmological Models from Galaxy Clustering and Weak Lensing}", eprint = "1810.02499", archivePrefix = "arXiv", primaryClass = "astro-ph.CO", reportNumber = "FERMILAB-PUB-18-507-PPD", doi = "10.1103/PhysRevD.99.123505", journal = "Phys. Rev. D", volume = "99", number = "12", pages = "123505", year = "2019" } %%============================================================================%% %% while using chicago reference style, both abbreviated and expanded form of %% %% author name format is acceptable. Refer below example for expanded form %% %%============================================================================%% %% author = "{Cameron, Deborah}", - single author %% author = "{Saito, Yukio} and {Hyuga, Hiroyuki}", - double author %%======================================%% %% Example for author names with suffix %% %%======================================%% %% author = "{Price, R. A. Jr} and {Curry, N. {III}} and McCann, K. E. and %% Fielding, J. L. and {Abercrombie, E. Jr}",