This is the first study that systematically examines the relationship between cryosection histology and the molecular profiles of glioma. We developed the CHARM framework to provide accurate diagnostic and subtype prediction, and we validated our machine-learning models in multiple patient cohorts, showing the reliability of our approaches. In addition, we visualized our models’ attention scores for identifying IDH mutational status from cryosection histopathology, which illuminated the histologic patterns potentially indicative of these important molecular aberrations. Given the fast inference time (less than 1 second per image tile) of our automated approach, this methodology can be practically applied to intraoperative diagnoses of glioma subtypes, which can enhance intraoperative surgical decisions, expedite enrolling eligible patients into clinical trials, and provide up-to-date diagnostic classification in resource-limited regions.
The updated molecular-based WHO classification improves our understanding and prognostic assessments of gliomas. With new molecular profiling techniques and emerging treatments, the WHO regularly updates its guidelines for categorizing cancers, including a major overhaul of central nervous system cancer classification in 2021. However, patients living in areas without access to genetic sequencing could not fully benefit from the new classification criteria. In addition, obtaining molecular diagnostic results requires days to weeks, which cannot provide real-time decision support during the surgical removal of glioma tissues. CHARM addresses these issues by enabling rapid and low-cost evaluations based on cryosection slides, attains significantly better prediction performance compared with previous studies, and differentiates the molecular subtypes of glioma defined by the 2021 WHO classification. CHARM further associates histologic features with molecular profiles. For example, round nuclei, edema, and intermediate cellularity were identified in oligodendrogliomas defined by IDH mutation and 1p/19q codeletion. Hence, CHARM demonstrated the potential for data-driven approaches to identify morphological characteristics related to novel molecular biomarkers. Our machine-learning-based methods allow researchers to re-evaluate morphological patterns and tumor microenvironments related to the new diagnostic guidelines. In addition, our quantitative analyses provide new insights into the morphology associated with key genetic aberrations and illuminate morphological similarities between cancers with similar clinical behavior. For example, CHARM revealed the morphological similarity between IDH-mutant low-grade astrocytomas with CDKN2A/2B homozygous deletion and IDH-mutant grade-4 astrocytomas. This pathology finding is consistent with clinical evidence showing that these two subgroups of tumors are more aggressive than other subtypes.
The hierarchical ViT architecture of CHARM preserves the global contextual connections between image features remotely scattered on a slide. In contrast, CNN-based models use convolution kernels that emphasize the local interaction between regions nearby. In practice, pathologists evaluate a slide using both local and global contextual findings, which is aligned with how the hierarchical vision transformer processes images. This observation may explain why CHARM achieved better performance in most tasks compared with CNNs. When training on smaller datasets (e.g., n = 25 for detecting IDH-mutant samples within the high-histologic-grade group), ViT’s capability of learning useful embeddings is more limited. Overall, our results suggested that CHARM with ViT performs better in most glioma classification tasks, while CNN-based models may be useful for scenarios with limited training samples.
Another critical clinical challenge CHARM overcomes is the variable quality of cryosection images. Previous pathology studies usually focused on permanent slides because they are less likely to contain poor-quality imaging regions, such as tissues of unequal thickness or fragmented tissues. Nevertheless, processing permanent section slides takes days and is thus not applicable for intraoperative pathology evaluation that guides surgical operations. Other studies have employed T2-weighted MRI to predict glioma subtypes. However, MRI-based approaches require more time to acquire and process the images, do not achieve better performance compared with our methods, and cannot provide morphological understanding and visualization at the cellular level. Another recent study employed stimulated Raman histology images to predict the molecular subtypes of glioma. Our methods achieved similar prediction performance and do not require special microscopy techniques.
In summary, our CHARM platform successfully identified glioma cells, classified histologic grade, and predicted clinically important molecular profiles using hematoxylin and eosin-stained cryosection images, which enables rapid intraoperative diagnoses. Our visualization framework further empowers pathologists to identify the morphological patterns associated with molecular profiles and clinical outcomes. Taken together, CHARM demonstrated the possibility of extracting untapped biomedical signals from cryosection slides and facilitated the development of real-time precision oncology.
