Leveraging Attention-Based Convolutional Neural Networks for Meningioma Classification in Computational Histopathology

Simple Summary Meningioma is the most common primary intracranial tumor. DNA methylation-based subtyping, while highly useful for diagnosis and treatment planning, is costly and not widely available. Therefore, the identification of methylation classes based on histological sections would be highly beneficial as it could greatly support and accelerate diagnostic and treatment decisions. We developed and systematically evaluated an AI framework to perform the classification of the most prevalent methylation subtypes based on histological sections. The model achieved a balanced accuracy of 0.870 for benign-1 vs benign-2 and 0.749 for benign-1 vs. intermediate-A in a narrow validation set. Combined with the network's assessed focus on key tumor regions these results provide a promising proof-of-concept of such an AI-driven classification approach in precision medicine.Abstract Convolutional neural networks (CNNs) are becoming increasingly valuable tools for advanced computational histopathology, promoting precision medicine through exceptional visual decoding abilities. Meningiomas, the most prevalent primary intracranial tumors, necessitate accurate grading and classification for informed clinical decision-making. Recently, DNA methylation-based molecular classification of meningiomas has proven to be more effective in predicting tumor recurrence than traditional histopathological methods. However, DNA methylation profiling is expensive, labor-intensive, and not widely accessible. Consequently, a digital histology-based prediction of DNA methylation classes would be advantageous, complementing molecular classification. In this study, we developed and rigorously assessed an attention-based multiple-instance deep neural network for predicting meningioma methylation classes using tumor methylome data from 142 (+51) patients and corresponding hematoxylin-eosin-stained histological sections. Pairwise analysis of sample cohorts from three meningioma methylation classes demonstrated high accuracy in two combinations. The performance of our approach was validated using an independent set of 51 meningioma patient samples. Importantly, attention map visualization revealed that the algorithm primarily focuses on tumor regions deemed significant by neuropathologists, offering insights into the decision-making process of the CNN. Our findings highlight the capacity of CNNs to effectively harness phenotypic information from histological sections through computerized images for precision medicine. Notably, this study is the first demonstration of predicting clinically relevant DNA methylome information using computer vision applied to standard histopathology. The introduced AI framework holds great potential in supporting, augmenting, and expediting meningioma classification in the future.