Multimodal AI improves classification of adult brain tumor types
Evaluating Single and Multi-Omics Based Explainable Artificial Intelligence (MOXAI) for Molecular Subclass Classification of Adult-Type Diffuse Gliomas
Computer Vision and Pattern RecognitionArtificial Intelligence
Summary
Identifying types of brain tumors helps doctors decide the best treatments. The authors created an AI that uses two kinds of genetic data together to better classify adult brain tumors called diffuse gliomas. Their AI was more accurate than others using only one data type. They also showed how the AI’s decisions link to known genes and DNA parts, making the results easier to understand.
What this means in practice
- •For clinical bioinformatics teams: Improve molecular classification of adult diffuse gliomas by integrating methylation and copy number data with explainable AI.
- •For pathology software developers: Incorporate multimodal explainable AI models to enhance automated tumor subtype diagnosis from genomic assays.
Authors
Md Zahangir Alom, Quynh T. Tran, Breuer Alexandar, Brent A. Orr
Abstract
DNA methylation (DNAM) profiling has emerged as a powerful diagnostic tool for classifying brain and solid tumors. However, existing computational models typically analyze methylation and copy number variation (CNV) data separately, failing to capture the complementary information their integration could provide. Moreover, current classification models lack mechanisms for within-class risk assessment analogous to traditional tumor grading, and no established explainability method can attribute classification decisions to specific genomic loci. In this paper, we present MOXAI (Multi-Omics Based Explainable AI), a deep learning framework that integrates DNA methylation and copy number data from methylation arrays to classify molecular subtypes of adult-type diffuse gliomas, alongside single-modality variants for comparison. Using a cohort from The Cancer Genome Atlas (TCGA), we trained ResNet50, DINOv2, and Graph Attention Network (GAT) models on methylation data alone, copy number data alone, and combined multimodal data. We further developed explainable AI (XAI) methods based on class activation maps (CAMs) and gradient-weighted CAM (Grad-CAM) to identify the specific CpG sites, genes, and chromosomal regions most relevant to each classification decision. The multimodal model achieved up to 92.98% cross-validation accuracy, outperforming models trained on CNV data alone. DINOv2 showed the strongest generalization, reaching 94.25% accuracy (confidence >0.9) on independent validation sets. XAI results aligned with established molecular features of adult-type diffuse glioma subtypes, confirming the biological interpretability of the framework.