DepViT-CAD: Deployable Vision Transformer-based cancer diagnosis in histopathology

Accurate and timely cancer diagnosis from histopathological slides is vital for effective clinical decision-making. This paper introduces DepViT-CAD, a deployable AI system for multi-class cancer diagnosis in histopathology. At its core is MAViT, a new Multi-Attention Vision Transformer designed to capture fine-grained morphological patterns across diverse tumor types. MAViT was trained and evaluated on expert-annotated patches from 1283 Whole-Slide Images (comprising 1008 training cases, 139 validation cases, and 275 test cases), covering 11 diagnostic categories, including 10 major cancers and non-tumor tissue. DepViT-CAD was indeed validated on two independent test cohorts: 275 WSIs from The Cancer Genome Atlas and 50 routine clinical cases from pathology labs, achieving diagnostic sensitivities of 94.11% and 92%, respectively. By combining state-of-the-art transformer architecture with large-scale real-world validation, DepViT-CAD offers a robust and scalable approach for AI-assisted cancer diagnostics. To support transparency and reproducibility, software and code will be made publicly available at GitHub.