TVT-PAPD: Pathology-Aware Prototype Distillation for Self-Supervised Whole Slide Image Classification
2026-07-11 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionMachine Learning
AI summaryⓘ
The authors created a new way for computers to learn about disease patterns in huge medical images without needing labeled examples. They combined a small version of a Vision Transformer with a special method that helps the computer recognize important tissue structures specific to pathology. Their approach improves the computer’s ability to spot key disease features efficiently and works well on brain tumor datasets. They also showed that their method can generalize to new datasets with good accuracy in classifying types of brain tumors.
Self-supervised learningVision TransformerPathologyWhole slide imagesPrototype distillationTissue morphologyGliomaCancer Genome AtlasCross-cohort generalizationFeature representation
Authors
Ramesh Naidu Laveti, Jaya Sreevalsan-Nair, T K Srikanth
Abstract
Self-supervised learning (SSL) has emerged as an effective paradigm for learning transferable representations from large-scale unlabeled whole slide images (WSIs). However, existing SSL methods primarily learn generic visual features and often fail to explicitly capture pathology-specific morphological patterns that are critical for disease characterization. To address this limitation, we propose Tiny Vision Transformer with Pathology-Aware Prototype Distillation (TVT-PAPD). This self-supervised pathology representation learning framework integrates a Tiny Vision Transformer (TVT) with a novel Pathology-Aware Prototype Distillation (PAPD) module. PAPD employs a learnable pathology prototype bank to discover and preserve representative tissue morphology patterns, encouraging semantically similar pathological regions to learn consistent and discriminative representations. The proposed framework enhances pathology-aware feature learning while maintaining computational efficiency with 90M parameters. Experiments on the Cancer Genome Atlas (TCGA) low-grade glioma (LGG)/glioblastoma (GBM) dataset and the Indian Pathology Brain (IPD-Brain) dataset demonstrate that TVT-PAPD achieves weighted F1-scores of 93.02% and 90.23%, respectively, for LGG-GBM classification, while exhibiting strong cross-cohort generalization across independent glioma datasets.