Comprehensive learning and adaptive teaching: Distilling multi-modal knowledge for pathological glioma grading

Xiaohan Xing, Meilu Zhu, Zhen Chen, Yixuan Yuan

Abstract: Highlights•Present a novel Comprehensive Learning and Adaptive Teaching framework to distill pathology-genomic knowledge and benefit the glioma grading with pathology slides.•Propose a Cross-modal Saliency Masking(CS-Mask) strategy to explore the neglected but useful features from both modalities, thus providing a better role model for the student.•Devise a novel Local Topology Preserving and Discrepancy Eliminating Contrastive Distillation(TDC-Distill) module to align feature distributions in an effective manner, and a Gradient-guided Knowledge Refinement(GK-Refine) scheme to enable adaptive knowledge absorption.