The fusion of multi-modal data, e.g., medical images and genomic profiles, can provide complementary information and further benefit disease diagnosis. However, multi-modal disease diagnosis confronts two challenges: (1) how to produce discriminative multi-modal representations by exploiting complementary information while avoiding noisy features from different modalities. (2) how to obtain an accurate diagnosis when only a single modality is available in real clinical scenarios. To tackle these two issues, we present a two-stage disease diagnostic framework. In the first multi-modal learning stage, we propose a novel Momentum-enriched Multi-Modal Low-Rank (M3LR) constraint to explore the high-order correlations and complementary information among different modalities, thus yielding more accurate multi-modal diagnosis. In the second stage, the privileged knowledge of the multi-modal teacher is transferred to the unimodal student via our proposed Discrepancy Supervised Contrastive Distillation (DSCD) and Gradient-guided Knowledge Modulation (GKM) modules, which benefit the unimodal-based diagnosis. We have validated our approach on two tasks: (i) glioma grading based on pathology slides and genomic data, and (ii) skin lesion classification based on dermoscopy and clinical images. Experimental results on both tasks demonstrate that our proposed method consistently outperforms existing approaches in both multi-modal and unimodal diagnoses.
Keywords: Glioma grading; Knowledge distillation; Low-rank decomposition; Multi-modal learning; Skin lesion classification.
Copyright © 2023. Published by Elsevier B.V.