Distilling genomic knowledge into pathology slides for robust cancer survival prediction
Computational Biomedicine · 2024
DOI: 10.70401/cbm.2026.0015 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Biomedicine, 2024. Verfasst von Yangfan Xu und 9 weiteren Autor:innen.
Abstract (Originalsprache)
Aims
To develop a robust and clinically feasible framework for cancer survival prediction using only histopathology images while leveraging transcriptomic knowledge during training.
Methods
The study proposed Adaptive Multi-modality Knowledge Distillation (AMKD), a framework designed to transfer complementary molecular-level information from transcriptomic data to pathology-based models. The AMKD framework consists of two essential elements. First, a gene-guided pathology enhancement module is designed to inject genomics-aware information from a multimodal teacher into pathology features. Second, an adaptive redundancy reduction loss is introduced to regulate knowledge distillation by accounting for prediction discrepancies between teacher and student models. This design allows the student model to retain biologically meaningful knowledge during training and remain effective with only histopathology data at inference.
Results
Comprehensive experiments on four The Cancer Genome Atlas (TCGA) cancer cohorts demonstrate that AMKD achieves state-of-the-art survival prediction performance, with an average concordance index (C-index) of 0.669, surpassing both unimodal pathology-based and fully multi-modal approaches. External validation on the independent Clinical Proteomic Tumor Analysis Consortium head and neck squamous cell carcinoma (CPTAC-HNSC) cohort further confirms the robustness and cross-dataset generalization ability of the proposed framework. Ablation studies further confirm the effectiveness of each proposed component in enhancing cross-modal knowledge transfer and improving generalization under incomplete modality scenarios.
Conclusion
The proposed AMKD framework provides a clinically practical solution for robust cancer survival analysis when transcriptomic data are unavailable. By adaptively distilling multi-modal knowledge into a pathology-based model, AMKD bridges the gap between research and clinical applicability, enabling scalable and cost-effective prognostic prediction in real-world settings.
Zitieren
APA
Xu, Y., Cai, L., Wang, Y., Cheng, H., Liu, F., Li, Y., Xue, R., Yuan, S., Zhang, Y., & Wang, R. (2024). Distilling genomic knowledge into pathology slides for robust cancer survival prediction. Computational Biomedicine. https://doi.org/10.70401/cbm.2026.0015
Vancouver
Xu Y, Cai L, Wang Y, Cheng H, Liu F, Li Y, et al. Distilling genomic knowledge into pathology slides for robust cancer survival prediction. Computational Biomedicine. 2024. doi:10.70401/cbm.2026.0015
BibTeX
@article{Xu2024,
author = {Xu, Yangfan and Cai, Linghan and Wang, Yifeng and Cheng, Hailun and Liu, Fengchun and Li, Yuanjia and Xue, Rui and Yuan, Shuofeng and Zhang, Yongbing and Wang, Runming},
title = {Distilling genomic knowledge into pathology slides for robust cancer survival prediction},
journal = {Computational Biomedicine},
year = {2024},
doi = {10.70401/cbm.2026.0015}
}
EUVIMED