Adaptive Prototype Learning for Multimodal Cancer Survival Analysis
This work addresses cancer survival prediction for medical applications, but it is incremental as it builds on existing multimodal integration methods.
The paper tackles the problem of excessive redundancy in multimodal data for cancer survival prediction by proposing Adaptive Prototype Learning (APL), which adaptively learns prototypes to reduce redundancy and preserve critical information, achieving superior performance over existing methods on five benchmark cancer datasets.
Leveraging multimodal data, particularly the integration of whole-slide histology images (WSIs) and transcriptomic profiles, holds great promise for improving cancer survival prediction. However, excessive redundancy in multimodal data can degrade model performance. In this paper, we propose Adaptive Prototype Learning (APL), a novel and effective approach for multimodal cancer survival analysis. APL adaptively learns representative prototypes in a data-driven manner, reducing redundancy while preserving critical information. Our method employs two sets of learnable query vectors that serve as a bridge between high-dimensional representations and survival prediction, capturing task-relevant features. Additionally, we introduce a multimodal mixed self-attention mechanism to enable cross-modal interactions, further enhancing information fusion. Extensive experiments on five benchmark cancer datasets demonstrate the superiority of our approach over existing methods. The code is available at https://github.com/HongLiuuuuu/APL.