Context-guided Prompt-learning for Continual WSI Classification

Giulia Corso, Francesca Miccolis, Angelo Porrello, Federico Bolelli, Simone Calderara, ELISA FICARRA

Keywords: WSI, Multi-instance Learning, Prompt Learning, Continual Learning

TL;DR: CooMIL enables privacy-preserving continual learning for WSIs without storing past data, using prompt learning to prevent forgetting.

Abstract: Whole Slide Images (WSIs) are crucial in histological diagnostics, providing high-resolution insights for analyzing cellular structures. In addition to challenges like the gigapixel scale of WSIs and the lack of pixel-level annotations, privacy restrictions further complicate their analysis. For instance, in a hospital network, different facilities need to collaborate on WSI analysis without the possibility of sharing sensitive patient data. A more practical and secure approach involves sharing models capable of continual adaptation to new data. However, without proper measures, catastrophic forgetting can occur. Traditional continual learning techniques rely on storing previous data, which violates privacy restrictions. To address this issue, this paper introduces Context Optimization Multiple Instance Learning (CooMIL), a rehearsal-free continual learning framework designed explicitly for WSI analysis. It employs a WSI-specific prompt learning procedure to adapt classification models across tasks, efficiently preventing catastrophic forgetting. Evaluated on four public WSI datasets from TCGA projects, our model significantly outperforms state-of-the-art methods within the WSI-based continual learning framework. The source code is available at https://github.com/FrancescaMiccolis/CooMIL

Submission Number: 20