Shapley Values-enabled Progressive Pseudo Bag Augmentation for Whole Slide Image Classification
This work addresses a key bottleneck in computational pathology for weakly supervised classification, offering enhanced interpretability, though it is incremental as it builds on existing multiple-instance learning methods.
The paper tackles the challenge of identifying crucial instances in whole-slide image classification by using Shapley values to improve instance importance estimation and progressive pseudo bag augmentation, achieving state-of-the-art results on multiple datasets like CAMELYON-16 and TCGA-LUNG.
In computational pathology, whole-slide image (WSI) classification presents a formidable challenge due to its gigapixel resolution and limited fine-grained annotations. Multiple-instance learning (MIL) offers a weakly supervised solution, yet refining instance-level information from bag-level labels remains challenging. While most of the conventional MIL methods use attention scores to estimate instance importance scores (IIS) which contribute to the prediction of the slide labels, these often lead to skewed attention distributions and inaccuracies in identifying crucial instances. To address these issues, we propose a new approach inspired by cooperative game theory: employing Shapley values to assess each instance's contribution, thereby improving IIS estimation. The computation of the Shapley value is then accelerated using attention, meanwhile retaining the enhanced instance identification and prioritization. We further introduce a framework for the progressive assignment of pseudo bags based on estimated IIS, encouraging more balanced attention distributions in MIL models. Our extensive experiments on CAMELYON-16, BRACS, TCGA-LUNG, and TCGA-BRCA datasets show our method's superiority over existing state-of-the-art approaches, offering enhanced interpretability and class-wise insights. Our source code is available at https://github.com/RenaoYan/PMIL.