Contrastive Cross-Bag Augmentation for Multiple Instance Learning-based Whole Slide Image Classification
This work addresses a domain-specific problem in medical imaging for whole slide image classification, offering an incremental improvement over existing methods.
The paper tackled the limited diversity in pseudo-bag augmentation for Multiple Instance Learning-based Whole Slide Image classification by proposing Contrastive Cross-Bag Augmentation, which increased diversity but reduced performance on slides with small tumor areas, addressed with a contrastive learning framework that outperformed state-of-the-art methods across multiple metrics.
Recent pseudo-bag augmentation methods for Multiple Instance Learning (MIL)-based Whole Slide Image (WSI) classification sample instances from a limited number of bags, resulting in constrained diversity. To address this issue, we propose Contrastive Cross-Bag Augmentation ($C^2Aug$) to sample instances from all bags with the same class to increase the diversity of pseudo-bags. However, introducing new instances into the pseudo-bag increases the number of critical instances (e.g., tumor instances). This increase results in a reduced occurrence of pseudo-bags containing few critical instances, thereby limiting model performance, particularly on test slides with small tumor areas. To address this, we introduce a bag-level and group-level contrastive learning framework to enhance the discrimination of features with distinct semantic meanings, thereby improving model performance. Experimental results demonstrate that $C^2Aug$ consistently outperforms state-of-the-art approaches across multiple evaluation metrics.