Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis

TL;DR

This paper introduces CoMEL, a novel continual multiple instance learning framework for histopathological whole slide images, enhancing localization and adaptability with minimal forgetting, and demonstrating superior performance over existing methods.

Contribution

The paper proposes CoMEL, combining GDAT, BPPL, and OWLoRA to improve continual MIL for WSIs, addressing large patch challenges and minimizing forgetting.

Findings

Outperforms prior methods by up to 11% in bag accuracy

Achieves up to 23.4% improvement in localization accuracy

Demonstrates effectiveness on three public WSI datasets

Abstract

Multiple instance learning (MIL) significantly reduced annotation costs via bag-level weak labels for large-scale images, such as histopathological whole slide images (WSIs). However, its adaptability to continual tasks with minimal forgetting has been rarely explored, especially on instance classification for localization. Weakly incremental learning for semantic segmentation has been studied for continual localization, but it focused on natural images, leveraging global relationships among hundreds of small patches (e.g., $16 \times 16$) using pre-trained models. This approach seems infeasible for MIL localization due to enormous amounts ($\sim 10^5$) of large patches (e.g., $256 \times 256$) and no available global relationships such as cancer cells. To address these challenges, we propose Continual Multiple Instance Learning with Enhanced Localization (CoMEL), an MIL framework for both localization and adaptability with minimal forgetting. CoMEL consists of (1) Grouped Double Attention Transformer (GDAT) for efficient instance encoding, (2) Bag Prototypes-based Pseudo-Labeling (BPPL) for reliable instance pseudo-labeling, and (3) Orthogonal Weighted Low-Rank Adaptation (OWLoRA) to mitigate forgetting in both bag and instance classification. Extensive experiments on three public WSI datasets demonstrate superior performance of CoMEL, outperforming the prior arts by up to $11.00\%$ in bag-level accuracy and up to $23.4\%$ in localization accuracy under the continual MIL setup.