Continual Multiple Instance Learning with Enhanced Localization for Histopathological Whole Slide Image Analysis
By: Byung Hyun Lee , Wongi Jeong , Woojae Han and more
Potential Business Impact:
Helps doctors find cancer faster with less work.
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.
Similar Papers
Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imaging
CV and Pattern Recognition
Helps AI learn new medical images without forgetting.
Cluster-Level Sparse Multi-Instance Learning for Whole-Slide Images
CV and Pattern Recognition
Finds important spots in medical pictures.
A Spatially-Aware Multiple Instance Learning Framework for Digital Pathology
Image and Video Processing
Helps doctors find cancer faster and better.