Pathological Prior-Guided Multiple Instance Learning For Mitigating Catastrophic Forgetting in Breast Cancer Whole Slide Image Classification
This addresses the problem of model forgetting in histopathology diagnosis for pathologists, but it is incremental as it builds on existing multiple instance learning and continual learning techniques.
The paper tackles catastrophic forgetting in breast cancer whole slide image classification during incremental training by proposing PaGMIL, which uses pathological priors to select patches and guide classification heads, achieving a better balance between current task performance and retention of previous tasks compared to other methods.
In histopathology, intelligent diagnosis of Whole Slide Images (WSIs) is essential for automating and objectifying diagnoses, reducing the workload of pathologists. However, diagnostic models often face the challenge of forgetting previously learned data during incremental training on datasets from different sources. To address this issue, we propose a new framework PaGMIL to mitigate catastrophic forgetting in breast cancer WSI classification. Our framework introduces two key components into the common MIL model architecture. First, it leverages microscopic pathological prior to select more accurate and diverse representative patches for MIL. Secondly, it trains separate classification heads for each task and uses macroscopic pathological prior knowledge, treating the thumbnail as a prompt guide (PG) to select the appropriate classification head. We evaluate the continual learning performance of PaGMIL across several public breast cancer datasets. PaGMIL achieves a better balance between the performance of the current task and the retention of previous tasks, outperforming other continual learning methods. Our code will be open-sourced upon acceptance.