MergeUp-augmented Semi-Weakly Supervised Learning for WSI Classification
This work addresses the problem of noisy labels in weakly supervised learning for computational pathology, offering an incremental improvement for WSI classification.
The paper tackled the challenge of whole slide image classification by addressing noise from pseudo bag augmentation, proposing a semi-weakly supervised learning method with adaptive pseudo bag assignment and MergeUp feature augmentation. Experimental results on CAMELYON-16, BRACS, and TCGA-LUNG datasets showed superiority over state-of-the-art approaches, though no specific numbers were provided.
Recent advancements in computational pathology and artificial intelligence have significantly improved whole slide image (WSI) classification. However, the gigapixel resolution of WSIs and the scarcity of manual annotations present substantial challenges. Multiple instance learning (MIL) is a promising weakly supervised learning approach for WSI classification. Recently research revealed employing pseudo bag augmentation can encourage models to learn various data, thus bolstering models' performance. While directly inheriting the parents' labels can introduce more noise by mislabeling in training. To address this issue, we translate the WSI classification task from weakly supervised learning to semi-weakly supervised learning, termed SWS-MIL, where adaptive pseudo bag augmentation (AdaPse) is employed to assign labeled and unlabeled data based on a threshold strategy. Using the "student-teacher" pattern, we introduce a feature augmentation technique, MergeUp, which merges bags with low-priority bags to enhance inter-category information, increasing training data diversity. Experimental results on the CAMELYON-16, BRACS, and TCGA-LUNG datasets demonstrate the superiority of our method over existing state-of-the-art approaches, affirming its efficacy in WSI classification.