MB-DSMIL-CL-PL: Scalable Weakly Supervised Ovarian Cancer Subtype Classification and Localisation Using Contrastive and Prototype Learning with Frozen Patch Features
This addresses the challenge of scalable AI-assisted diagnosis for ovarian cancer subtypes in pathology departments, though it is incremental as it builds on existing frozen feature approaches.
The paper tackles ovarian cancer subtype classification and localization from histopathology images by proposing a method using contrastive and prototype learning with frozen patch features, achieving improvements of 70.4% and 15.3% in F1 scores for instance- and slide-level classification, and 16.9% AUC gain for instance localization.
The study of histopathological subtypes is valuable for the personalisation of effective treatment strategies for ovarian cancer. However, increasing diagnostic workloads present a challenge for UK pathology departments, leading to the rise in AI approaches. While traditional approaches in this field have relied on pre-computed, frozen image features, recent advances have shifted towards end-to-end feature extraction, providing an improvement in accuracy but at the expense of significantly reduced scalability during training and time-consuming experimentation. In this paper, we propose a new approach for subtype classification and localisation in ovarian cancer histopathology images using contrastive and prototype learning with pre-computed, frozen features via feature-space augmentations. Compared to DSMIL, our method achieves an improvement of 70.4\% and 15.3\% in F1 score for instance- and slide-level classification, respectively, along with AUC gains of 16.9\% for instance localisation and 2.3\% for slide classification, while maintaining the use of frozen patch features.