NearbyPatchCL: Leveraging Nearby Patches for Self-Supervised Patch-Level Multi-Class Classification in Whole-Slide Images
This work addresses patch-level multi-class classification in whole-slide images for cancer diagnosis, offering a novel self-supervised approach that reduces annotation needs, but it is incremental as it builds on existing contrastive learning methods.
The paper tackles the problem of unstable patch-wise representation in whole-slide image analysis for cancer diagnosis by introducing NearbyPatchCL, a self-supervised learning method that uses nearby patches as positive samples and a decoupled contrastive loss, achieving a top-1 classification accuracy of 87.56% and comparable results with only 1% labeled data.
Whole-slide image (WSI) analysis plays a crucial role in cancer diagnosis and treatment. In addressing the demands of this critical task, self-supervised learning (SSL) methods have emerged as a valuable resource, leveraging their efficiency in circumventing the need for a large number of annotations, which can be both costly and time-consuming to deploy supervised methods. Nevertheless, patch-wise representation may exhibit instability in performance, primarily due to class imbalances stemming from patch selection within WSIs. In this paper, we introduce Nearby Patch Contrastive Learning (NearbyPatchCL), a novel self-supervised learning method that leverages nearby patches as positive samples and a decoupled contrastive loss for robust representation learning. Our method demonstrates a tangible enhancement in performance for downstream tasks involving patch-level multi-class classification. Additionally, we curate a new dataset derived from WSIs sourced from the Canine Cutaneous Cancer Histology, thus establishing a benchmark for the rigorous evaluation of patch-level multi-class classification methodologies. Intensive experiments show that our method significantly outperforms the supervised baseline and state-of-the-art SSL methods with top-1 classification accuracy of 87.56%. Our method also achieves comparable results while utilizing a mere 1% of labeled data, a stark contrast to the 100% labeled data requirement of other approaches. Source code: https://github.com/nvtien457/NearbyPatchCL