Cluster-Based Learning from Weakly Labeled Bags in Digital Pathology
This work addresses the challenge of training deep neural networks with limited annotations for medical image analysis, specifically in digital pathology, and is incremental as it builds on existing weakly supervised methods.
The paper tackles the problem of reducing expert annotation burden in digital pathology by proposing a weakly supervised learning approach to detect metastases in breast lymph node images, achieving competitive performance on the Camelyon dataset with image-level labels and limited patch subsets during training.
To alleviate the burden of gathering detailed expert annotations when training deep neural networks, we propose a weakly supervised learning approach to recognize metastases in microscopic images of breast lymph nodes. We describe an alternative training loss which clusters weakly labeled bags in latent space to inform relevance of patch-instances during training of a convolutional neural network. We evaluate our method on the Camelyon dataset which contains high-resolution digital slides of breast lymph nodes, where labels are provided at the image-level and only subsets of patches are made available during training.