Domain Adaptation-based Augmentation for Weakly Supervised Nuclei Detection
This addresses the challenge of high labeling costs and domain diversity in pathology for researchers and clinicians, though it is incremental as it builds on existing domain adaptation and weak supervision techniques.
The paper tackles the problem of reducing labeling effort for nuclei detection in computational pathology by introducing a weakly supervised inter-domain approach that uses stain normalization and image translation to generate synthetic labeled images for an unlabeled target domain, achieving superiority over state-of-the-art fully-supervised methods in experiments.
The detection of nuclei is one of the most fundamental components of computational pathology. Current state-of-the-art methods are based on deep learning, with the prerequisite that extensive labeled datasets are available. The increasing number of patient cohorts to be analyzed, the diversity of tissue stains and indications, as well as the cost of dataset labeling motivates the development of novel methods to reduce labeling effort across domains. We introduce in this work a weakly supervised 'inter-domain' approach that (i) performs stain normalization and unpaired image-to-image translation to transform labeled images on a source domain to synthetic labeled images on an unlabeled target domain and (ii) uses the resulting synthetic labeled images to train a detection network on the target domain. Extensive experiments show the superiority of the proposed approach against the state-of-the-art 'intra-domain' detection based on fully-supervised learning.