Cluster-Guided Semi-Supervised Domain Adaptation for Imbalanced Medical Image Classification
This addresses domain adaptation for imbalanced medical image classification, which is an incremental improvement with specific application to pathology.
The paper tackled the problem of class-imbalanced medical image classification by developing a semi-supervised domain adaptation method with a clustering pipeline, achieving state-of-the-art performance on severely imbalanced pathological image patches.
Semi-supervised domain adaptation is a technique to build a classifier for a target domain by modifying a classifier in another (source) domain using many unlabeled samples and a small number of labeled samples from the target domain. In this paper, we develop a semi-supervised domain adaptation method, which has robustness to class-imbalanced situations, which are common in medical image classification tasks. For robustness, we propose a weakly-supervised clustering pipeline to obtain high-purity clusters and utilize the clusters in representation learning for domain adaptation. The proposed method showed state-of-the-art performance in the experiment using severely class-imbalanced pathological image patches.