An Attentive Representative Sample Selection Strategy Combined with Balanced Batch Training for Skin Lesion Segmentation
This work addresses the challenge of optimizing annotation efforts for skin lesion segmentation, which is incremental as it builds on prior sampling methods with specific improvements.
The paper tackled the problem of selecting effective training subsets for annotation in medical image segmentation, particularly under minimal supervision, by using prototypical contrasting learning and clustering to choose representative samples and introducing unsupervised balanced batch dataloading. The method achieved superior performance on the ISIC 2018 skin lesion dataset compared to a state-of-the-art data sampling method in low annotation budget scenarios.
An often overlooked problem in medical image segmentation research is the effective selection of training subsets to annotate from a complete set of unlabelled data. Many studies select their training sets at random, which may lead to suboptimal model performance, especially in the minimal supervision setting where each training image has a profound effect on performance outcomes. This work aims to address this issue. We use prototypical contrasting learning and clustering to extract representative and diverse samples for annotation. We improve upon prior works with a bespoke cluster-based image selection process. Additionally, we introduce the concept of unsupervised balanced batch dataloading to medical image segmentation, which aims to improve model learning with minimally annotated data. We evaluated our method on a public skin lesion dataset (ISIC 2018) and compared it to another state-of-the-art data sampling method. Our method achieved superior performance in a low annotation budget scenario.