Less is More: Sample Selection and Label Conditioning Improve Skin Lesion Segmentation
This work addresses the problem of data scarcity in medical imaging segmentation for dermatology, but it is incremental as it builds on existing methods with specific optimizations.
The paper tackles the challenge of limited annotated data in skin lesion segmentation by showing that segmentation improves with less data through sample selection based on inter-annotator agreement and conditioning ground-truth masks to remove excessive detail, resulting in impacts equivalent to 12% and 16% of the gain from using a better deep-learning model.
Segmenting skin lesions images is relevant both for itself and for assisting in lesion classification, but suffers from the challenge in obtaining annotated data. In this work, we show that segmentation may improve with less data, by selecting the training samples with best inter-annotator agreement, and conditioning the ground-truth masks to remove excessive detail. We perform an exhaustive experimental design considering several sources of variation, including three different test sets, two different deep-learning architectures, and several replications, for a total of 540 experimental runs. We found that sample selection and detail removal may have impacts corresponding, respectively, to 12% and 16% of the one obtained by picking a better deep-learning model.