Learning from Partially Overlapping Labels: Image Segmentation under Annotation Shift
This addresses the scarcity of high-quality annotated images for abdominal organ segmentation, though it is incremental as it builds on existing methods for handling annotation heterogeneity.
The paper tackles the problem of training accurate image segmentation models by combining heterogeneously annotated datasets with partially overlapping labels, and finds that a semi-supervised approach with an adaptive cross entropy loss substantially improves segmentation accuracy compared to baselines.
Scarcity of high quality annotated images remains a limiting factor for training accurate image segmentation models. While more and more annotated datasets become publicly available, the number of samples in each individual database is often small. Combining different databases to create larger amounts of training data is appealing yet challenging due to the heterogeneity as a result of differences in data acquisition and annotation processes, often yielding incompatible or even conflicting information. In this paper, we investigate and propose several strategies for learning from partially overlapping labels in the context of abdominal organ segmentation. We find that combining a semi-supervised approach with an adaptive cross entropy loss can successfully exploit heterogeneously annotated data and substantially improve segmentation accuracy compared to baseline and alternative approaches.