Semi-supervised Segmentation of Histopathology Images with Noise-Aware Topological Consistency
This work addresses the need for accurate segmentation in digital pathology to reduce annotation time, though it is incremental as it builds on existing semi-supervised methods by focusing on topological consistency.
The paper tackles the problem of topological errors in semi-supervised segmentation of histopathology images, such as missing or incorrectly merged glands, by proposing TopoSemiSeg with a noise-aware topological consistency loss, achieving superior performance on topology-aware metrics in experiments on public datasets.
In digital pathology, segmenting densely distributed objects like glands and nuclei is crucial for downstream analysis. Since detailed pixel-wise annotations are very time-consuming, we need semi-supervised segmentation methods that can learn from unlabeled images. Existing semi-supervised methods are often prone to topological errors, e.g., missing or incorrectly merged/separated glands or nuclei. To address this issue, we propose TopoSemiSeg, the first semi-supervised method that learns the topological representation from unlabeled histopathology images. The major challenge is for unlabeled images; we only have predictions carrying noisy topology. To this end, we introduce a noise-aware topological consistency loss to align the representations of a teacher and a student model. By decomposing the topology of the prediction into signal topology and noisy topology, we ensure that the models learn the true topological signals and become robust to noise. Extensive experiments on public histopathology image datasets show the superiority of our method, especially on topology-aware evaluation metrics. Code is available at https://github.com/Melon-Xu/TopoSemiSeg.