ContextLoss: Context Information for Topology-Preserving Segmentation
This work addresses topological errors in segmentation for applications like navigation and medical imaging, representing an incremental improvement over existing loss functions.
The paper tackles the problem of preserving topology in image segmentation, such as for road networks, by proposing a novel loss function called ContextLoss that improves topological correctness by considering errors with their full context, resulting in up to 44% more repaired missed connections compared to state-of-the-art methods.
In image segmentation, preserving the topology of segmented structures like vessels, membranes, or roads is crucial. For instance, topological errors on road networks can significantly impact navigation. Recently proposed solutions are loss functions based on critical pixel masks that consider the whole skeleton of the segmented structures in the critical pixel mask. We propose the novel loss function ContextLoss (CLoss) that improves topological correctness by considering topological errors with their whole context in the critical pixel mask. The additional context improves the network focus on the topological errors. Further, we propose two intuitive metrics to verify improved connectivity due to a closing of missed connections. We benchmark our proposed CLoss on three public datasets (2D & 3D) and our own 3D nano-imaging dataset of bone cement lines. Training with our proposed CLoss increases performance on topology-aware metrics and repairs up to 44% more missed connections than other state-of-the-art methods. We make the code publicly available.