From Zero to Topo ( Part 3)

A journey to learn about topology-preserving image segmentation. We continue the journey with the third paper about this topic "Topology-Preserving Deep Image Segmentation". As we mentioned in the previous articles, the state-of-the-art segmentation algorithms are still prone to make errors on fine-scale structures, such as small object instances, instances with multiple connected components, and thin connections. Therefore, Xiaoling et al. propose TopoNet, a novel deep segmentation method that learns to segment with correct topology. In particular, they proposed a topological loss that enforces the segmentation results to have the same topology as the ground truth, i.e., having the same Betti number (number of connected components and handles).