Timezone: »

Topology-Preserving Deep Image Segmentation
Xiaoling Hu · Fuxin Li · Dimitris Samaras · Chao Chen

Wed Dec 11 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #83

Segmentation algorithms are prone to make topological errors on fine-scale struc- tures, e.g., broken connections. We propose a novel method that learns to segment with correct topology. In particular, we design a continuous-valued loss function that enforces a segmentation to have the same topology as the ground truth, i.e.,having the same Betti number. The proposed topology-preserving loss function is differentiable and can be incorporated into end-to-end training of a deep neural network. Our method achieves much better performance on the Betti number error, which directly accounts for the topological correctness. It also performs superior on other topology-relevant metrics, e.g., the Adjusted Rand Index and the Variation of Information, without sacrificing per-pixel accuracy. We illustrate the effectiveness of the proposed method on a broad spectrum of natural and biomedical datasets.

Author Information

Xiaoling Hu (Stony Brook University)
Fuxin Li (Oregon State University)
Dimitris Samaras (Stony Brook University)
Chao Chen (Stony Brook University)

More from the Same Authors