Saved in:
Bibliographic Details
Main Authors: Lux, Laurin, Berger, Alexander H., Weers, Alexander, Stucki, Nico, Rueckert, Daniel, Bauer, Ulrich, Paetzold, Johannes C.
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.03228
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Topological correctness plays a critical role in many image segmentation tasks, yet most networks are trained using pixel-wise loss functions, such as Dice, neglecting topological accuracy. Existing topology-aware methods often lack robust topological guarantees, are limited to specific use cases, or impose high computational costs. In this work, we propose a novel, graph-based framework for topologically accurate image segmentation that is both computationally efficient and generally applicable. Our method constructs a component graph that fully encodes the topological information of both the prediction and ground truth, allowing us to efficiently identify topologically critical regions and aggregate a loss based on local neighborhood information. Furthermore, we introduce a strict topological metric capturing the homotopy equivalence between the union and intersection of prediction-label pairs. We formally prove the topological guarantees of our approach and empirically validate its effectiveness on binary and multi-class datasets. Our loss demonstrates state-of-the-art performance with up to fivefold faster loss computation compared to persistent homology methods.