Topologically Faithful Multi-class Segmentation in Medical Images
Authors:
- Alexander H. BergerABAlexander H. Berger
- Nico StuckiNSNico Stucki
- Laurin LuxLLLaurin Lux
- Vincent BuerginVBVincent Buergin
- Suprosanna ShitSSSuprosanna Shit
- Anna BanaszakABAnna Banaszak
- Daniel RueckertDRDaniel Rueckert
- Ulrich BauerUBUlrich Bauer
- Johannes C. PaetzoldJPJohannes C. Paetzold
Preprint
Abstract
Topological accuracy in medical image segmentation is a highly important property for downstream applications such as network analysis and flow modeling in vessels or cell counting. Recently, significant methodological advancements have brought well-founded concepts from algebraic topology to binary segmentation. However, these approaches have been underexplored in multi-class segmentation scenarios, where topological errors are common. We propose a general loss function for topologically faithful multi-class segmentation extending the recent Betti matching concept, which is based on induced matchings of persistence barcodes. We project the N-class segmentation problem to N single-class segmentation tasks, which allows us to use 1-parameter persistent homology, making training of neural networks computationally feasible. We validate our method on a comprehensive set of four medical datasets with highly variant topological characteristics. Our loss formulation significantly enhances topological correctness in cardiac, cell, artery-vein, and Circle of Willis segmentation.Keywords
All Related Versions
- Version 1, 2024-03-16, ArXiv
- Version 2, 2024-10-09, ArXiv
- Published version: , 721.