Topologically Faithful Multi-class Segmentation in Medical Images

Authors:
  • ABAlexander H. Berger
    Alexander H. Berger
  • NSNico Stucki
    Nico Stucki
  • LLLaurin Lux
    Laurin Lux
  • VBVincent Buergin
    Vincent Buergin
  • SSSuprosanna Shit
    Suprosanna Shit
  • ABAnna Banaszak
    Anna Banaszak
  • DRDaniel Rueckert
    Daniel Rueckert
  • UBUlrich Bauer
    Ulrich Bauer
  • JPJohannes C. Paetzold
    Johannes C. Paetzold

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.