Efficient Betti Matching Enables Topology-Aware 3D Segmentation via Persistent Homology

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Stucki, Nico, Bürgin, Vincent, Paetzold, Johannes C., Bauer, Ulrich
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913418668146688
author Stucki, Nico
Bürgin, Vincent
Paetzold, Johannes C.
Bauer, Ulrich
author_facet Stucki, Nico
Bürgin, Vincent
Paetzold, Johannes C.
Bauer, Ulrich
contents In this work, we propose an efficient algorithm for the calculation of the Betti matching, which can be used as a loss function to train topology aware segmentation networks. Betti matching loss builds on techniques from topological data analysis, specifically persistent homology. A major challenge is the computational cost of computing persistence barcodes. In response to this challenge, we propose a new, highly optimized implementation of Betti matching, implemented in C++ together with a python interface, which achieves significant speedups compared to the state-of-the-art implementation Cubical Ripser. We use Betti matching 3D to train segmentation networks with the Betti matching loss and demonstrate improved topological correctness of predicted segmentations across several datasets. The source code is available at https://github.com/nstucki/Betti-Matching-3D.
format Preprint
id arxiv_https___arxiv_org_abs_2407_04683
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Efficient Betti Matching Enables Topology-Aware 3D Segmentation via Persistent Homology
Stucki, Nico
Bürgin, Vincent
Paetzold, Johannes C.
Bauer, Ulrich
Algebraic Topology
Computer Vision and Pattern Recognition
In this work, we propose an efficient algorithm for the calculation of the Betti matching, which can be used as a loss function to train topology aware segmentation networks. Betti matching loss builds on techniques from topological data analysis, specifically persistent homology. A major challenge is the computational cost of computing persistence barcodes. In response to this challenge, we propose a new, highly optimized implementation of Betti matching, implemented in C++ together with a python interface, which achieves significant speedups compared to the state-of-the-art implementation Cubical Ripser. We use Betti matching 3D to train segmentation networks with the Betti matching loss and demonstrate improved topological correctness of predicted segmentations across several datasets. The source code is available at https://github.com/nstucki/Betti-Matching-3D.
title Efficient Betti Matching Enables Topology-Aware 3D Segmentation via Persistent Homology
topic Algebraic Topology
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.04683