Topologically faithful image segmentation via induced matching of persistence barcodes

11/28/2022
by   Nico Stucki, et al.
0

Image segmentation is a largely researched field where neural networks find vast applications in many facets of technology. Some of the most popular approaches to train segmentation networks employ loss functions optimizing pixel-overlap, an objective that is insufficient for many segmentation tasks. In recent years, their limitations fueled a growing interest in topology-aware methods, which aim to recover the correct topology of the segmented structures. However, so far, none of the existing approaches achieve a spatially correct matching between the topological features of ground truth and prediction. In this work, we propose the first topologically and feature-wise accurate metric and loss function for supervised image segmentation, which we term Betti matching. We show how induced matchings guarantee the spatially correct matching between barcodes in a segmentation setting. Furthermore, we propose an efficient algorithm to compute the Betti matching of images. We show that the Betti matching error is an interpretable metric to evaluate the topological correctness of segmentations, which is more sensitive than the well-established Betti number error. Moreover, the differentiability of the Betti matching loss enables its use as a loss function. It improves the topological performance of segmentation networks across six diverse datasets while preserving the volumetric performance. Our code is available in https://github.com/nstucki/Betti-matching.

READ FULL TEXT

page 8

page 13

page 14

page 15

page 16

page 17

page 18

page 19

research
06/12/2019

Topology-Preserving Deep Image Segmentation

Segmentation algorithms are prone to make topological errors on fine-sca...
research
03/31/2023

The Topology-Overlap Trade-Off in Retinal Arteriole-Venule Segmentation

Retinal fundus images can be an invaluable diagnosis tool for screening ...
research
12/15/2021

Structure-Aware Image Segmentation with Homotopy Warping

Besides per-pixel accuracy, topological correctness is also crucial for ...
research
04/24/2023

Topology-Aware Focal Loss for 3D Image Segmentation

The efficacy of segmentation algorithms is frequently compromised by top...
research
03/16/2020

clDice – a Topology-Preserving Loss Function for Tubular Structure Segmentation

Accurate segmentation of tubular, network-like structures, such as vesse...
research
07/23/2022

BuyTheDips: PathLoss for improved topology-preserving deep learning-based image segmentation

Capturing the global topology of an image is essential for proposing an ...
research
07/06/2023

Topology-Aware Loss for Aorta and Great Vessel Segmentation in Computed Tomography Images

Segmentation networks are not explicitly imposed to learn global invaria...

Please sign up or login with your details

Forgot password? Click here to reset