Pitfalls of topology-aware image segmentation
Preprint
Abstract
Topological correctness, i.e., the preservation of structural integrity and specific characteristics of shape, is a fundamental requirement for medical imaging tasks, such as neuron or vessel segmentation. Despite the recent surge in topology-aware methods addressing this challenge, their real-world applicability is hindered by flawed benchmarking practices. In this paper, we identify critical pitfalls in model evaluation that include inadequate connectivity choices, overlooked topological artifacts in ground truth annotations, and inappropriate use of evaluation metrics. Through detailed empirical analysis, we uncover these issues' profound impact on the evaluation and ranking of segmentation methods. Drawing from our findings, we propose a set of actionable recommendations to establish fair and robust evaluation standards for topology-aware medical image segmentation methods.Keywords
All Related Versions
This publication has 27 references indexed in Scilit:
- Understanding metric-related pitfalls in image analysis validationNature Methods, 2024
- Metrics reloaded: recommendations for image analysis validationNature Methods, 2024
- The Persistent Homology of Dual Digital Image Constructions2022
- Machine learning analysis of whole mouse brain vasculatureNature Methods, 2020
- High-precision automated reconstruction of neurons with flood-filling networksNature Methods, 2018
- Longitudinal multiple sclerosis lesion segmentation: Resource and challengeNeuroImage, 2017
- TED: A Tolerant Edit Distance for segmentation evaluationMethods, 2017
- Saturated Reconstruction of a Volume of NeocortexCell, 2015
- Comparing clusterings—an information based distanceJournal of Multivariate Analysis, 2007
- Comparing partitionsJournal of Classification, 1985