A Persistent Homology-Based Topological Loss Function for Multi-class CNN Segmentation of Cardiac MRI
| Autor: | James R. Clough, Nick Byrne, Andrew P. King, Giovanni Montana |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Connected component Persistent homology Computer science Computer Vision and Pattern Recognition (cs.CV) Image and Video Processing (eess.IV) Computer Science - Computer Vision and Pattern Recognition Image segmentation Electrical Engineering and Systems Science - Image and Video Processing Topology Article Image (mathematics) Computer Science::Computer Vision and Pattern Recognition Prior probability FOS: Electrical engineering electronic engineering information engineering A priori and a posteriori Segmentation Topology (chemistry) |
| Zdroj: | Stat Atlases Comput Models Heart Statistical Atlases and Computational Models of the Heart. M&Ms and EMIDEC Challenges ISBN: 9783030681067 M&Ms and EMIDEC/STACOM@MICCAI |
| Popis: | With respect to spatial overlap, CNN-based segmentation of short axis cardiovascular magnetic resonance (CMR) images has achieved a level of performance consistent with inter observer variation. However, conventional training procedures frequently depend on pixel-wise loss functions, limiting optimisation with respect to extended or global features. As a result, inferred segmentations can lack spatial coherence, including spurious connected components or holes. Such results are implausible, violating the anticipated topology of image segments, which is frequently known a priori. Addressing this challenge, published work has employed persistent homology, constructing topological loss functions for the evaluation of image segments against an explicit prior. Building a richer description of segmentation topology by considering all possible labels and label pairs, we extend these losses to the task of multi-class segmentation. These topological priors allow us to resolve all topological errors in a subset of 150 examples from the ACDC short axis CMR training data set, without sacrificing overlap performance. To be presented at the STACOM workshop at MICCAI 2020 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|