A persistent homology-based topological loss function for multi-class CNN segmentation of cardiac MRI
This work addresses the issue of implausible segmentations in cardiac MRI analysis, which is incremental by building on existing topological loss methods for multi-class tasks.
The paper tackled the problem of spatial incoherence in CNN-based cardiac MRI segmentation by extending topological loss functions to multi-class segmentation, resolving all topological errors in 150 examples from the ACDC dataset without compromising overlap performance.
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.