Evaluation of state-of-the-art segmentation algorithms for left ventricle infarct from late Gadolinium enhancement MR images

Abstract

Studies have demonstrated the feasibility of late Gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging for guiding the management of patients with sequelae to myocardial infarction, such as ventricular tachycardia and heart failure. Clinical implementation of these developments necessitates a reproducible and reliable segmentation of the infarcted regions. It is challenging to compare new algorithms for infarct segmentation in the left ventricle (LV) with existing algorithms. Benchmarking datasets with evaluation strategies are much needed to facilitate comparison. This manuscript presents a benchmarking evaluation framework for future algorithms that segment infarct from LGE CMR of the LV. The image database consists of 30 LGE CMR images of both humans and pigs that were acquired from two separate imaging centres. A consensus ground truth was obtained for all data using maximum likelihood estimation. Six widely-used fixed-thresholding methods and five recently developed algorithms are tested on the benchmarking framework. Results demonstrate that the algorithms have better overlap with the consensus ground truth than most of the n-SD fixed-thresholding methods, with the exception of the Full-Width-at-Half-Maximum (FWHM) fixed-thresholding method. Some of the pitfalls of fixed thresholding methods are demonstrated in this work. The benchmarking evaluation framework, which is a contribution of this work, can be used to test and benchmark future algorithms that detect and quantify infarct in LGE CMR images of the LV. The datasets, ground truth and evaluation code have been made publicly available through the website: https://www.cardiacatlas.org/web/guest/challenges.

Automated Scar Segmentation From Cardiac Magnetic Resonance-Late Gadolinium Enhancement Images Using a Deep-Learning Approach

“…For each of the three protocols, CMR-LGE images were pre-processed prior to FCNN training and testing. In particular, CMR-LGE images were automatically cropped to reduce the processing area, as commonly suggested in the literature [8]. The circular structure was used to identify the LV cavity in the CMR-LGE image.…”

Real‐time MRI guidance of cardiac interventions

“…Markov random field, graph cuts). 70–72 Moreover, multi-atlas segmentation methods can use prior anatomical knowledge and combine intensity, gradient and contextual information into an augmented feature vector to guide the label fusion of cardiac structures by support vector machine classifiers, significantly improving the segmentation accuracy. 73 …”

“…69 The most popular segmentation methods employed to delineate structures (eg, chamber walls in cine images, infarcted areas in 2D/3D LGE images, or RF ablation lesions) are typically based on manual or semiautomated algorithms such as: classification (thresholding, k-means), deformable models (eg, snake, level-set), atlases, and probabilistic methods (eg, Markov random field, graph cuts). [70][71][72] Moreover, multiatlas segmentation methods can use prior anatomical knowledge and combine intensity, gradient, and contextual information into an augmented feature vector to guide the label fusion of cardiac structures by support vector machine classifiers, significantly improving the segmentation accuracy. 73 Further developments are under way to implement optimization schemes that can speed up segmentation methods, to identify atrial/ventricular walls from surrounding structures and to generate intraoperative 3D whole heart (WH) models/shells.…”

Cardiac imaging: working towards fully-automated machine analysis & interpretation

“…As the latter is not particularly burdensome, automated methods have not become particularly widespread or utilized for this purpose. Nonetheless, several studies have successfully shown the feasibility of automating segmentation of LGE images and quantifying scar burden as percentage myocardium or absolute volume [84–91]. Most methods employed simple standard deviation thresholding from a base healthy tissue intensity value.…”