Key result
A combined deep-learning approach using YOLO and UNet achieved high segmentation accuracy for the LV epicardium and endocardium in CMR images.
Why the study?
Quantification of left ventricle parameters across all cardiac magnetic resonance imaging frames is very time consuming even for experienced radiologists.
Does a combined deep-learning approach (YOLO and UNet) accurately segment the left ventricle in short-axis cardiac magnetic resonance imaging?
Does a combined deep-learning approach (YOLO and UNet) accurately segment the left ventricle in short-axis cardiac magnetic resonance imaging?
A combined CNN approach using YOLO and UNet provides accurate fully automatic left ventricle segmentation in short-axis CMR datasets.
Answers are grounded in this paper and cite their sources.
Supports automated LV segmentation in CMR research; leaves open prospective clinical validation before adoption.
In clinical practice, cardiac magnetic resonance imaging (CMR) is considered the gold-standard imaging modality for the evaluation of function and structure of the left ventricle (LV). However, the quantification of LV parameters in all frames, even when performed by experienced radiologists, is very time consuming mainly due to the inhomogeneity of cardiac structures within each image, the variability of the cardiac structures across subjects and the complicated global/regional temporal deformation of the myocardium during the cardiac cycle. In this work, we employed a combination of two convolutional neural networks (CNN) to develop a fully automatic LV segmentation method for Short Axis CMR datasets. The first CNN defines the region of interest (ROI) of the cardiac chambers based on You Only Look Once (YOLO) network. The output of YOLO net is used to filter the image and feed the second CNN, based on UNet network, which segments the myocardium and the blood pool. The method was validated in CMR exams of 59 individuals from an institutional clinical protocol. Segmentation results, evaluated by metrics Percentage of Good Contours, Dice Index and Average Perpendicular distance, were 98,59% ± 4,28%, 0,93 ± 0,06 and 0,72 mm ± 0,62 mm, respectively, for the LV epicardium, and 94,98% ± 14,04%, 0,86 ± 0,13 and 1,19 mm ± 1,29 mm, respectively, for the LV endocardium. The combination of two CNNs demonstrated good performance in terms of the evaluated metrics when compared to literature results.
No takes yet. Share an insight, caveat, or question.
Moreno et al. (2019) studied Individuals undergoing cardiac magnetic resonance imaging (n=59). Combined deep-learning approach (YOLO and UNet) was evaluated on Segmentation performance (Percentage of Good Contours, Dice Index, Average Perpendicular distance). A combined deep-learning approach using YOLO and UNet achieved high segmentation accuracy for the LV epicardium and endocardium in CMR images.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: