Key result
A combined deep-learning approach using YOLO and UNet achieved high segmentation accuracy for the LV epicardium (Dice Index 0.93) and endocardium (Dice Index 0.86) 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?
Population
59 individuals from an institutional clinical protocol with CMR exams
Comparison
Combined deep-learning approach (YOLO and UNet) for LV segmentation
Design
Validation study
Authors
Loading...
Supports automated LV segmentation in CMR research; leaves open prospective clinical validation before adoption.
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.
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 (Dice Index 0.93) and endocardium (Dice Index 0.86) in CMR images.
Synapse has enriched 2 closely related papers on similar clinical questions. Consider them for comparative context: