Cardiac MRI Left Ventricle Segmentation and Quantification: A Framework Combining U-Net and Continuous Max-Flow

• Published in: Statistical Atlases and Computational Models of the Heart. Atrial Segmentation and LV Quantification Challenges Vol. 11395; pp. 450 - 458
• Main Authors: Guo, Fumin, Ng, Matthew, Wright, Graham
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2019; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Cardiac MRI segmentation; Continuous max-flow; Deep learning; LV function quantification
• ISBN: 9783030120283; 3030120287
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-12029-0_48

Cardiac magnetic resonance imaging (MRI) is routinely used for cardiovascular disease diagnosis and therapy guidance. Left ventricle (LV) segmentation is typically required as a first step to quantify cardiac indices. In this work, we developed an automatic approach for LV segmentation and indices quantification of cardiac MRI. We employed a U-net convolutional neural network to generate LV segmentation probability maps. The initial probability maps were used to provide the labeling cost measurements of a continuous min-cut segmentation model and the final segmentation was regularized using image edge information. The continuous min-cut segmentation model was solved globally and exactly through convex relaxation and dual optimization on a GPU. We applied our approach to a clinical dataset of 45 subjects and achieved a mean DSC of $$89.4\pm 5.0\%$$ and average symmetric surface distance of $$0.81\pm 0.31$$  mm for LV myocardium segmentation. For LV indices quantification, we observed a mean absolute error of 114.8 mm $$^2$$ for LV cavity, 168.6 mm $$^2$$ for LV myocardium, $$\sim $$ 1.8 mm for LV cavity dimensions, and 1.2 $${\sim }$$ 1.6 mm for LV myocardium wall thickness measurements. These results suggest that our framework provide the potential for LV function quantification using cardiac MRI.