Left Ventricle Segmentation in Cardiac MR Images via an Improved ResUnet

• Published in: International journal of biomedical imaging Vol. 2022; pp. 1 - 10
• Main Authors: Xu, Shengzhou, Lu, Haoran, Cheng, Shiyu, Pei, Chengdan
• Format: Journal Article
• Language: English
• Published: United States Hindawi 08.07.2022; John Wiley & Sons, Inc; Wiley
• Subjects: Accuracy; Automation; Cardiology; Cardiovascular diseases; Convolution; Datasets; Deep learning; Efficiency; Epicardium; Heart; Heart failure; Image enhancement; Image processing; Image segmentation; Ischemia; Magnetic resonance imaging; Medical imaging; Medical imaging equipment; Methods; Model accuracy; Neural networks; Performance enhancement; Ventricle
• ISSN: 1687-4188; 1687-4196
• DOI: 10.1155/2022/8669305

Cardiovascular diseases are reported as the leading cause of death around the world. Automatic segmentation of the left ventricle (LV) from magnetic resonance (MR) images is essential for an early diagnosis. An enhanced ResUnet is proposed in this paper to improve the performance of extracting LV endocardium and epicardium from MR images, improving the accuracy of the model by introducing a medium skip connection for the contracting path and a short skip connection for the residual unit. Also, a depth-wise separable convolution replaces the typical convolution operation to improve training efficiency. In the MICCAI 2009 LV segmentation challenge test dataset, the percentages of “good” contours, dice metric, and average perpendicular distance of endocardium (epicardium) are 99.12%±2.29%100%±0%,0.93±0.02 0.96±0.01,and 1.60±0.42 mm 1.37±0.23 mm, respectively. Experimental results demonstrate that the proposed model obtains promising performance and outperforms state-of-the-art methods. By incorporating these various skip connections, the segmentation accuracy of the model is significantly improved, while the depth-wise separable convolution also improves the model efficiency.