An 8-layer residual U-Net with deep supervision for segmentation of the left ventricle in cardiac CT angiography. (March 2021)

• Record Type: Journal Article
• Authors: Li, Changling; Song, Xiangfen; Zhao, Hang; Feng, Li; Hu, Tao; Zhang, Yuchen; Jiang, Jun; Wang, Jianan; Xiang, Jianping; Sun, Yong
• Is Part Of: Computer methods and programs in biomedicine. Volume 200(2021)
• Publication Date: 2021-03
• Subjects: Left ventricle segmentation -- Cardiac CT angiography -- Deep learning -- Residual U-Net -- Deep supervision; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2020.105876
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We proposed an 8-layer residual U-Net with deep supervision for segmentation of the left ventricle in cardiac CT angiography. Experimental results exhibited that our method had high segmentation accuracy and robustness for different left ventricle shape, size, and image contrast. We used online data augmentation composed of sequential random rotation, scaling, and shear transformation in the training process, which contributes to improve the generalization and robustness of our method. We annotated the data by an interactive semi-supervised algorithm of graph cut, confirmed by cardiologists, which is more convenient and objective than the manual annotation. ABSTRACT: Background and Objectives: Accurate segmentation of left ventricle (LV) is a fundamental step in evaluation of cardiac function. Cardiac CT angiography (CCTA) has become an important clinical diagnostic method for cardio-vascular disease (CVD) due to its non-invasive, short exam time, and low cost. To obtain the segmentation of the LV in CCTA scans, we present a deep learning method based on an 8-layer residual U-Net with deep supervision. Methods: Based on the original 4-layer U-Net, our method deepened the network to eight layers, which increased the fitting capacity of the network, thus greatly improved its LV recognition capability. Residual blocks were incorporated to optimize the network from the increased depth. Auxiliary paths as deep supervision were introduced to supervise the intermediate information to improve the segmentation quality. In this study, we collected CCTA scans of 100 patients. Eighty patients with 1600 discrete slices were used to train the LV segmentation and the remaining 20 patients with 400 discrete slices were used for testing our method. An interactive graph cut algorithm was utilized reliably to annotate the LV reference standard that was further confirmed by cardiologists. Online data augmentation was performed in the training process to improve the generalization and robustness of our method. Results: Compared with the segmentation results from the original U-Net and FC-DenseNet56 with Dice similarity coefficient (DSC) of 0.878±0.230 and 0.897±0.189, respectively, our method demonstrated higher segmentation accuracy and robustness for varying LV shape, size, and contrast, achieving DSC of 0.927±0.139. Without online data augmentation, our method resulted in inferior performance with DSC of 0.911±0.170. In addition, compared with the provided results from other existing studies in the LV segmentation of cardiac CT images, our method achieved a competitive performance for the LV segmentation. Conclusions: The proposed 8-layer residual U-Net with deep supervision accurately and efficiently segments the LV in CCTA scans. This method has potential advantages to be a reliable segmentation method and useful for the evaluation of cardiac function in the future study.