Automated coronary artery calcium scoring using nested U-Net and focal loss

Jia-Sheng Hong; Yun-Hsuan Tzeng; Wei-Hsian Yin; Kuan-Ting Wu; Huan-Yu Hsu; Chia-Feng Lu; Ho-Ren Liu; Yu-Te Wu

doi:10.1016/j.csbj.2022.03.025

Automated coronary artery calcium scoring using nested U-Net and focal loss

Comput Struct Biotechnol J. 2022 Mar 26:20:1681-1690. doi: 10.1016/j.csbj.2022.03.025. eCollection 2022.

Authors

Jia-Sheng Hong^{1

2}, Yun-Hsuan Tzeng^{3

4}, Wei-Hsian Yin^{4

5}, Kuan-Ting Wu^{1

3}, Huan-Yu Hsu^{3

3}, Chia-Feng Lu², Ho-Ren Liu⁴, Yu-Te Wu^{1

6}

Affiliations

¹ Institute of Biophotonics, National Yang Ming Chiao Tung University, Taipei 112, Taiwan.
² Department of Biomedical Imaging and Radiological Sciences, National Yang Ming Chiao Tung University, Taipei 112, Taiwan.
³ School of Medicine, National Yang Ming Chiao Tung University, Taipei 112, Taiwan.
⁴ Division of Advanced Medical Imaging, Health Management Center, Cheng Hsin General Hospital, Taipei 112, Taiwan.
⁵ Heart Center, Cheng Hsin General Hospital, Taipei 112, Taiwan.
⁶ Brain Research Center, National Yang Ming Chiao Tung University, Taipei 112, Taiwan.

Abstract

Coronary artery calcium (CAC) is a great risk predictor of the atherosclerotic cardiovascular disease and CAC scores can be used to stratify the risk of heart disease. Current clinical analysis of CAC is performed using onsite semiautomated software. This semiautomated CAC analysis requires experienced radiologists and radiologic technologists and is both demanding and time-consuming. The purpose of this study is to develop a fully automated CAC detection model that can quantify CAC scores. A total of 1,811 cases of cardiac examinations involving contrast-free multidetector computed tomography were retrospectively collected. We divided the database into the Training Data Set, Validation Data Set, Testing Data Set 1, and Testing Data Set 2. The Training, Validation, and Testing Data Set 1 contained cases with clinically detected CAC; Testing Data Set 2 contained those without detected calcium. The intraclass correlation coefficients between the overall standard and model-predicted scores were 1.00 for both the Training Data Set and Testing Data Set 1. In Testing Data Set 2, the model was able to detect clinically undetected cases of mild calcium. The results suggested that the proposed model's automated detection of CAC was highly consistent with clinical semiautomated CAC analysis. The proposed model demonstrated potential for clinical applications that can improve the quality of CAC risk stratification.

Keywords: Automated coronary artery calcium detection; Coronary artery calcium scoring; Focal loss; Multidetector computed tomography; U-Net++.