Cardiac CT motion artifact grading via semi-automatic labeling and vessel tracking using synthetic image-augmented training data

Article type: Research Article

Authors: Xu, Yongshun^a | Sushmit, Asif^b | Lyu, Qing^b | Li, Ying^c | Cao, Ximiao^c | Maltz, Jonathan S.^{c; d; *} | Wang, Ge^{b; *} | Yu, Hengyong^{a; *}

Affiliations: [a] Department of Electrical and Computer Engineering, University of Massachusetts Lowell, Lowell, MA, USA | [b] Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, USA | [c] Molecular Imaging and Computed Tomography, GE Healthcare, 3000 N Grandview Boulevard, Waukesha, WI, USA | [d] Molecular Biophysics and Integrated Bioimaging, Lawrence Berkeley National Laboratory, University of California, Berkeley, CA, USA

Correspondence: [*] Corresponding authors: J.S. Maltz, Molecular Imaging and Computed Tomography, GE Healthcare, 3000 N Grandview Boulevard, Waukesha, WI, 53188, USA. E-mail: jonathan.maltz@ge.com; G. Wang, Department of Biomedical Engineering, Rensselaer Polytechnic Institute, Troy, NY, 12180, USA. E-mail: wangg6@rpi.edu; H.Y. Yu, Department of Electrical and Computer Engineering, University of Massachusetts Lowell, Lowell, MA, 01854, USA. E-mail: hengyong_yu@uml.edu.

Abstract: Cardiac CT provides critical information for the evaluation of cardiovascular diseases. However, involuntary patient motion and physiological movement of the organs during CT scanning cause motion blur in the reconstructed CT images, degrading both cardiac CT image quality and its diagnostic value. In this paper, we propose and demonstrate an effective and efficient method for CT coronary angiography image quality grading via semi-automatic labeling and vessel tracking. These algorithms produce scores that accord with those of expert readers to within 0.85 points on a 5-point scale. We also train a neural network model to perform fully-automatic motion artifact grading. We demonstrate, using XCAT simulation tools to generate realistic phantom CT data, that supplementing clinical data with synthetic data improves the scoring performance of this network. With respect to ground truth scores assigned by expert operators, the mean square error of grading motion of the right coronary artery is reduced by 36% by synthetic data supplementation. This demonstrates that augmentation of clinical training data with realistically synthesized images can potentially reduce the number of clinical studies needed to train the network.

Keywords: Cardiac CT, motion artifacts, semi-automatic labeling, vessel tracking, deep learning

DOI: 10.3233/XST-211109

Journal: Journal of X-Ray Science and Technology, vol. 30, no. 3, pp. 433-445, 2022