Deep Learning-Based Cardiac CT Coronary Motion Correction Method with Temporal Weight Adjustment: Clinical Data Evaluation.
Authors
Affiliations (4)
Affiliations (4)
- Department of Research Institute, Beijing Wandong Medical Technology Ltd., Beijing, 100016, China.
- Department of Radiology, The Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an, 710004, China.
- Department of Research Institute, Beijing Wandong Medical Technology Ltd., Beijing, 100016, China. [email protected].
- Department of Research Institute, Beijing Wandong Medical Technology Ltd., Beijing, 100016, China. [email protected].
Abstract
Cardiac motion artifacts frequently degrade the quality and interpretability of coronary computed tomography angiography (CCTA) images, making it difficult for radiologists to identify and evaluate the details of the coronary vessels accurately. In this paper, a deep learning-based approach for coronary artery motion compensation, namely a temporal-weighted motion correction network (TW-MoCoNet), was proposed. Firstly, the motion data required for TW-MoCoNet training were generated using a motion artifact simulation method based on the original no-artifact CCTA images. Secondly, TW-MoCoNet, consisting of a temporal weighting correction module and a differentiable spatial transformer module, was trained using these generated paired images. Finally, the proposed method was evaluated on 67 clinical data with objective metrics including peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), fold-overlap ratio (FOR), low-intensity region score (LIRS), and motion artifact score (MAS). Additionally, subjective image quality was evaluated using a 4-point Likert scale to assess visual improvements. The experimental results demonstrated a substantial improvement in both the objective and subjective evaluations of image quality after motion correction was applied. The proportion of the segments with moderate artifacts, scored 2 points, has a notable decrease of 80.2% (from 26.37 to 5.22%), and the proportion of artifact-free segments (scored 4 points) has reached 50.0%, which is of great clinical significance. In conclusion, the deep learning-based motion correction method proposed in this paper can effectively reduce motion artifacts, enhance image clarity, and improve clinical interpretability, thus effectively assisting doctors in accurately identifying and evaluating the details of coronary vessels.