Key result
The automated framework predicted right coronary artery resting phases with 92.7% accuracy, 90.5% sensitivity, and 95.0% specificity compared to expert annotations.
Why the study?
Static cardiac imaging requires prior information on the cardiac resting phase, prompting the development of a fully automated framework to detect right coronary artery resting phase in CINE series.
Does an automated resting phase detection framework accurately identify the right coronary artery resting phase compared to expert manual annotation in patients undergoing cardiac MRI?
Does an automated resting phase detection framework accurately identify the right coronary artery resting phase compared to expert manual annotation in patients undergoing cardiac MRI?
A fully automated deep learning and image registration framework can accurately and robustly detect the right coronary artery resting phase in cardiac MRI, facilitating static imaging acquisitions.
Answers are grounded in this paper and cite their sources.
May facilitate automated static cardiac MRI; leaves open prospective validation before clinical use.
Static cardiac imaging such as late gadolinium enhancement, mapping, or 3-D coronary angiography require prior information, e.g., the phase during a cardiac cycle with least motion, called resting phase (RP). The purpose of this work is to propose a fully automated framework that allows the detection of the right coronary artery (RCA) RP within CINE series. The proposed prototype system consists of three main steps. First, the localization of the regions of interest (ROI) is performed. Second, the cropped ROI series are taken for tracking motions over all time points. Third, the output motion values are used to classify RPs. In this work, we focused on the detection of the area with the outer edge of the cross-section of the RCA as our target. The proposed framework was evaluated on 102 clinically acquired dataset at 1.5T and 3T. The automatically classified RPs were compared with the reference RPs annotated manually by a expert for testing the robustness and feasibility of the framework. The predicted RCA RPs showed high agreement with the experts annotated RPs with 92.7% accuracy, 90.5% sensitivity and 95.0% specificity for the unseen study dataset. The mean absolute difference of the start and end RP was 13.6 ± 18.6 ms for the validation study dataset (n=102). In this work, automated RP detection has been introduced by the proposed framework and demonstrated feasibility, robustness, and applicability for static imaging acquisitions.
No takes yet. Share an insight, caveat, or question.
Yoon et al. (2023) studied Coronary assessment (n=102). Automated Cardiac Resting Phase Detection framework vs. Manual expert annotation was evaluated on Accuracy of predicted right coronary artery resting phases compared to expert annotations. The automated framework predicted right coronary artery resting phases with 92.7% accuracy, 90.5% sensitivity, and 95.0% specificity compared to expert annotations.
Synapse has enriched 10 related papers. Consider them for comparative context: