Automated detection of cardiac rest period for trigger delay calculation for image-based navigator coronary magnetic resonance angiography

Abstract

Background: Coronary magnetic resonance angiography (coronary MRA) is increasingly being considered as a clinically viable method to investigate coronary artery disease (CAD). Accurate determination of the trigger delay to place the acquisition window within the quiescent part of the cardiac cycle is critical for coronary MRA in order to reduce cardiac motion. This is currently reliant on operator-led decision making, which can negatively affect consistency of scan acquisition. Recently developed deep learning (DL) derived software may overcome these issues by automation of cardiac rest period detection.

Methods: Thirty individuals (female, n = 10) were investigated using a 0.9 mm isotropic image-navigator (iNAV)-based motion-corrected coronary MRA sequence. Each individual was scanned three times utilising different strategies for determination of the optimal trigger delay: (1) the DL software, (2) an experienced operator decision, and (3) a previously utilised formula for determining the trigger delay. Methodologies were compared using custom-made analysis software to assess visible coronary vessel length and coronary vessel sharpness for the entire vessel length and the first 4 cm of each vessel.

Results: There was no difference in image quality between any of the methodologies for determination of the optimal trigger delay, as assessed by visible coronary vessel length, coronary vessel sharpness for each entire vessel and vessel sharpness for the first 4 cm of the left mainstem, left anterior descending or right coronary arteries. However, vessel length of the left circumflex was slightly greater using the formula method. The time taken to calculate the trigger delay was significantly lower for the DL-method as compared to the operator-led approach (106 ± 38.0 s vs 168 ± 39.2 s, p < 0.01, 95% CI of difference 25.5-98.1 s).

Conclusions: Deep learning-derived automated software can effectively and efficiently determine the optimal trigger delay for acquisition of coronary MRA and thus may simplify workflow and improve reproducibility.

Keywords: Cardiac magnetic resonance angiography; Cardiac rest period; Deep learning.

Fig. 1

Showing the process of scan planning and the degree of automation. Following acquisition and automated analysis of a free-breathing 4-chamber scan the DL-based software identifies both the end-systolic (A) and mid-diastolic rest (B) periods, which can be used to determine the acquisition window. The DL based software also determines the position of the coronal 3D imaging slab (in yellow) and iNAV box (in blue) to be used in the coronary MRA acquisition. The placement of the shim box and 3D imaging plane does on occasion require slight manual adjustment, especially in cases where the heart is larger than average

Fig. 2

Showing reformatting of the left anterior descending artery (yellow arrow) and the right coronary artery (blue arrow) for the formula method (A), operator-led method (B) and the deep-learning method (C)