February 12, 2024 — Free-breathing cine deep learning (DL) can reliably estimate left ventricular ejection fraction ( LVEF) measurements. -Owned.
“The free-breathing cine-DL sequence was shown to have significantly lower bias in LVEF measurements and superior subjective quality compared to the standard breath-hold cine sequence,” said Amiens, France. writes David Monteuuis, M.D., of University Hospital’s Department of Radiology. “Cine-DL resulted in a larger left ventricular volume.”
David et al.’s AJR-approved manuscript included patients undergoing 1.5T or 3T cardiac MRI for evaluation of IHD (March 15-June 21, 2023). Examination included a study free-breathing cine short-axis sequence (cine-DL) with DL reconstruction. Two radiologists (R1, R2) blindedly evaluated LVEF, left ventricular end-diastolic volume (LVEDV), left ventricular end-systolic volume (LVESV), and subjective image quality for cine DL sequences and standard breath-holds. was independently evaluated. Balanced SSFP sequence. R1 evaluated artifacts.
Finally, in IHD patients, free-breathing cine sequences with DL reconstruction had significantly lower bias in LVEF measurements (R1: 0.4%, R2: 0.7%) and improved subjective image quality (R1: 2.3±0.5 vs. 1.9±0.8, R2). : 2.2±0.4 vs. 1.9±0.7), shorter acquisition time (0.6±0.1 vs. 2.4±0.6 min).
“This free-breathing cine DL sequence may be particularly useful in the evaluation of dyspneic patients who are unable to perform repeated breath holds,” the AJR authors added.
For more information, please visit www.arrs.or.
