Deep Learning‐Based Acceleration of Compressed Sensing for Noncontrast‐Enhanced Coronary Magnetic Resonance Angiography in Patients With Suspected Coronary Artery Disease

Abstract

BackgroundThe clinical application of coronary MR angiography (MRA) remains limited due to its long acquisition time and often unsatisfactory image quality. A compressed sensing artificial intelligence (CSAI) framework was recently introduced to overcome these limitations, but its feasibility in coronary MRA is unknown.PurposeTo evaluate the diagnostic performance of noncontrast‐enhanced coronary MRA with CSAI in patients with suspected coronary artery disease (CAD).Study TypeProspective observational study.PopulationA total of 64 consecutive patients (mean age ± standard deviation [SD]: 59 ± 10 years, 48.4% females) with suspected CAD.Field Strength/SequenceA 3.0‐T, balanced steady‐state free precession sequence.AssessmentThree observers evaluated the image quality for 15 coronary segments of the right and left coronary arteries using a 5‐point scoring system (1 = not visible; 5 = excellent). Image scores ≥3 were considered diagnostic. Furthermore, the detection of CAD with ≥50% stenosis was evaluated in comparison to reference standard coronary computed tomography angiography (CTA). Mean acquisition times for CSAI‐based coronary MRA were measured.Statistical TestsFor each patient, vessel and segment, sensitivity, specificity, and diagnostic accuracy of CSAI‐based coronary MRA for detecting CAD with ≥50% stenosis according to coronary CTA were calculated. Intraclass correlation coefficients (ICCs) were used to assess the interobserver agreement.ResultsThe mean MR acquisition time ± SD was 8.1 ± 2.4 minutes. Twenty‐five (39.1%) patients had CAD with ≥50% stenosis on coronary CTA and 29 (45.3%) patients on MRA. A total of 885 segments on the CTA images and 818/885 (92.4%) coronary MRA segments were diagnostic (image score ≥3). The sensitivity, specificity, and diagnostic accuracy were as follows: per patient (92.0%, 84.6%, and 87.5%), per vessel (82.9%, 93.4%, and 91.1%), and per segment (77.6%, 98.2%, and 96.6%), respectively. The ICCs for image quality and stenosis assessment were 0.76–0.99 and 0.66–1.00, respectively.Data ConclusionThe image quality and diagnostic performance of coronary MRA with CSAI may show good results in comparison to coronary CTA in patients with suspected CAD.Evidence Level1.Technical Efficacy2.

Editorial for “Deep Learning‐Based Acceleration of Compressed Sensing Noncontrast‐Enhanced Coronary Magnetic Resonance Angiography in Patients With Suspected Coronary Artery Disease”

“…In the study by Sun and colleagues, 6 the authors have utilized a novel convolutional neural network (CNN) called adaptive‐CS‐network, which has been adapted from a network deployed previously in musculoskeletal MRI 7 . This CNN improves standard CS reconstruction by learning optimal reconstruction parameters with the goal of balancing signal‐to‐noise and acquisition time in noncontrast cMRA.…”