Effects of Deep Learning Reconstruction Technique in High-Resolution Non-contrast Magnetic Resonance Coronary Angiography at a 3-Tesla Machine. Issue 1 (February 2021)

• Record Type: Journal Article
• Authors: Yokota, Yasuhiro; Takeda, Chika; Kidoh, Masafumi; Oda, Seitaro; Aoki, Ryo; Ito, Kenichi; Morita, Kosuke; Haraoka, Kentaro; Yamashita, Yuichi; Iizuka, Hitoshi; Kato, Shingo; Tsujita, Kenichi; Ikeda, Osamu; Yamashita, Yasuyuki; Utsunomiya, Daisuke
• Other Names: Chong Jaron guest-editor.
• Is Part Of: Canadian Association of Radiologists journal. Volume 72:Issue 1(2021)
• Page Start: 120
• Page End: 127
• Publication Date: 2021-02
• Subjects: magnetic resonance imaging -- magnetic resonance coronary angiography -- deep learning -- reconstruction; Radiology, Medical -- Periodicals; Radiology, Medical -- Canada -- Periodicals; 616.0757
• DOI: 10.1177/0846537119900469
• Languages: English
• ISSNs: 0846-5371

Abstract

Purpose: To evaluate the effects of deep learning reconstruction (DLR) in qualitative and quantitative image quality of non-contrast magnetic resonance coronary angiography (MRCA). Methods: Ten healthy volunteers underwent conventional MRCA (C-MRCA) and high-resolution (HR) MRCA on a 3T magnetic resonance imaging with a voxel size of 1.8 × 1.1 × 1.7 mm 3 and 1.8 × 0.6 × 1.0 mm 3, respectively, for C-MRCA and HR-MRCA. High-resolution magnetic resonance coronary angiography was also reconstructed with the DLR technique (DLR-HR-MRCA). We compared the contrast-to-noise ratio (CNR) and visual evaluation scores for vessel sharpness and traceability of proximal and distal coronary vessels on a 4-point scale among 3 image series. Results: The vascular CNR value on the C-MRCA and the DLR-HR-MRCA was significantly higher than that on the HR-MRCA in the proximal and distal coronary arteries (13.9 ± 6.4, 11.3 ± 4.4, and 7.8 ± 2.6 for C-MRCA, DLR-HR-MRCA, and HR-MRCA, P < .05, respectively). Mean visual evaluation scores for the vessel sharpness and traceability of proximal and distal coronary vessels were significantly higher on the HR-DLR-MRCA than the C-MRCA ( P < .05, respectively). Conclusion: Deep learning reconstruction significantly improved the CNR of coronary arteries on HR-MRCA, resulting in both higher visual image quality and better vessel traceability compared with C-MRCA.