Breath-hold 3D magnetic resonance cholangiopancreatography at 1.5 T using a deep learning-based noise-reduction approach: Comparison with the conventional respiratory-triggered technique. Issue 144 (November 2021)

• Record Type: Journal Article
• Authors: Tajima, Taku; Akai, Hiroyuki; Sugawara, Haruto; Yasaka, Koichiro; Kunimatsu, Akira; Yoshioka, Naoki; Akahane, Masaaki; Ohtomo, Kuni; Abe, Osamu; Kiryu, Shigeru
• Is Part Of: European journal of radiology. Issue 144(2021)
• Publication Date: 2021-11
• Subjects: Artificial intelligence -- Deep learning -- Magnetic resonance cholangiopancreatography -- Fast MR imaging; BH breath-hold -- CNR contrast-to-noise ratio -- dDLR denoising procedure with deep learning-based reconstruction -- DLR deep learning-based reconstruction -- MRCP magnetic resonance cholangiopancreatography -- MRI magnetic resonance imaging -- Resp respiratory-triggered -- ROI region of interest -- SNR signal-to-noise ratio; Medical radiology -- Periodicals; Radiology -- Periodicals; Radiologie médicale -- Périodiques; Medical radiology; Periodicals; 616.075705
• DOI: 10.1016/j.ejrad.2021.109994
• Languages: English
• ISSNs: 0720-048X

Abstract

Highlights: Denoising procedure with deep learning-based reconstruction (dDLR) is a novel method. The image quality of breath-hold MRCP (BH-MRCP) at 1.5 T was improved by dDLR. The image quality of denoised BH-MRCP was equivalent or even superior to Resp-MRCP. Abstract: Objectives: To assess the image quality of conventional respiratory-triggered 3-dimentional (3D) magnetic resonance cholangiopancreatography (Resp-MRCP) and breath-hold 3D MRCP (BH-MRCP) with and without denoising procedure using deep learning-based reconstruction (dDLR) at 1.5 T. Methods: Forty-two patients underwent MRCP at 1.5 T MRI. The following imaging sequences were performed: Resp-MRCP and BH-MRCP. We applied the dDLR method to the BH-MRCP data (BH-dDLR-MRCP). As a qualitative analysis, two radiologists rated the visibility of the proximal common bile duct (CBD), pancreaticobiliary junction, distal main pancreatic duct, cystic duct, and right and left hepatic ducts. Artifacts and overall image quality were also rated. The signal-to-noise ratios (SNRs), contrast ratios, and contrast-to-noise ratios (CNRs) of the CBD images were calculated for quantitative analysis. Results: BH-MRCP was successfully performed in a single BH. The qualitative and quantitative measurements for BH-dDLR-MRCP were significantly higher than for BH-MRCP ( P < 0.02 and P < 0.001, respectively), and the qualitative measurements for BH-dDLR-MRCP were equivalent to or higher than for Resp-MRCP ( P = 0.048–1.000). The SNRs and CNRs for BH-dDLR-MRCP were significantly higher than for Resp-MRCP ( P < 0.001 and P = 0.001, respectively). Conclusion: dDLR is useful and clinically feasible for BH-MRCP at 1.5 T MRI, and enables rapid imaging without loss of image quality compared to conventional Resp-MRCP.