Prospective Evaluation of Accelerated Brain MRI Using Deep Learning-Based Reconstruction: Simultaneous Application to 2D Spin-Echo and 3D Gradient-Echo Sequences
Kyu Sung Choi, Chanrim Park, Ji Ye Lee, Kyung Hoon Lee, Young Hun Jeon, Inpyeong Hwang, Roh‐Eul Yoo, Tae Jin Yun, Mi Ji Lee, Keun‐Hwa Jung, Koung Mi Kang
Abstract
Objective: To prospectively evaluate the effect of accelerated deep learning-based reconstruction (Accel-DL) on improving brain magnetic resonance imaging (MRI) quality and reducing scan time compared to that in conventional MRI. Materials and Methods:This study included 150 participants (51 male; mean age 57.3 16.2 years).Each group of 50 participants was scanned using one of three 3T scanners from three different vendors.Conventional and Accel-DL MRI images were obtained from each participant and compared using 2D T1-and T2-weighted and 3D gradient-echo sequences.Accel-DL acquisition was achieved using optimized scan parameters to reduce the scan time, with the acquired images reconstructed using U-Net-based software to transform low-quality, undersampled k-space data into high-quality images.The scan times of Accel-DL and conventional MRI methods were compared.Four neuroradiologists assessed the overall image quality, structural delineation, and artifacts using Likert scale (5-and 3-point scales).Inter-reader agreement was assessed using Fleiss' kappa coefficient.Signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) were calculated, and volumetric quantification of regional structures and white matter hyperintensities (WMHs) was performed.Results: Accel-DL showed a mean scan time reduction of 39.4% (range, 24.2%-51.3%).Accel-DL improved overall image quality (3.78 0.71 vs. 3.36 0.61, P < 0.001), structure delineation (2.47 0.61 vs. 2.35 0.62, P < 0.001), and artifacts (3.73 0.72 vs. 3.71 0.69, P = 0.016).Inter-reader agreement was fair to substantial ( = 0.34-0.50).SNR and CNR increased in P = 0.02; 12.4 4.1 vs. 4.4 11.2, P = 0.02).Bland-Altman plots revealed no significant differences in the volumetric measurements of 98.2% of the relevant regions, except in the deep gray matter, including the thalamus.Five of the six lesion categories showed no significant differences in WMH segmentation, except for leukocortical lesions (r = 0.64 0.29).Conclusion: Accel-DL substantially reduced the scan time and improved the quality of brain MRI in both spin-echo and gradientecho sequences without compromising volumetry, including lesion quantification.