Koch KM, Sherafati M, Arpinar VE, Bhave S, Ausman R, Nencka AS, Lebel RM, McKinnon G, Kaushik SS, Vierck D, Stetz MR, Fernando S, and Mannem R
Purpose: To evaluate two settings (noise reduction of 50% or 75%) of a deep learning (DL) reconstruction model relative to each other and to conventional MR image reconstructions on clinical orthopedic MRI datasets., Materials and Methods: This retrospective study included 54 patients who underwent two-dimensional fast spin-echo MRI for hip ( n = 22; mean age, 44 years ± 13 [standard deviation]; nine men) or shoulder ( n = 32; mean age, 56 years ± 17; 17 men) conditions between March 2019 and June 2020. MR images were reconstructed with conventional methods and the vendor-provided and commercially available DL model applied with 50% and 75% noise reduction settings (DL 50 and DL 75, respectively). Quantitative analytics, including relative anatomic edge sharpness, relative signal-to-noise ratio (rSNR), and relative contrast-to-noise ratio (rCNR) were computed for each dataset. In addition, the image sets were randomized, blinded, and presented to three board-certified musculoskeletal radiologists for ranking based on overall image quality and diagnostic confidence. Statistical analysis was performed with a nonparametric hypothesis comparing derived quantitative metrics from each reconstruction approach. In addition, inter- and intrarater agreement analysis was performed on the radiologists' rankings., Results: Both denoising settings of the DL reconstruction showed improved edge sharpness, rSNR, and rCNR relative to the conventional reconstructions. The reader rankings demonstrated strong agreement, with both DL reconstructions outperforming the conventional approach (Gwet agreement coefficient = 0.98). However, there was lower agreement between the readers on which DL reconstruction denoising setting produced higher-quality images (Gwet agreement coefficient = 0.31 for DL 50 and 0.35 for DL 75)., Conclusion: The vendor-provided DL MRI reconstruction showed higher edge sharpness, rSNR, and rCNR in comparison with conventional methods; however, optimal levels of denoising may need to be further assessed. Keywords: MRI Reconstruction Method, Deep Learning, Image Analysis, Signal-to-Noise Ratio, MR-Imaging, Neural Networks, Hip, Shoulder, Physics, Observer Performance, Technology Assessment Supplemental material is available for this article. © RSNA, 2021., Competing Interests: Disclosures of Conflicts of Interest: K.M.K. institution received a grant from GE Healthcare. M.S. disclosed no relevant relationships. V.E.A. disclosed no relevant relationships. S.B. disclosed no relevant relationships. R.A. disclosed no relevant relationships. A.S.N. institution received funding from GE Healthcare for work in neuroimaging MRI technology development and dissemination; is an inventor on patents including MRI technology focusing on multispectral imaging and magnetic field measurement and modulation; is a scientific advisor for and holds stock in Vasognosis, a start-up company focused on neurovascular imaging applications. R.M.L. is employed by and holds stock options in GE Healthcare; GE Healthcare has patents pending on the algorithms used in this work, but no money has been received. G.M. is employed by GE Healthcare; has been issued U.S. patent no. US10635943B1. S.S.K. is employed by GE Healthcare; received royalties from the Medical College of Wisconsin for a licensed patent unrelated to this work that was filed in 2015. D.V. disclosed no relevant relationships. M.R.S. disclosed no relevant relationships. S.F. disclosed no relevant relationships. R.M. disclosed no relevant relationships., (2021 by the Radiological Society of North America, Inc.)