From the Department of Radiology, New York University Grossman School of Medicine, 650 1st Ave, New York, NY 10016 (P.M.J., D.J.L., J.S.B., M.K., G.C., E.A., M.S., W.R.W., L.C., D.K.S., M.P.R., F.K.); Meta AI Research (FAIR), Menlo Park, Calif (J.Z., C.L.Z., A.S.); Meta AI Research, New York, NY (M.M.); Institute of Computer Graphics and Vision, Graz University of Technology, Graz, Austria (T.P.); and Faculty of Engineering, Friedrich Alexander University Erlangen-Nurnberg (FAU), Erlangen, Germany (F.K.).
Radiology. 2023 Apr;307(2):e220425. doi: 10.1148/radiol.220425. Epub 2023 Jan 17.
Background MRI is a powerful diagnostic tool with a long acquisition time. Recently, deep learning (DL) methods have provided accelerated high-quality image reconstructions from undersampled data, but it is unclear if DL image reconstruction can be reliably translated to everyday clinical practice. Purpose To determine the diagnostic equivalence of prospectively accelerated DL-reconstructed knee MRI compared with conventional accelerated MRI for evaluating internal derangement of the knee in a clinical setting. Materials and Methods A DL reconstruction model was trained with images from 298 clinical 3-T knee examinations. In a prospective analysis, patients clinically referred for knee MRI underwent a conventional accelerated knee MRI protocol at 3 T followed by an accelerated DL protocol between January 2020 and February 2021. The equivalence of the DL reconstruction of the images relative to the conventional images for the detection of an abnormality was assessed in terms of interchangeability. Each examination was reviewed by six musculoskeletal radiologists. Analyses pertaining to the detection of meniscal or ligament tears and bone marrow or cartilage abnormalities were based on four-point ordinal scores for the likelihood of an abnormality. Additionally, the protocols were compared with use of four-point ordinal scores for each aspect of image quality: overall image quality, presence of artifacts, sharpness, and signal-to-noise ratio. Results A total of 170 participants (mean age ± SD, 45 years ± 16; 76 men) were evaluated. The DL-reconstructed images were determined to be of diagnostic equivalence with the conventional images for detection of abnormalities. The overall image quality score, averaged over six readers, was significantly better ( < .001) for the DL than for the conventional images. Conclusion In a clinical setting, deep learning reconstruction enabled a nearly twofold reduction in scan time for a knee MRI and was diagnostically equivalent with the conventional protocol. © RSNA, 2023 See also the editorial by Roemer in this issue.
背景 MRI 是一种强大的诊断工具，采集时间较长。最近，深度学习（DL）方法已经能够从欠采样数据中提供加速的高质量图像重建，但尚不清楚 DL 图像重建是否可以可靠地转化为日常临床实践。目的 确定前瞻性加速 DL 重建膝关节 MRI 与常规加速 MRI 在临床环境中评估膝关节内部紊乱的诊断等效性。材料与方法 使用来自 298 例临床 3-T 膝关节检查的图像来训练 DL 重建模型。在一项前瞻性分析中，临床转诊行膝关节 MRI 的患者在 3 T 下接受常规加速膝关节 MRI 方案，然后在 2020 年 1 月至 2021 年 2 月之间接受加速 DL 方案。评估了图像的 DL 重建相对于常规图像在检测异常方面的可互换性。每位检查者由六名肌肉骨骼放射科医生进行评估。基于异常可能性的四点有序评分，对半月板或韧带撕裂以及骨髓或软骨异常的检测进行了分析。此外，还使用四点有序评分比较了两种方案在图像质量的各个方面的表现：整体图像质量、伪影存在、锐度和信噪比。结果 共评估了 170 名参与者（平均年龄±标准差，45 岁±16；76 名男性）。DL 重建图像被确定为与常规图像在检测异常方面具有诊断等效性。在六名读者中，平均的整体图像质量评分明显更高（<.001），DL 图像优于常规图像。结论 在临床环境中，深度学习重建使膝关节 MRI 的扫描时间减少了近两倍，并且与常规方案具有诊断等效性。©RSNA，2023 本期还刊登了 Roemer 的社论。
