Department of Radiology and Imaging, Hospital for Special Surgery, 535 E 70th St, New York, NY, 10021, USA.
GE Healthcare, Waukesha, WI, USA.
Skeletal Radiol. 2023 Apr;52(4):725-732. doi: 10.1007/s00256-022-04211-5. Epub 2022 Oct 21.
To compare standard-of-care two-dimensional MRI acquisitions of the cervical spine with those from a single three-dimensional MRI acquisition, reconstructed using a deep-learning-based reconstruction algorithm. We hypothesized that the improved image quality provided by deep-learning-based reconstruction would result in improved inter-rater agreement for cervical spine foraminal stenosis compared to conventional two-dimensional acquisitions.
Forty-one patients underwent routine cervical spine MRI with a conventional protocol comprising two-dimensional T2-weighted fast spin echo scans (2 axial planes, 1 sagittal plane), and an isotropic-resolution three-dimensional T2-weighted fast spin echo scan reconstructed over a 4-h time window with a deep-learning-based reconstruction algorithm. Three radiologists retrospectively assessed images for the degree to which motion artifact limited clinical assessment, and foraminal and central stenosis at each level. Inter-rater agreement was analyzed with weighted Fleiss's kappa (k) and comparisons between two-dimensional and three-dimensional sequences were performed with Wilcoxon signed-rank test.
Inter-rater agreement for foraminal stenosis was "substantial" for two-dimensional sequences (k = 0.76) and "excellent" for the three-dimensional sequence (k = 0.81). Agreement was "excellent" for both sequences (k = 0.85 and 0.83) for central stenosis. The three-dimensional sequence had less perceptible motion artifact (p ≤ 0.001-0.036). Mean total scan time was 10.8 min for the two-dimensional sequences, and 7.3 min for the three-dimensional sequence.
Three-dimensional MRI reconstructed with a deep-learning-based algorithm provided "excellent" inter-observer agreement for foraminal and central stenosis, which was at least equivalent to standard-of-care two-dimensional imaging. Three-dimensional MRI with deep-learning-based reconstruction was less prone to motion artifact, with overall scan time savings.
比较标准护理二维颈椎 MRI 采集与使用基于深度学习的重建算法进行重建的单个三维 MRI 采集。我们假设，与传统二维采集相比，基于深度学习的重建提供的改进图像质量将导致颈椎椎间孔狭窄的观察者间一致性提高。
41 例患者接受常规颈椎 MRI 检查，常规方案包括二维 T2 加权快速自旋回波扫描（2 个轴位平面，1 个矢状位平面）和各向同性分辨率三维 T2 加权快速自旋回波扫描，在 4 小时的时间窗口内使用基于深度学习的重建算法进行重建。三位放射科医生回顾性评估了运动伪影限制临床评估的程度，以及每个水平的椎间孔和中央狭窄程度。使用加权 Fleiss kappa（k）分析观察者间一致性，并使用 Wilcoxon 符号秩检验比较二维和三维序列。
二维序列的椎间孔狭窄观察者间一致性为“中等”（k=0.76），三维序列的观察者间一致性为“优秀”（k=0.81）。两种序列的中央狭窄观察者间一致性均为“优秀”（k=0.85 和 0.83）。三维序列的运动伪影更不易察觉（p≤0.001-0.036）。二维序列的总扫描时间平均为 10.8 分钟，三维序列的总扫描时间为 7.3 分钟。
使用基于深度学习的算法重建的三维 MRI 为椎间孔和中央狭窄提供了“优秀”的观察者间一致性，至少与标准护理二维成像相当。基于深度学习的三维 MRI 运动伪影较少，总扫描时间节省。
