Department of Orthopaedic Surgery, Graduate School of Medicine, Chiba University, Chiba, Japan.
Chiba University Center for Frontier Medical Engineering, Chiba, Japan.
Spine (Phila Pa 1976). 2023 Feb 15;48(4):288-294. doi: 10.1097/BRS.0000000000004532. Epub 2022 Nov 4.
A retrospective analysis of magnetic resonance imaging (MRI).
The study aimed to evaluate the performance of a convolutional neural network (CNN) to differentiate spinal pyogenic spondylitis from Modic change on MRI. We compared the performance of CNN to that of four clinicians.
Discrimination between pyogenic spondylitis and spinal Modic change is crucial in clinical practice. CNN deep-learning approaches for medical imaging are being increasingly utilized.
We retrospectively reviewed MRIs from pyogenic spondylitis and spinal Modic change patients. There were 50 patients per group. Sagittal T1-weighted (T1WI), sagittal T2-weighted (T2WI), and short TI inversion recovery (STIR) MRIs were used for CNN training and validation. The deep learning framework Tensorflow was used to construct the CNN architecture. To evaluate CNN performance, we plotted the receiver operating characteristic curve and calculated the area under the curve. We compared the accuracy, sensitivity, and specificity of CNN diagnosis to that of a radiologist, spine surgeon, and two orthopedic surgeons.
The CNN-based area under the curves of the receiver operating characteristic curve from the T1WI, T2WI, and STIR were 0.95, 0.94, and 0.95, respectively. The accuracy of the CNN was significantly greater than that of the four clinicians on T1WI and STIR (P<0.05), and better than a radiologist and one orthopedic surgeon on the T2WI (P<0.05). The sensitivity was significantly better than that of the four clincians on T1WI and STIR (P<0.05), and better than a radiologist and one orthopedic surgeon on the T2WI (P<0.05). The specificity was significantly better than one orthopedic surgeon on T1WI and T2WI (P<0.05) and better than both orthopedic surgeons on STIR (P<0.05).
We differentiated between Modic changes and pyogenic spondylitis using a CNN that interprets MRI. The performance of the CNN was comparable to, or better than, that of the four clinicians.
回顾性磁共振成像（MRI）分析。
本研究旨在评估卷积神经网络（CNN）在区分脊柱化脓性脊柱炎和 MRI 上的 Modic 改变方面的性能。我们比较了 CNN 的性能与四位临床医生的性能。
区分化脓性脊柱炎和脊柱 Modic 改变在临床实践中至关重要。用于医学成像的 CNN 深度学习方法越来越多地被应用。
我们回顾性地分析了化脓性脊柱炎和脊柱 Modic 改变患者的 MRI。每组各有 50 名患者。矢状 T1 加权（T1WI）、矢状 T2 加权（T2WI）和短 TI 反转恢复（STIR）MRI 用于 CNN 训练和验证。我们使用 Tensorflow 深度学习框架构建 CNN 架构。为了评估 CNN 的性能，我们绘制了接收者操作特征曲线并计算了曲线下面积。我们比较了 CNN 诊断的准确性、敏感性和特异性与放射科医生、脊柱外科医生和两位骨科医生的诊断结果。
基于 CNN 的 T1WI、T2WI 和 STIR 的接收者操作特征曲线下面积分别为 0.95、0.94 和 0.95。在 T1WI 和 STIR 上，CNN 的准确率明显高于四位临床医生（P<0.05），在 T2WI 上优于一位放射科医生和一位骨科医生（P<0.05）。在 T1WI 和 STIR 上，CNN 的灵敏度明显高于四位临床医生（P<0.05），在 T2WI 上优于一位放射科医生和一位骨科医生（P<0.05）。在 T1WI 和 T2WI 上，CNN 的特异性明显优于一位骨科医生（P<0.05），在 STIR 上优于两位骨科医生（P<0.05）。
我们使用解释 MRI 的 CNN 来区分 Modic 变化和化脓性脊柱炎。CNN 的性能与四位临床医生的性能相当或更好。
