Department of Orthopaedic Surgery, Osaka City University Graduate School of Medicine, 1-4-3 Asahi-machi, Abeno-ku, Osaka 545-8585, Japan.
Department of Orthopaedic Surgery, Osaka City University Graduate School of Medicine, 1-4-3 Asahi-machi, Abeno-ku, Osaka 545-8585, Japan.
Spine J. 2021 Oct;21(10):1652-1658. doi: 10.1016/j.spinee.2021.03.006. Epub 2021 Mar 13.
Accurate diagnosis of osteoporotic vertebral fracture (OVF) is important for improving treatment outcomes; however, the gold standard has not been established yet. A deep-learning approach based on convolutional neural network (CNN) has attracted attention in the medical imaging field.
To construct a CNN to detect fresh OVF on magnetic resonance (MR) images.
STUDY DESIGN/SETTING: Retrospective analysis of MR images PATIENT SAMPLE: This retrospective study included 814 patients with fresh OVF. For CNN training and validation, 1624 slices of T1-weighted MR image were obtained and used.
We plotted the receiver operating characteristic (ROC) curve and calculated the area under the curve (AUC) in order to evaluate the performance of the CNN. Consequently, the sensitivity, specificity, and accuracy of the diagnosis by CNN and that of the two spine surgeons were compared.
We constructed an optimal model using ensemble method by combining nine types of CNNs to detect fresh OVFs. Furthermore, two spine surgeons independently evaluated 100 vertebrae, which were randomly extracted from test data.
The ensemble method using VGG16, VGG19, DenseNet201, and ResNet50 was the combination with the highest AUC of ROC curves. The AUC was 0.949. The evaluation metrics of the diagnosis (CNN/surgeon 1/surgeon 2) for 100 vertebrae were as follows: sensitivity: 88.1%/88.1%/100%; specificity: 87.9%/86.2%/65.5%; accuracy: 88.0%/87.0%/80.0%.
In detecting fresh OVF using MR images, the performance of the CNN was comparable to that of two spine surgeons.
准确诊断骨质疏松性椎体骨折（OVF）对于改善治疗效果至关重要，但尚未确立金标准。基于卷积神经网络（CNN）的深度学习方法在医学成像领域引起了关注。
构建用于检测磁共振（MR）图像中新发 OVF 的 CNN。
研究设计/设置：回顾性 MR 图像分析
本回顾性研究纳入了 814 例新发 OVF 患者。为了进行 CNN 训练和验证，共获得了 1624 张 T1 加权 MR 图像。
我们绘制了接收器工作特征（ROC）曲线，并计算了曲线下面积（AUC），以评估 CNN 的性能。然后，比较了 CNN 诊断的敏感性、特异性和准确性，以及两位脊柱外科医生的诊断准确性。
我们使用集成方法构建了一个最佳模型，该方法结合了 9 种 CNN 来检测新发 OVF。此外，两位脊柱外科医生独立评估了从测试数据中随机抽取的 100 个椎体。
使用 VGG16、VGG19、DenseNet201 和 ResNet50 的集成方法具有最高的 ROC 曲线 AUC。AUC 为 0.949。100 个椎体的诊断评估指标（CNN/外科医生 1/外科医生 2）如下：敏感性：88.1%/88.1%/100%；特异性：87.9%/86.2%/65.5%；准确性：88.0%/87.0%/80.0%。
在使用 MR 图像检测新发 OVF 时，CNN 的性能与两位脊柱外科医生相当。
