使用深度学习系统基于X线片对中央型腰椎管狭窄症患者进行诊断分诊
该研究开发了基于卷积神经网络(CNN)的深度学习模型,利用X线片诊断严重中央型腰椎管狭窄症(LSS)。VGG19模型在训练12,442张图像后AUROC达90.0%(95%CI 89.8%-90.3%),5折模型平均准确率82.8%(95%CI 82.5%-83.1%);外部验证AUROC为89.3%(95%CI 88.7%-90.0%),5折模型平均准确率81.8%(95%CI 80.6%-83.0%)。作者认为该算法可作为分诊工具,并能准确定位狭窄病变。
要点
- 基于X线片的CNN模型诊断严重中央型LSS的AUROC为90.0%(95%CI 89.8%-90.3%)。
- 5折模型平均准确率82.8%(95%CI 82.5%-83.1%),外部验证AUROC为89.3%(95%CI 88.7%-90.0%)。
- Grad-CAM特征点合理,可归类为椎间盘高度降低、椎间孔狭窄、椎弓根短小及小关节高密度。
核心结论
- 基于CNN的X线片算法诊断中央型LSS具有高准确率,有望作为分诊工具,并能准确定位狭窄病变以辅助医生识别LSS。
研究设计与样本
- 回顾性纳入2005年5月1日至2017年12月31日期间同时接受脊柱MRI和X线检查的患者,根据正式MRI报告连续纳入严重中央型LSS组或健康对照组,收集两组X线片。
- 开发基于CNN的迁移学习算法对X线表现进行LSS或正常的二分类,使用受试者工作特征曲线下面积(AUROC)、准确率、敏感度、特异度及阳性和阴性预测值六项指标评估模型。
主要发现
- VGG19模型训练12,442张图像后AUROC最高达90.0%(95%CI 89.8%-90.3%),5折模型平均准确率为82.8%(95%CI 82.5%-83.1%)。
- 外部验证AUROC为89.3%(95%CI 88.7%-90.0%),5折模型平均准确率为81.8%(95%CI 80.6%-83.0%)。
- Grad-CAM特征点合理,特征可归类为椎间盘高度降低、椎间孔狭窄、椎弓根短小及小关节高密度。
- 多因素logistic回归分析显示,年龄和性别等人口学因素的组合未改善模型性能。
关键数值与推荐
- VGG19模型AUROC 90.0%(95%CI 89.8%-90.3%),5折模型平均准确率82.8%(95%CI 82.5%-83.1%)。
- 外部验证AUROC 89.3%(95%CI 88.7%-90.0%),5折模型平均准确率81.8%(95%CI 80.6%-83.0%)。
临床怎么用
- 作者认为该算法有望作为分诊工具,并可准确定位狭窄病变以辅助医生识别LSS。
局限性
- 原文未报告局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVE: Magnetic resonance imaging (MRI) is the gold-standard tool for diagnosing lumbar spinal stenosis (LSS), but it is difficult to promptly examine all suspected cases with MRI considering the modality's high cost and limited accessibility. Although radiography is an efficient screening technique owing to its low cost, rapid operability, and wide availability, its diagnostic accuracy is relatively poor. In this study, the authors aimed to develop a deep learning model with a convolutional neural network (CNN) for diagnosing severe central LSS using radiography and to evaluate radiological diagnostic features using gradient-weighted class activation mapping (Grad-CAM). METHODS: Patients who had undergone both spinal MRI and radiography in the period from May 1, 2005, to December 31, 2017, were screened. According to the formal MRI report, participants were consecutively included in the severe central LSS or healthy control group, and radiographs for both groups were collected. A CNN-based transfer learning algorithm was developed to classify radiographic findings as LSS or normal (binary classification). The proposed models were evaluated using six performance metrics: area under the receiver operating characteristic curve (AUROC), accuracy, sensitivity, specificity, and positive and negative predictive values. RESULTS: The VGG19 model achieved the highest accuracy with an AUROC of 90.0% (95% CI 89.8%-90.3%) by training 12,442 images. Accuracy was 82.8% (95% CI 82.5%-83.1%) by averaging 5-fold models. Feature points on Grad-CAM were reasonable, and the features could be categorized into reduced disc height, narrow foramina, short pedicle, and hyperdense facet joint. The AUROC in the extra validation was 89.3% (95% CI 88.7%-90.0%). Accuracy was 81.8% (95% CI 80.6%-83.0%) by averaging 5-fold models. Multivariate logistic regression analysis showed that a combination of demographic factors (age and sex) did not improve the model performance. CONCLUSIONS: The algorithm trained by a CNN to identify central LSS on radiographs showed high diagnostic accuracy and is expected to be useful as a triage tool. The algorithm could accurately localize the stenotic lesion to assist physicians in the identification of LSS.
引用
- Kim T, Kim YG, Park S, et al. Diagnostic triage in patients with central lumbar spinal stenosis using a deep learning system of radiographs. J Neurosurg Spine. 2022. PMID: 35061993. doi:10.3171/2021.11.SPINE211136
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。