Use of residual neural network for the detection of ossification of the posterior longitudinal ligament on plain cervical radiography
Use of residual neural network for the detection of ossification of the posterior longitudinal ligament on plain cervical radiography
复制标题
DOI：
10.1007/s00586-021-06914-0
复制
发表时间：
2021-07-01
影响因子：
2.8
通讯作者：
Yamamoto, Kengo
中科院分区：
文献类型：
--
作者：
Murata, Kazuma;Endo, Kenji;Yamamoto, Kengo
后纵韧带骨化(OPLL)会导致严重的问题，如脊髓病和急性脊髓损伤。因此，早期、准确地诊断OPLL可避免预后不良。平片是评价OPLL的基本方法。因此，最大限度地减少OPLL在X线片上的诊断误差至关重要。基于残差神经网络(RNN)的图像识别已被认为是一种潜在有效的骨科疾病诊断策略；然而，使用RNN检测OPLL的准确性仍不清楚。用672例患者(304例OPLL患者和368例阴性患者1,773例图像)的颈椎侧位X线片图像训练RNN。计算RNN诊断的准确性、敏感性、特异性、假阳性率和假阴性率。模型的平均准确率为98.9%，灵敏度为97.0%，特异度为99.4%，假阳性率为2.2%，假阴性率为1.0%。该模型的曲线下面积为0.99(95%可信区间，0.97-1.00)，其中每一折叠的AUC估计分别为0.99、0.99、0.98、0.98和0.99。由神经网络训练的算法可以在颈椎侧位X线片上对OPLL进行二值分类。因此，RNN可能是一种有用的筛查工具，以帮助医生在未来的环境中识别OPLL患者。为了实现临床上对OPLL患者的准确识别，RNN必须与其他原因的脊髓病一起训练。
Ossification of the posterior longitudinal ligament (OPLL) causes serious problems, such as myelopathy and acute spinal cord injury. The early and accurate diagnosis of OPLL would hence prevent the miserable prognoses. Plain lateral radiography is an essential method for the evaluation of OPLL. Therefore, minimizing the diagnostic errors of OPLL on radiography is crucial. Image identification based on a residual neural network (RNN) has been recognized to be potentially effective as a diagnostic strategy for orthopedic diseases; however, the accuracy of detecting OPLL using RNN has remained unclear. An RNN was trained with plain lateral cervical radiography images of 2,318 images from 672 patients (535 images from 304 patients with OPLL and 1,773 images from 368 patients of Negative). The accuracy, sensitivity, specificity, false positive rate, and false negative rate of diagnosis of the RNN were calculated. The mean accuracy, sensitivity, specificity, false positive rate, and false negative rate of the model were 98.9%, 97.0%, 99.4%, 2.2%, and 1.0%, respectively. The model achieved an overall area under the curve of 0.99 (95% confidence interval, 0.97-1.00) in which AUC in each fold estimated was 0.99, 0.99, 0.98, 0.98, and 0.99, respectively. An algorithm trained by an RNN could make binary classification of OPLL on cervical lateral X-ray images. RNN may hence be useful as a screening tool to assist physicians in identifying patients with OPLL in future setting. To achieve accurate identification of OPLL patients clinically, RNN has to be trained with other cause of myelopathy.