Department of Radiology, Peking University Third Hospital, 49 North Garden Road, Haidian District, Beijing, 100191, PR China.
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China.
BMC Med Imaging. 2024 Nov 26;24(1):320. doi: 10.1186/s12880-024-01489-w.
A deep learning (DL) model that can automatically detect and classify cervical canal and neural foraminal stenosis using cervical spine magnetic resonance imaging (MRI) can improve diagnostic accuracy and efficiency.
A method comprising region-of-interest (ROI) detection and cascade prediction was formulated for diagnosing cervical spinal stenosis based on a DL model. First, three part-specific convolutional neural networks were employed to detect the ROIs in different parts of the cervical MR images. Cascade prediction of the stenosis categories was subsequently performed to record the stenosis level and position on each patient slice. Finally, the results were combined to obtain a patient-level diagnostic report. Performance was evaluated based on the accuracy (ACC), area under the curve (AUC), sensitivity, specificity, F1 Score, diagnosis time of the DL model, and recall rate for ROI detection localization.
The average recall rate of the ROI localization was 89.3% (neural foramen) and 99.7% (central canal) under the five-fold cross-validation of the DL model. In the dichotomous classification (normal or mild vs. moderate or severe), the ACC and AUC of the DL model were comparable to those of the radiologists, and the F1 score (84.8%) of the DL model was slightly higher than that of the radiologists (83.8%) for the central canal. Diagnosing whether the central canal or neural foramen of a slice is narrowed in the cervical MRI scan required an average of 15 and 0.098 s for the radiologists and DL model, respectively.
The DL model demonstrated comparable performance with subspecialist radiologists for the detection and classification of central canal and neural foraminal stenosis on cervical spine MRI. Moreover, the DL model demonstrated significant timesaving ability.
一种能够使用颈椎磁共振成像（MRI）自动检测和分类颈椎管和神经孔狭窄的深度学习（DL）模型可以提高诊断准确性和效率。
我们制定了一种基于 DL 模型的诊断颈椎椎管狭窄的方法，包括感兴趣区域（ROI）检测和级联预测。首先，使用三个特定于部位的卷积神经网络来检测颈椎 MR 图像不同部位的 ROI。随后对狭窄类别进行级联预测，以记录每位患者切片上的狭窄程度和位置。最后，将结果合并以获得患者级别的诊断报告。根据 DL 模型的准确性（ACC）、曲线下面积（AUC）、敏感性、特异性、F1 评分、诊断时间和 ROI 检测定位的召回率来评估性能。
在 DL 模型的五重交叉验证下，ROI 定位的平均召回率分别为 89.3%（神经孔）和 99.7%（中央管）。在二分类（正常或轻度与中度或重度）中，DL 模型的 ACC 和 AUC 与放射科医生相当，DL 模型的 F1 评分（84.8%）略高于放射科医生（83.8%）对中央管的评分。诊断颈椎 MRI 扫描中某一切片的中央管或神经孔是否狭窄，放射科医生平均需要 15 秒，DL 模型平均需要 0.098 秒。
DL 模型在检测和分类颈椎 MRI 上的中央管和神经孔狭窄方面与专科放射科医生的表现相当。此外，DL 模型具有显著的节省时间的能力。
