Deep learning model for the automated detection and classification of central canal and neural foraminal stenosis upon cervical spine magnetic resonance imaging

doi:10.1186/s12880-024-01489-w

	Deep learning model for the automated detection and classification of central canal and neural foraminal stenosis upon cervical spine magnetic resonance imaging
	Zhang, Enlong 1; Yao, Meiyi 2; Li, Yuan 1; Wang, Qizheng 1; Song, Xinhang 2; Chen, Yongye 1; Liu, Ke 1; Zhao, Weili 1; Xing, Xiaoying 1; Zhou, Yan 1; Meng, Fanyu 2; Ouyang, Hanqiang 3; Chen, Gongwei 2; Jiang, Liang 3; Lang, Ning 1; Jiang, Shuqiang 2; Yuan, Huishu 1
	2024-11-26
发表期刊	BMC MEDICAL IMAGING
ISSN	1471-2342
卷号	24 期号:1 页码:9
摘要	BackgroundA 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.MethodsA 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.ResultsThe 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.ConclusionsThe 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.
关键词	Deep learning MRI Cervical spinal stenosis Convolutional neural network
DOI	10.1186/s12880-024-01489-w
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation[Z190020] ; National Natural Science Foundation of China[82371921] ; National Natural Science Foundation of China[81971578] ; National Natural Science Foundation of China[62032022] ; National Natural Science Foundation of China[61902378] ; National Natural Science Foundation of China[81871326] ; National Natural Science Foundation of China[81901791] ; National Natural Science Foundation of China[82102638] ; Clinical Medicine Plus X-Young Scholars Project, Peking University, the Fundamental Research Funds for the Central Universities[PKU2021LCXQ005] ; Peking University Third Hospital Clinical Key Project[BYSYZD2021040]
WOS研究方向	Radiology, Nuclear Medicine & Medical Imaging
WOS类目	Radiology, Nuclear Medicine & Medical Imaging
WOS记录号	WOS:001363416700001
出版者	BMC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/41175
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Lang, Ning; Jiang, Shuqiang; Yuan, Huishu
作者单位	1.Peking Univ Third Hosp, Dept Radiol, 49 North Garden Rd, Beijing 100191, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, Beijing, Peoples R China 3.Peking Univ Third Hosp, Engn Res Ctr Bone & Joint Precis Med, Beijing Key Lab Spinal Dis Res, Dept Orthoped, 49 North Garden Rd, Beijing 100191, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Enlong,Yao, Meiyi,Li, Yuan,et al. Deep learning model for the automated detection and classification of central canal and neural foraminal stenosis upon cervical spine magnetic resonance imaging[J]. BMC MEDICAL IMAGING,2024,24(1):9.
APA	Zhang, Enlong.,Yao, Meiyi.,Li, Yuan.,Wang, Qizheng.,Song, Xinhang.,...&Yuan, Huishu.(2024).Deep learning model for the automated detection and classification of central canal and neural foraminal stenosis upon cervical spine magnetic resonance imaging.BMC MEDICAL IMAGING,24(1),9.
MLA	Zhang, Enlong,et al."Deep learning model for the automated detection and classification of central canal and neural foraminal stenosis upon cervical spine magnetic resonance imaging".BMC MEDICAL IMAGING 24.1(2024):9.