Deep Learning Model for Automated Detection and Classification of Central Canal, Lateral Recess, and Neural Foraminal Stenosis at Lumbar Spine MRI
Deep Learning Model for Automated Detection and Classification of Central Canal, Lateral Recess, and Neural Foraminal Stenosis at Lumbar Spine MRI
复制标题
DOI：
10.1148/radiol.2021204289
复制
发表时间：
2021-07-01
期刊：
影响因子：
19.7
通讯作者：
Quek, Swee Tian
中科院分区：
文献类型：
--
作者：
Hallinan, James Thomas Patrick Decourcy;Zhu, Lei;Quek, Swee Tian
背景：腰椎管狭窄的MRI评估是重复且耗时的。深度学习（DL）可以提高生产率和报告的一致性。目的：建立用于腰椎中央管、外侧隐窝和椎间孔狭窄自动检测和分类的DL模型。材料和方法：在这项回顾性研究中，纳入了2015年9月至2018年9月腰椎MRI扫描。排除了脊柱内固定患者的研究或图像质量欠佳的研究，以及钆后研究和脊柱侧凸患者的研究。采用轴向t2加权和矢状t1加权图像。研究分为内部训练集（80%）、验证集（9%）和测试集（11%）。训练数据由四名放射科医生使用预定义的等级（正常、轻度、中度和严重）进行标记。建立了双组分深度学习模型。首先，训练卷积神经网络（CNN）检测感兴趣区域（ROI），再训练卷积神经网络进行分类。内部测试集由具有31年经验的肌肉骨骼放射科医生（参考标准）和两个专科放射科医生（放射科医生1:a.m.， 5年经验；放射科医生2:j.t.p.d.h.， 9年经验）标记。在外部测试集上评估DL模型的性能。计算了检测召回率（以百分比计）、间一致性（Gwet）、灵敏度和特异性。结果：总体上，446例腰椎MRI研究被分析（446例患者；平均年龄+/-标准差，52岁+/- 19岁；240名女性），其中396例患者在训练组（80%）和验证组（9%），50例患者在内部测试组（11%）。对于内部测试，DL模型和放射科医生的中央管回忆率大于99%，与放射科医生2（97.1%）相比，DL模型和放射科医生1（83.9%）的神经孔回忆率降低（84.5%）
Background: Assessment of lumbar spinal stenosis at MRI is repetitive and time consuming. Deep learning (DL) could improve -productivity and the consistency of reporting.Purpose: To develop a DL model for automated detection and classification of lumbar central canal, lateral recess, and neural -foraminal stenosis.Materials and Methods: In this retrospective study, lumbar spine MRI scans obtained from September 2015 to September 2018 were included. Studies of patients with spinal instrumentation or studies with suboptimal image quality, as well as postgadolinium studies and studies of patients with scoliosis, were excluded. Axial T2-weighted and sagittal T1-weighted images were used. Studies were split into an internal training set (80%), validation set (9%), and test set (11%). Training data were labeled by four radiologists using predefined gradings (normal, mild, moderate, and severe). A two-component DL model was developed. First, a convolutional neural network (CNN) was trained to detect the region of interest (ROI), with a second CNN for classification. An internal test set was labeled by a musculoskeletal radiologist with 31 years of experience (reference standard) and two subspecialist radiologists (radiologist 1: A.M., 5 years of experience; radiologist 2: J.T.P.D.H., 9 years of experience). DL model performance on an external test set was evaluated. Detection recall (in percentage), interrater agreement (Gwet.), sensitivity, and specificity were calculated.Results: Overall, 446 MRI lumbar spine studies were analyzed (446 patients; mean age +/- standard deviation, 52 years +/- 19; 240 women), with 396 patients in the training (80%) and validation (9%) sets and 50 (11%) in the internal test set. For internal testing, DL model and radiologist central canal recall were greater than 99%, with reduced neural foramina recall for the DL model (84.5%) and radiologist 1 (83.9%) compared with radiologist 2 (97.1%) (P