Li Kai-Yu, Lu Zhe-Yang, Tian Yu-Han, Liu Xiao-Peng, Zhang Ye-Kai, Qiu Jia-Wei, Li Hua-Lin, Zhang Yu-Long, Huang Jia-Wei, Ye Hao-Bo, Tian Nai Feng
Department of Orthopedic Surgery, Second Affiliated Hospital and Yuying Children's Hospital of Wenzhou Medical University, Wenzhou, China.
Renji College of Wenzhou Medical University, Wenzhou, China.
Front Neurosci. 2024 Dec 6;18:1501972. doi: 10.3389/fnins.2024.1501972. eCollection 2024.
The purpose of our study is to develop a deep learning (DL) model based on MRI and analyze its consistency with the treatment recommendations for degenerative cervical spine disorders provided by the spine surgeons at our hospital.
In this study, MRI of patients who were hospitalized for cervical spine degenerative disorders at our hospital from July 2023 to July 2024 were primarily collected. The dataset was divided into a training set, a validation set, and an external validation set. Four versions of the DL model were constructed. The external validation set was used to assess the consistency between the DL model and spine surgeons' recommendations about indication of cervical spine surgery regarding the dataset.
This study collected a total of 756 MR images from 189 patients. The external validation set included 30 patients and a total of 120 MR images, consisting of 43 images for grade 0, 20 images for grade 1, and 57 images for grade 2. The region of interest (ROI) detection model completed the ROI detection task perfectly. For the binary classification (grades 0 and 1, 2), DL version 1 showed the best consistency with the spine surgeons, achieving a Cohen's Kappa value of 0.874. DL version 4 also achieved nearly perfect consistency, with a Cohen's Kappa value of 0.811. For the three-class classification, DL version 1 demonstrated the best consistency with the spine surgeons, achieving a Cohen's Kappa value of 0.743, while DL version 2 and DL version 4 also showed substantial consistency, with Cohen's Kappa values of 0.615 and 0.664, respectively.
We initially developed deep learning algorithms that can provide clinical recommendations based on cervical spine MRI. The algorithm shows substantial consistency with experienced spine surgeons.
本研究旨在开发一种基于磁共振成像（MRI）的深度学习（DL）模型，并分析其与我院脊柱外科医生针对退行性颈椎疾病提供的治疗建议的一致性。
本研究主要收集了2023年7月至2024年7月在我院因颈椎退行性疾病住院患者的MRI图像。数据集被分为训练集、验证集和外部验证集。构建了四个版本的DL模型。外部验证集用于评估DL模型与脊柱外科医生关于数据集中颈椎手术指征建议之间的一致性。
本研究共收集了来自189名患者的756张MR图像。外部验证集包括30名患者和总共120张MR图像，其中0级图像43张、1级图像20张、2级图像57张。感兴趣区域（ROI）检测模型完美完成了ROI检测任务。对于二分类（0级和1级、2级），DL版本1与脊柱外科医生的一致性最佳，Cohen's Kappa值为0.874。DL版本4也达到了近乎完美的一致性，Cohen's Kappa值为0.811。对于三分类，DL版本1与脊柱外科医生的一致性最佳，Cohen's Kappa值为0.743，而DL版本2和DL版本4也显示出较高的一致性，Cohen's Kappa值分别为0.615和0.664。
我们初步开发了可基于颈椎MRI提供临床建议的深度学习算法。该算法与经验丰富的脊柱外科医生显示出较高的一致性。
