Magnetic resonance image segmentation of the compressed spinal cord in patients with degenerative cervical myelopathy using convolutional neural networks
Magnetic resonance image segmentation of the compressed spinal cord in patients with degenerative cervical myelopathy using convolutional neural networks
复制标题
使用卷积神经网络对退行性脊髓型颈椎病患者受压脊髓进行磁共振图像分割
DOI：
10.1007/s11548-022-02783-0
复制
发表时间：
2023
期刊：
影响因子：
--
通讯作者：
Orita S.
中科院分区：
文献类型：
--
作者：
Nozawa K;Maki S;Furuya T;Okimatsu S;Inoue T;Yunde A;Miura M;Shiratani Y;Shiga Y;Inage K;Eguchi Y;Ohtori S;Orita S.
目的脊髓分割是基于图谱的脊髓图像分析的第一步，但是对退行性脊髓型颈椎病患者的受压脊髓进行分割具有挑战性。我们应用卷积神经网络模型从 DCM 患者的 T2 加权轴向磁共振图像中分割脊髓。此外，我们评估了该网络分割的横截面积与患者神经症状之间的相关性。方法使用U-Net、DeepLabv3 + 和PyTorch构建CNN架构。 CNN 使用来自 174 名患者的 2762 个轴向切片进行了训练，另外还保留了来自 33 名患者的 517 个轴向切片进行验证，以及来自 46 名患者的 777 个轴向切片进行测试。 CNN 的性能在测试数据集上进行评估，并以 Dice 系数作为结果衡量标准。计算由 CNN 分割的最大压缩级别的 CSA 与 C2 级别的 CSA 之比。使用 Spearman 等级相关系数研究测试数据集中 DCM 患者的脊髓 CSA 比率与日本骨科协会评分之间的相关性。结果当使用 U-Net 作为架构、EfficientNet-b7 作为迁移学习模型时，获得了最佳的 Dice 系数。 DCM患者脊髓CSA比值与JOA评分之间的Spearman’srs为0.38（p= 0.007），呈现弱相关性。结论利用以变形脊髓磁共振图像作为训练数据的深度学习，我们能够对DCM患者受压脊髓进行分割，与专家手动分割具有较高的一致性。此外，脊髓 CSA 比率与神经系统症状的相关性较弱，但显着。我们的研究展示了对 DCM 患者实施基于图谱的自动化分析所需的第一步。
PurposeSpinal cord segmentation is the first step in atlas-based spinal cord image analysis, but segmentation of compressed spinal cords from patients with degenerative cervical myelopathy is challenging. We applied convolutional neural network models to segment the spinal cord from T2-weighted axial magnetic resonance images of DCM patients. Furthermore, we assessed the correlation between the cross-sectional area segmented by this network and the neurological symptoms of the patients.MethodsThe CNN architecture was built using U-Net and DeepLabv3 + and PyTorch. The CNN was trained on 2762 axial slices from 174 patients, and an additional 517 axial slices from 33 patients were held out for validation and 777 axial slices from 46 patients for testing. The performance of the CNN was evaluated on a test dataset with Dice coefficients as the outcome measure. The ratio of CSA at the maximum compression level to CSA at the C2 level, as segmented by the CNN, was calculated. The correlation between the spinal cord CSA ratio and the Japanese Orthopaedic Association score in DCM patients from the test dataset was investigated using Spearman's rank correlation coefficient.ResultsThe best Dice coefficient was achieved when U-Net was used as the architecture and EfficientNet-b7 as the model for transfer learning. Spearman'srsbetween the spinal cord CSA ratio and the JOA score of DCM patients was 0.38 (p= 0.007), showing a weak correlation.ConclusionUsing deep learning with magnetic resonance images of deformed spinal cords as training data, we were able to segment compressed spinal cords of DCM patients with a high concordance with expert manual segmentation. In addition, the spinal cord CSA ratio was weakly, but significantly, correlated with neurological symptoms. Our study demonstrated the first steps needed to implement automated atlas-based analysis of DCM patients.
登录
查看更多内容
影响因子：
3.9
作者：
Ost K;Jacobs WB;Evaniew N;Cohen-Adad J;Anderson D;Cadotte DW
通讯作者：
Cadotte DW
影响因子：
10.6
作者：
De Leener, Benjamin;Cohen-Adad, Julien;Kadoury, Samuel
通讯作者：
Kadoury, Samuel
影响因子：
3.7
作者：
Martin AR;De Leener B;Cohen-Adad J;Kalsi-Ryan S;Cadotte DW;Wilson JR;Tetreault L;Nouri A;Crawley A;Mikulis DJ;Ginsberg H;Massicotte EM;Fehlings MG
通讯作者：
Fehlings MG
影响因子：
8.6
作者：
Hernandez, Ana Luisa C. C.;Rezende, Thiago J. R.;Franca Jr, Marcondes C.
通讯作者：
Franca Jr, Marcondes C.
影响因子：
5.7
作者：
De Leener, Benjamin;Kadoury, Samuel;Cohen-Adad, Julien
通讯作者：
Cohen-Adad, Julien