Construction and validation of a unified 3D convolutional neural network framework for automated identification of cervical spinal cord injury based on CT imaging
4 affiliations
- 1Department of Limb and Joint Ward, Wuzhou Red Cross Hospital, Wuzhou, Guangxi Province China
- 2Department of Spine Ward, Wuzhou Red Cross Hospital, Wuzhou, Guangxi Province China
- 3Department of Medical Imaging Department, Wuzhou Red Cross Hospital, Wuzhou, Guangxi China
- 4Department of Information, Wuzhou Red Cross Hospital, Wuzhou, Guangxi Province China
Abstract
Objective: To construct and validate a standardized three-dimensional convolutional neural network (3D CNN) framework based on cervical spine CT imaging for automated identification of cervical spinal cord injury (CSCI), and to evaluate its stability across multicenter data and potential clinical applicability.
Methods: Cervical spine CT images were retrospectively collected from two independent clinical centers, including cases with and without cervical spinal cord injury. All images were converted to NIfTI format through a unified preprocessing pipeline, and three-dimensional spinal cord regions of interest (ROIs) were delineated using ITK-SNAP to assess interobserver consistency. A standardized 3D CNN architecture was constructed, and the dataset was divided into training, internal validation, and external validation sets using a stratified random strategy. Model training was performed using the PyTorch framework. Classification performance across different datasets was systematically evaluated, and ROC curves, precision–recall (PR) curves, prediction probability distributions, and threshold sensitivity analyses were used to explore the model’s clinical application characteristics.
Results: The model demonstrated stable discriminative performance across the training, internal validation, and external validation sets, with AUC-ROC values of 0.943, 0.953, and 0.948, respectively, and AUC-PR values of 0.936, 0.939, and 0.943, respectively. Performance metrics showed minimal variation among datasets, with no evident overfitting or performance degradation. Prediction probability distributions indicated good separation between injured and non-injured samples. Threshold sensitivity analysis showed that the model could achieve performance trade-offs under different threshold settings, suggesting a degree of flexibility for clinical decision-making.
Conclusion: Based on standardized data processing and network design, the 3D CNN effectively extracted latent spatial information associated with cervical spinal cord injury from CT images. The proposed framework demonstrated good stability and reproducibility across multicenter data and may serve as a preliminary research framework for CT-based CSCI risk evaluation, particularly in scenarios where MRI is unavailable or limited. Prospective validation is required before clinical deployment. It also provides a methodological reference for the standardized construction of deep learning models in medical imaging research.
Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12880-026-02626-3.
Related
- Construction and validation of an identification model for frailty in maintenance hemodialysis patients using multiple machine learning algorithms: a cross-sectional study of retrospectively collected data
- Identification and validation of feature genes using a ferroptosis-informed analytical framework in medulloblastoma
- An attention-guided dense convolutional network for automated diabetic foot ulcer segmentation
- Automated correction of training sets for biological image segmentation by convolutional networks
- Automated quantitative analysis can support the identification of progressive pulmonary fibrosis in fibrotic interstitial lung disease.
BibTeX
@article{ou2026construction,
title = {{Construction and validation of a unified 3D convolutional neural network framework for automated identification of cervical spinal cord injury based on CT imaging}},
author = {Deyan Ou and Yongxin Mo and Yu Huang and Yongqing Ye and Sen Lin and Linkun Pan and Rongdao Lin and Shengle Huang and Shixin Pan},
journal = {BMC Medical Imaging},
year = {2026},
month = oct,
doi = {10.1186/s12880-026-02626-3},
url = {https://doi.org/10.1186/s12880-026-02626-3},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - Construction and validation of a unified 3D convolutional neural network framework for automated identification of cervical spinal cord injury based on CT imaging
AU - Deyan Ou
AU - Yongxin Mo
AU - Yu Huang
AU - Yongqing Ye
AU - Sen Lin
AU - Linkun Pan
AU - Rongdao Lin
AU - Shengle Huang
AU - Shixin Pan
PY - 2026
DA - 2026/10/27
JO - BMC Medical Imaging
DO - 10.1186/s12880-026-02626-3
UR - https://doi.org/10.1186/s12880-026-02626-3
AB - Objective: To construct and validate a standardized three-dimensional convolutional neural network (3D CNN) framework based on cervical spine CT imaging for automated identification of cervical spinal cord injury (CSCI), and to evaluate its stability across multicenter data and potential clinical applicability. Methods: Cervical spine CT images were retrospectively collected from two independent clinical centers, including cases with and without cervical spinal cord injury. All images were converted to NIfTI format through a unified preprocessing pipeline, and three-dimensional spinal cord regions of interest (ROIs) were delineated using ITK-SNAP to assess interobserver consistency. A standardized 3D CNN architecture was constructed, and the dataset was divided into training, internal validation, and external validation sets using a stratified random strategy. Model training was performed using the PyTorch framework. Classification performance across different datasets was systematically evaluated, and ROC curves, precision–recall (PR) curves, prediction probability distributions, and threshold sensitivity analyses were used to explore the model’s clinical application characteristics. Results: The model demonstrated stable discriminative performance across the training, internal validation, and external validation sets, with AUC-ROC values of 0.943, 0.953, and 0.948, respectively, and AUC-PR values of 0.936, 0.939, and 0.943, respectively. Performance metrics showed minimal variation among datasets, with no evident overfitting or performance degradation. Prediction probability distributions indicated good separation between injured and non-injured samples. Threshold sensitivity analysis showed that the model could achieve performance trade-offs under different threshold settings, suggesting a degree of flexibility for clinical decision-making. Conclusion: Based on standardized data processing and network design, the 3D CNN effectively extracted latent spatial information associated with cervical spinal cord injury from CT images. The proposed framework demonstrated good stability and reproducibility across multicenter data and may serve as a preliminary research framework for CT-based CSCI risk evaluation, particularly in scenarios where MRI is unavailable or limited. Prospective validation is required before clinical deployment. It also provides a methodological reference for the standardized construction of deep learning models in medical imaging research. Supplementary Information: The online version contains supplementary material available at https://doi.org/10.1186/s12880-026-02626-3.
SN - 1471-2342
ER -