Detection of Abnormalities in Spinal Cord Injury MRI Using Image Processing and Machine Learning
Received: 29 September 2025 | Revised: 4 November 2025 and 16 November 2025 | Accepted: 19 November 2025 | Online: 9 February 2026
Corresponding author: Subramanya Bhat
Abstract
To enhance the analysis of radiological spine imaging and improve clinical decision-making for traumatic Spinal Cord Injury (SCI), existing Machine Learning (ML) algorithms require refinements in accuracy and clinical applicability. This study implements Deep Learning (DL) models for the automated detection of SCI in MRI images resulting from trauma, such as falls and accidents. A retrospective analysis was conducted on 890 MRI images categorized into four severity levels: Highly Severe (A), Less Severe (B), Mildly Severe (C), and No Injury (D). The DL framework utilizes EfficientNet-B0, Swin Transformer V2-S, and DenseNet121 architectures. Multi-class prediction models were developed for the four considered severity grades, and the results demonstrate that the proposed approach outperforms state-of-the-art methods across several metrics, including Accuracy, F1-Score, Precision, Recall, Jaccard Index (IoU), and Dice Coefficient.
Keywords:
convolution neural networks, deep learning, machine learning, magnetic resonance imaging, spinal cord injuryDownloads
References
S. Maki et al., "Machine Learning and Deep Learning in Spinal Injury: A Narrative Review of Algorithms in Diagnosis and Prognosis," Journal of Clinical Medicine, vol. 13, no. 3, Jan. 2024, Art. no. 705. DOI: https://doi.org/10.3390/jcm13030705
I. G. L. N. A. Artha Wiguna et al., "A deep learning approach for cervical cord injury severity determination through axial and sagittal magnetic resonance imaging segmentation and classification," European Spine Journal, vol. 33, no. 11, pp. 4204–4213, Nov. 2024. DOI: https://doi.org/10.1007/s00586-024-08464-7
D. B. McCoy et al., "Convolutional Neural Network-Based Automated Segmentation of the Spinal Cord and Contusion Injury: Deep Learning Biomarker Correlates of Motor Impairment in Acute Spinal Cord Injury," AJNR. American journal of neuroradiology, vol. 40, no. 4, pp. 737–744, Apr. 2019. DOI: https://doi.org/10.3174/ajnr.A6020
E. Naga Karthik et al., "SCIseg: Automatic Segmentation of Intramedullary Lesions in Spinal Cord Injury on T2-weighted MRI Scans," Radiology: Artificial Intelligence, vol. 7, no. 1, Jan. 2025, Art. no. e240005. DOI: https://doi.org/10.1148/ryai.240005
Z. Yang, L. Chen, T. Fu, Z. Yin, and F. Yang, "Spine Image Segmentation Based on U-Net and Atrous spatial pyramid pooling," Journal of Physics: Conference Series, vol. 2209, no. 1, Feb. 2022, Art. no. 012020. DOI: https://doi.org/10.1088/1742-6596/2209/1/012020
Z. Wang, P. Xiao, and H. Tan, "Spinal magnetic resonance image segmentation based on U-net," Journal of Radiation Research and Applied Sciences, vol. 16, no. 3, Sept. 2023, Art. no. 100627. DOI: https://doi.org/10.1016/j.jrras.2023.100627
S. Wang, Z. Jiang, H. Yang, X. Li, and Z. Yang, "Automatic Segmentation of Lumbar Spine MRI Images Based on Improved Attention U-Net," Computational Intelligence and Neuroscience, vol. 2022, no. 1, 2022, Art. no. 4259471. DOI: https://doi.org/10.1155/2022/4259471
G. Ghobrial and C. Roth, "Deep learning-based automated segmentation and quantification of the dural sac cross-sectional area in lumbar spine MRI," Frontiers in Radiology, vol. 5, Mar. 2025. DOI: https://doi.org/10.3389/fradi.2025.1503625
M. T. Elahi, "Toward Deep Learning-based Segmentation and Quantitative Analysis of Cervical Spinal Cord Magnetic Resonance Images." arXiv, Sept. 28, 2024.
C. Gros et al., "Automatic segmentation of the spinal cord and intramedullary multiple sclerosis lesions with convolutional neural networks," NeuroImage, vol. 184, pp. 901–915, Jan. 2019. DOI: https://doi.org/10.1016/j.neuroimage.2018.09.081
SK. H. Ahammad, V. Rajesh, and MD. Z. U. Rahman, "Fast and Accurate Feature Extraction-Based Segmentation Framework for Spinal Cord Injury Severity Classification," IEEE Access, vol. 7, pp. 46092–46103, 2019. DOI: https://doi.org/10.1109/ACCESS.2019.2909583
A. Bueno et al., "Automated Cervical Spinal Cord Segmentation in Real-World MRI of Multiple Sclerosis Patients by Optimized Hybrid Residual Attention-Aware Convolutional Neural Networks," Journal of Digital Imaging, vol. 35, no. 5, pp. 1131–1142, Oct. 2022. DOI: https://doi.org/10.1007/s10278-022-00637-4
T. Inoue et al., "XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord Injury," Neurotrauma Reports, vol. 1, no. 1, pp. 8–16, 2020. DOI: https://doi.org/10.1089/neur.2020.0009
D. Kapoor and C. Xu, "Spinal Cord Injury AIS Predictions Using Machine Learning," eNeuro, vol. 10, no. 1, Jan. 2023. DOI: https://doi.org/10.1523/ENEURO.0149-22.2022
Z. Merali, J. Z. Wang, J. H. Badhiwala, C. D. Witiw, J. R. Wilson, and M. G. Fehlings, "A deep learning model for detection of cervical spinal cord compression in MRI scans," Scientific Reports, vol. 11, no. 1, May 2021, Art. no. 10473. DOI: https://doi.org/10.1038/s41598-021-89848-3
E. Zhang 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, vol. 24, no. 1, Nov. 2024, Art. no. 320. DOI: https://doi.org/10.1186/s12880-024-01489-w
J. T. P. D. Hallinan et al., "Deep Learning Model for Automated Detection and Classification of Central Canal, Lateral Recess, and Neural Foraminal Stenosis at Lumbar Spine MRI," Radiology, vol. 300, no. 1, pp. 130–138, July 2021. DOI: https://doi.org/10.1148/radiol.2021204289
N. C. Lehnen et al., "Detection of Degenerative Changes on MR Images of the Lumbar Spine with a Convolutional Neural Network: A Feasibility Study," Diagnostics, vol. 11, no. 5, May 2021, Art. no. 902. DOI: https://doi.org/10.3390/diagnostics11050902
V. Tumko et al., "A neural network model for detection and classification of lumbar spinal stenosis on MRI," European Spine Journal, vol. 33, no. 3, pp. 941–948, Mar. 2024. DOI: https://doi.org/10.1007/s00586-023-08089-2
E.-J. Hwang, J.-Y. Jung, S. K. Lee, S.-E. Lee, and W.-H. Jee, "Machine Learning for Diagnosis of Hematologic Diseases in Magnetic Resonance Imaging of Lumbar Spines," Scientific Reports, vol. 9, no. 1, Apr. 2019, Art. no. 6046. DOI: https://doi.org/10.1038/s41598-019-42579-y
K. Kita et al., "Bimodal artificial intelligence using TabNet for differentiating spinal cord tumors-Integration of patient background information and images," iScience, vol. 26, no. 10, Oct. 2023, Art. no. 107900. DOI: https://doi.org/10.1016/j.isci.2023.107900
S. Ma, Y. Huang, X. Che, and R. Gu, "Faster RCNN-based detection of cervical spinal cord injury and disc degeneration," Journal of Applied Clinical Medical Physics, vol. 21, no. 9, pp. 235–243, 2020. DOI: https://doi.org/10.1002/acm2.13001
P. S, A. S, D. A, and G. N, "Detection of Spinal Cord Injury using Deep Learning Algorithm," in 2022 International Conference on Sustainable Computing and Data Communication Systems (ICSCDS), Apr. 2022, pp. 270–275. DOI: https://doi.org/10.1109/ICSCDS53736.2022.9760935
Sk. H. Ahammad, V. Rajesh, Md. Z. U. Rahman, and A. Lay-Ekuakille, "A Hybrid CNN-Based Segmentation and Boosting Classifier for Real Time Sensor Spinal Cord Injury Data," IEEE Sensors Journal, vol. 20, no. 17, pp. 10092–10101, Sept. 2020. DOI: https://doi.org/10.1109/JSEN.2020.2992879
J.-T. Lu et al., "DeepSPINE: Automated Lumbar Vertebral Segmentation, Disc-level Designation, and Spinal Stenosis Grading Using Deep Learning." arXiv, July 26, 2018.
T. Kumar and R. Ponnusamy, "Robust Medical X-Ray Image Classification by Deep Learning with Multi-Versus Optimizer," Engineering, Technology & Applied Science Research, vol. 13, no. 4, pp. 111406–11411, Aug. 2023. DOI: https://doi.org/10.48084/etasr.6127
T. Shimizu et al., "Efficacy of a machine learning-based approach in predicting neurological prognosis of cervical spinal cord injury patients following urgent surgery within 24 h after injury," Journal of Clinical Neuroscience, vol. 107, pp. 150–156, Jan. 2023. DOI: https://doi.org/10.1016/j.jocn.2022.11.003
Y. Zhu et al., "A quantitative evaluation of the deep learning model of segmentation and measurement of cervical spine MRI in healthy adults," Journal of Applied Clinical Medical Physics, vol. 25, no. 3, Mar. 2024, Art. no. e14282. DOI: https://doi.org/10.1002/acm2.14282
Z. A. Merali, E. Colak, and J. R. Wilson, "Applications of Machine Learning to Imaging of Spinal Disorders: Current Status and Future Directions," Global Spine Journal, vol. 11, no. 1_suppl, pp. 23S-29S, Apr. 2021. DOI: https://doi.org/10.1177/2192568220961353
Downloads
How to Cite
License
Copyright (c) 2026 Gangadhara, Subramanya Bhat
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
