A neural network model for detection and classification of central lumbosacral spinal stenosis on MRI scans

Objective: to develop a convolutional neural network (CNN) model to classify the presence and severity of central lumbar spinal stenosis (LSS) during MRI examination and to demonstrate its effectiveness as an accurate and consistent diagnostic tool.

Methods. Morphological classifications of LSS and quantitative measurements of key anatomical structures were combined using two CNNs. To classify central stenosis, models were trained on 1635 labeled lumbar spine MRI studies consisting of T2-weighted sagittal and axial planes at the level of each vertebra. The accuracy of the model was assessed using an external validation set of 150 MRI studies graded by a panel of 7 radiologists as: no stenosis, mild, moderate or severe spinal canal stenosis. The reference value for all types of stenosis was determined by majority vote, and in the event of disagreement, a decision was made by an external radiologist. The radiologists' interpretations were then compared with those of the trained model.

Results. The model demonstrated comparable performance to the average radiologist both in identifying the presence/absence of LSS and in classifying severity for all 3 types of stenosis. For central canal stenosis, the sensitivity and specificity of the CNN were (0.93; 0.85) for binary classification (presence/absence) compared to the average radiologist (0.86; 0.86). For lateral pocket stenosis, the sensitivity and specificity of CNN were (0.92; 0.80) compared to the radiologist's mean (0.83; 0.94). For foraminal stenosis, the sensitivity and specificity of CNN were (0.89; 0.86) compared to the radiologist's mean (0.81; 0.91). Multiclass classification of stenosis severity showed similar statistics.

Conclusions. CNNs showed comparable performance to radiologists in detecting and classifying LSS. The integration of neural network models in pathology detection could provide higher accuracy, efficiency, systematicity, and the possibility of subsequent interpretation in diagnostic practice.

1. Kalichman L, Cole R, Kim DH, et al. Spinal stenosis prevalence and association with symptoms: the Framingham Study. Spine J. 2009;9(7):545-550. https://doi.org/10.1016/j.spinee.2009.03.005

2. Wu AM, Zou F, Cao Y, et al. Lumbar spinal stenosis: an update on the epidemiology, diagnosis and treatment. Ame Medical J. 2017;2(5):63-63. https://doi.org/10.21037/amj.2017.04.13

3. Katz JN, Harris MB. Lumbar Spinal Stenosis. New Engl J Medicine. 2008;358(8):818-825. https://doi.org/10.1056/nejmcp0708097

4. Lurie J, Tomkins-Lane C. Management of lumbar spinal stenosis. Bmj. 2016;352:h6234. https://doi.org/10.1136/bmj.h6234

5. Kreiner DS, Shaffer WO, Baisden JL, et al. An evidence-based clinical guideline for the diagnosis and treatment of degenerative lumbar spinal stenosis (update). Spine J. 2013;13(7):734-743. https://doi.org/10.1016/j.spinee.2012.11.059

6. Majidi H, Shafizad M, Niksolat F, et al. Relationship Between Magnetic Resonance Imaging Findings and Clinical Symptoms in Patients with Suspected Lumbar Spinal Canal Stenosis: a Case-control Study. Acta Informatica Medica. 2019;27(4):229-233. https://doi.org/10.5455/aim.2019.27.229-233

7. Steurer J, Roner S, Gnannt R, Hodler J, Collaboration LR. Quantitative radiologic criteria for the diagnosis of lumbar spinal stenosis: a systematic literature review. Bmc Musculoskelet Di. 2011;12(1):175. https://doi.org/10.1186/1471-2474-12-175

8. Andreisek G, Deyo RA, Jarvik JG, et al. Consensus conference on core radiological parameters to describe lumbar stenosis - an initiative for structured reporting. Eur Radiol. 2014;24(12):3224-3232. https://doi.org/10.1007/s00330-014-3346-z

9. Lehnen NC, Haase R, Faber J, et al. Detection of Degenerative Changes on MR Images of the Lumbar Spine with a Convolutional Neural Network: A Feasibility Study. Diagnostics. 2021;11(5):902. https://doi.org/10.3390/diagnostics11050902

10. Jamaludin A, Kadir T, Zisserman A. SpineNet: Automated classification and evidence visualization in spinal MRIs. Med Image Anal. 2017;41:63-73. https://doi.org/10.1016/j.media.2017.07.002

11. Hallinan JTPD, Zhu L, Yang K, et al. Deep Learning Model for Automated Detection and Classification of Central Canal, Lateral Recess, and Neural Foraminal Stenosis at Lumbar Spine MRI. Radiology. 2021;300(1):130-138. https://doi.org/10.1148/radiol.2021204289

12. Ronneberger, O., Fischer, P. and Brox, T., 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18 (pp. 234-241). Springer International Publishing.

13. Radosavovic, I., Kosaraju, R.P., Girshick, R., He, K. and Dollár, P., 2020. Designing network design spaces. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 10428-10436).

14. Pannell WC, Savin DD, Scott TP, Wang JC, Daubs MD. Trends in the surgical treatment of lumbar spine disease in the United States. Spine J. 2015;15(8):1719-1727. https://doi.org/10.1016/j.spinee.2013.10.014

15. Lu JT, Pedemonte S, Bizzo B, et al. DeepSPINE: Automated Lumbar Vertebral Segmentation, Disc-level Designation, and Spinal Stenosis Grading Using Deep Learning. Arxiv. Published online 2018. https://doi.org/10.48550/arxiv.1807.10215

16. Won D, Lee HJ, Lee SJ, Park SH. Spinal Stenosis Grading in Magnetic Resonance Imaging Using Deep Convolutional Neural Networks. Spine. 2020;45(12):804-812. https://doi.org/10.1097/brs.0000000000003377

17. Su ZH, Liu J, Yang MS, et al. Automatic Grading of Disc Herniation, Central Canal Stenosis and Nerve Roots Compression in Lumbar Magnetic Resonance Image Diagnosis. Front Endocrinol. 2022;13:890371. https://doi.org/10.3389/fendo.2022.890371

18. Andrasinova T, Adamova B, Buskova J, Kerkovsky M, Jarkovsky J, Bednarik J. Is there a Correlation Between Degree of Radiologic Lumbar Spinal Stenosis and its Clinical Manifestation? Clin Spine Surg. 2018;31(8):E403-E408. https://doi.org/10.1097/bsd.0000000000000681

19. Mourad R, Kolisnyk S, Baiun Y, et al. Performance of hybrid artificial intelligence in determining candidacy for lumbar stenosis surgery. Eur Spine J. 2022;31(8):2149-2155. https://doi.org/10.1007/s00586-022-07307-7