Diagnostic accuracy of artificial intelligence technologies in analyzing magnetic resonance imaging results for detecting degenerative changes in the lumbosacral spine

Degenerative spinal diseases are a major medical problem and a common cause of chronic pain, reduced quality of life, and loss of work capacity. Modern treatment approaches, including conservative methods and surgical interventions, do not always demonstrate sufficient clinical efficacy, highlighting the need for improved diagnostic capabilities.

Magnetic resonance imaging is the primary modality for visualizing spinal pathologies, providing a detailed assessment of structures, including intervertebral discs, the spinal cord, and surrounding tissues. However, routine MRI diagnostics face significant methodological challenges, such as the need to perform numerous standardized measurements. The integration of artificial intelligence into radiology offers a solution to these problems: algorithms can automate image processing, speeding up analysis and enhancing diagnostic accuracy.

Objective: To evaluate the diagnostic accuracy of automated detection of degenerative changes in the lumbosacral spine using AI-assisted MRI.

Materials and Methods. A retrospective diagnostic study was conducted, comprising 100 examinations. Artificial intelligence services (hereinafter referred to as AI service 1, AI-2, AI-3) integrated into the Unified Radiological Information System (URIS) of the Moscow Unified Medical Information and Analytical System (EMIAS) were used as the index test.

A test dataset was prepared by three experts based on MRI scans of the lumbosacral spine (T2 sagittal, T2 axial, 4 mm slice thickness). Inclusion criteria were patients aged 18–90 years without artifacts or comorbid pathologies. The evaluation of the AI services involved analyzing degenerative changes: dorsal intervertebral disc protrusions; measurements (anteroposterior diameter of the dural sac on axial and sagittal images, transverse diameter of the dural sac on axial images); and the cross-sectional area of the dural sac.

Conclusion. Calibration testing confirmed the importance of evaluating the effectiveness of AI services in medicine. AI-1 and AI-3 demonstrated high reliability (AUC >0.95), making them suitable for clinical use. AI-2 requires refinement, as its performance metrics were significantly lower than claimed and further declined in external validation, limiting its practical application.

1. Tyurnikov V.M. Degenerative-dystrophic lesions of the spine: diagnosis, clinical features, and treatment. RMJ. 2008; 26: 1739. (In Russian)

2. Podchufarova E.V., Yakhno N.N., Alekseev V.V. et al. Chronic pain syndromes of lumbosacral localization: the role of structural musculoskeletal disorders and psychological factors. Pain. 2003; 1: 38–43. (In Russian)

3. Kreneva Yu.A., Panov V.P., Avdeeva M.V., Bogomolova K.A. Restorative potential of complex rehabilitation in the primary health care provision for patients with degenerative disc diseases. Preventive and Clinical Medicine. 2018; 2 (67): 76–82. (In Russian)

4. Orel A.M., Semenova O.K. The frequency of degenerative-dystrophic lesions of the joints of the spine in young and middle-aged patients with dorsopathy. Russian Osteopathic Journal. 2019; 3–4: 30–36. https://doi.org/10.32885/2220-0975-2019-3-4-30-36 (In Russian)

5. Vishlova I., Karpov S., Starodubtsev A. Low back pain syndrome: epidemiology and clinical manifestations. Medical News of North Caucasus. 2016; 4: 586–587. https://doi.org/10.14300/mnnc.2016.00142 (In Russian)

6. Gholamrezanezhad A., Basques K., Batouli A. et al. Clinical Nononcologic Applications of PET/CT and PET/MRI in Musculoskeletal, Orthopedic, and Rheumatologic Imaging. Am. J. Roentgenol. 2018; 210 (6): W245–W263. https://doi.org/10.2214/AJR.17.18523

7. Guidelines for the development of occupational safety instructions for personnel of magnetic resonance imaging (MRI) units (departments) [Internet]. Moscow: Research and Practical Center of Medical Radiology, Moscow Healthcare Department; 2017. 32 p. https://telemedai.ru/media/uploads/2023/02/21/44-_.pdf (In Russian)

8. Hajiheydari N., Delgosha M.S., Saheb T. AI in medical diagnosis: A contextualised study of patient motivations and concerns. Soc. Sci. Med. 2025; 371: 117850. https://doi.org/10.1016/j.socscimed.2025.117850

9. Xuan J., Ke B., Ma W. et al. Spinal disease diagnosis assistant based on MRI images using deep transfer learning methods. Front. Public Health. 2023; 11: 1044525. https://doi.org/10.3389/fpubh.2023.1044525

10. Su Z.H., Liu J., Yang M.S. et al. Automatic Grading of Disc Herniation, Central Canal Stenosis and Nerve Roots Compression in Lumbar Magnetic Resonance Image Diagnosis. Front. Endocrinol. (Lausanne). 2022; 13: 890371. https://doi.org/10.3389/fendo.2022.890371

11. Experiment on the use of artificial intelligence technologies for the analysis of medical images [Electronic resource]. MosMed.AI. State Budgetary Healthcare Institution ‘Scientific and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Department of Health’. URL: https://mosmed.ai/ai/ (In Russian)

12. Bobrovskaya T.M., Vasiliev Yu.A., Nikitin N.Yu., Arzamasov K.M. Approaches to building radiology datasets. Medical Doctor and Information Technologies.. 2023; 4: 14–23. https://doi.org/10.25881/18110193_2023_4_14

13. Vasiliev Yu.A., Vladzymyrskyy A.V., Omelyanskaya O.V. et al. Methodology for testing and monitoring artificial intelligence-based software for medical diagnostics. Digital Diagnostics. 2023; 4 (3): 252–267. https://doi.org/10.17816/DD321971 (In Russian)

14. Documents of the experiment on the use of artificial intelligence technologies for the analysis of medical images [Electronic resource]. MosMed.AI. State Budgetary Healthcare Institution ‘Scientific and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Department of Health’. URL: https://mosmed.ai/ai/docs/ (In Russian)

15. Certificate of State Registration of a Database No. 2023621223, Russian Federation. MosMedData: MRI with signs of pathologies of the lumbosacral spine: No. 2023620789; application dated March 24, 2023; published April 17, 2023 / Yu.A. Vasiliev, E.V. Turavilova, A.V. Vladzimirsky et al.; applicant: State Budgetary Healthcare Institution of the City of Moscow “Research and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Healthcare Department.” (In Russian)

16. Clinical Trials of Artificial Intelligence Systems (Radiology). Moscow: State Budgetary Healthcare Institution of Moscow “Scientific and Practical Clinical Center for Diagnostics and Telemedicine Technologies of the Moscow Department of Healthcare”, 2023. 40 p. https://mosmed.ai/documents/294/web_Клинические_испытания_систем_искусственного_интеллекта_Pxp0V2i.pdf (In Russian)

17. Sun X., Xu W. Fast implementation of DeLong’s algorithm for comparing the areas under correlated receiver operating characteristic curves. IEEE Transactions on Signal Processing. 2014; 21 (11): 1389–1393. https://doi.org/10.1109/LSP.2014.2337313

18. Pauly M., Asendorf T., Konietschke F. Permutation-based inference for the AUC: A unified approach for continuous and discontinuous data. Biom. J. 2016; 58 (6): 1319–1337. https://doi.org/10.1002/bimj.201500105

19. Bobrovskaya T.M., Vasiliev Yu.A., Nikitin N.Yu. et al. Sample Size for Assessing the Diagnostic Accuracy of Artificial Intelligence-Based Software in Radiology. Siberian Journal of Clinical and Experimental Medicine. 2024; 39 (3): 188–198.

20. https://doi.org/10.29001/2073-8552-2024-39-3-188-198 (In Russian)

21. Nahm F.S. Receiver operating characteristic curve: overview and practical use for clinicians. Korean J. Anesthesiol. 2022; 75 (1): 25–36. https://doi.org/10.4097/kja.21209

22. Low back pain and sciatica in over 16s: assessment and management. London: National Institute for Health and Care Excellence (NICE); 2020 Dec 11. https://www.ncbi.nlm.nih.gov/books/NBK562933/

23. Kwee R.M., Amasha A..AH., Kwee T.C. Reading Times of Common Musculoskeletal MRI Examinations: A Survey Study. Tomography. 2024; 10 (9): 1527–1533. https://doi.org/10.3390/tomography10090112

24. Zheng H.D., Sun Y.L., Kong D.W. et al. Deep learning-based high-accuracy quantitation for lumbar intervertebral disc degeneration from MRI. Nat. Commun. 2022; 13 (1): 841. https://doi.org/10.1038/s41467-022-28387-5

25. Grob A., Loibl M., Jamaludin A. et al. External validation of the deep learning system “SpineNet” for grading radiological features of degeneration on MRIs of the lumbar spine. Eur. Spine J. 2022; 31 (8): 2137–2148. https://doi.org/10.1007/s00586-022-07311-x

26. 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

27. Bichu Y.M., Hansa I., Bichu A.Y. et al. Applications of artificial intelligence and machine learning in orthodontics: a scoping review. Prog. Orthod. 2021; 22 (1): 18. https://doi.org/10.1186/s40510-021-00361-9

28.