Artificial intelligence in spinal imaging - a narrative review

Abstract

Clinical integration of artificial intelligence (AI) in spinal surgery is still in its early stages, with spinal imaging being the most prominent. We present a review of recent literature on the topic. The reporting of traditional spinal imaging has been slow due to overburdened staff and unreliable in some patients. AI applications have shown promising results in improving the speed and quality of imaging while reducing costs and radiation exposure. Specific examples of clinical implementation include osteoporosis screening, diagnosing degenerative spine diseases and differentiating tuberculous and pyogenic spondylitis, helping in preoperative measurements and surgical planning. Other tools have demonstrated the ability to help clinicians in real time to reduce rates of missed fractures and to rule out cord impingement in emergency settings. Novel variants of magnetic resonance imaging (MRI) and synthetic computed tomography (sCT) scans, without ionizing radiation, have been successful in reducing the resource burden and scan time, while maintaining clinical utility. At its current stage, AI has the potential to improve significantly and is expected to tremendously enhance the efficiency and accuracy of radiologists and spine care providers. However, clinical validation studies are still required before the widespread integration of AI in direct patient care.

Keywords

Artificial intelligence / spinal imaging / spine / surgery / deep learning / machine learning / neural networks

References

[1] Grzybowski A,Lambert WC.A history of artificial intelligence.Clin Dermatol2024;42:221-9

[2] Malik P, Pathania M, Rathaur VK. Overview of artificial intelligence in medicine.J Family Med Prim Care2019;8:2328-31 PMCID:PMC6691444

[3] Mayo RC.Artificial intelligence and deep learning - radiology’s next frontier?.Clin Imaging2018;49:87-8

[4] Feddock CA.The lost art of clinical skills.Am J Med2007;120:374-8

[5] Li S.Malpractice liability risk and use of diagnostic imaging services: a systematic review of the literature.J Am Coll Radiol2015;12:1403-12

[6] Herzog R,Flanders AE.Variability in diagnostic error rates of 10 MRI centers performing lumbar spine MRI examinations on the same patient within a 3-week period.Spine J2017;17:554-61

[7] McHugh ML.Interrater reliability: the kappa statistic.Biochem Med2012;22:276-82 PMCID:PMC3900052

[8] Russell S.Artificial intelligence. fears of an AI pioneer.Science2015;349:252

[9] IBM. AI vs. machine learning vs. deep learning vs. neural networks: what’s the difference? 2023. https://www.ibm.com/think/topics/ai-vs-machine-learning-vs-deep-learning-vs-neural-networks. (accessed 2025-02-11)

[10] Samuel AL.Some studies in machine learning using the game of checkers.IBM J Res Dev1959;3:210-29

[11] Jakhar D.Artificial intelligence, machine learning and deep learning: definitions and differences.Clin Exp Dermatol2020;45:131-2

[12] Tian C,Li Z,Fei L.Attention-guided CNN for image denoising.Neural Netw2020;124:117-29

[13] Burge R,Solomon DH,King A.Incidence and economic burden of osteoporosis-related fractures in the United States, 2005-2025.J Bone Miner Res2007;22:465-75

[14] Mugge L,Caras A.Osteoporosis as a risk factor for intraoperative complications and long-term instrumentation failure in patients with scoliotic spinal deformity.Spine2022;47:1435-42

[15] Gillespie CW.Trends and disparities in osteoporosis screening among women in the United States, 2008-2014.Am J Med2017;130:306-16

[16] Malik AT,Phillips FM.Declining trend in osteoporosis management and screening following vertebral compression fractures - a national analysis of commercial insurance and medicare advantage beneficiaries.Spine J2020;20:538-46

[17] Ferizi U,Hysi P.Artificial intelligence applied to osteoporosis: a performance comparison of machine learning algorithms in predicting fragility fractures from MRI data.J Magn Reson Imaging2019;49:1029-38 PMCID:PMC7340101

[18] Kathirvelu D,Kalpana V.A computer aided diagnosis system for measurement of mandibular cortical thickness on dental panoramic radiographs in prediction of women with low bone mineral density.J Med Syst2019;43:148

[19] Pan Y,Wang H.Automatic opportunistic osteoporosis screening using low-dose chest computed tomography scans obtained for lung cancer screening.Eur Radiol2020;30:4107-16 PMCID:PMC7305250

[20] Lee CS,Weaver SJ.Cognitive and system factors contributing to diagnostic errors in radiology.AJR Am J Roentgenol2013;201:611-7

[21] Lin RT,Como CJ.Formal radiologist interpretations of intraoperative spine radiographs have low clinical value.Spine2024;49:933-40

[22] Levi AD,Anderson P.Neurologic deterioration secondary to unrecognized spinal instability following trauma - a multicenter study.Spine2006;31:451-8

[23] Parenteau CS,Campbell IC.Prevalence of spine degeneration diagnosis by type, age, gender, and obesity using Medicare data.Sci Rep2021;11:5389 PMCID:PMC7940625

[24] Jamaludin A, Lootus M, Kadir T, et al; Genodisc Consortium. ISSLS PRIZE IN BIOENGINEERING SCIENCE 2017: Automation of reading of radiological features from magnetic resonance images (MRIs) of the lumbar spine without human intervention is comparable with an expert radiologist.Eur Spine J2017;26:1374-83

[25] Kim K,Lee YH,Lee HS.Performance of the deep convolutional neural network based magnetic resonance image scoring algorithm for differentiating between tuberculous and pyogenic spondylitis.Sci Rep2018;8:13124 PMCID:PMC6120953

[26] Pan Y,Chen T.Evaluation of a computer-aided method for measuring the Cobb angle on chest X-rays.Eur Spine J2019;28:3035-43

[27] Guermazi A,Kompel AJ.Improving radiographic fracture recognition performance and efficiency using artificial intelligence.Radiology2022;302:627-36

[28] Voter AF,Garrett JW.Diagnostic accuracy and failure mode analysis of a deep learning algorithm for the detection of cervical spine fractures.AJNR Am J Neuroradiol2021;42:1550-6 PMCID:PMC8367597

[29] Terai H,Toyoda H.Tandem keyhole foraminotomy in the treatment of cervical radiculopathy: retrospective review of 35 cases.J Orthop Surg Res2014;9:38 PMCID:PMC4041334

[30] Nakamura Y,Tatsugami F.Possibility of deep learning in medical imaging focusing improvement of computed tomography image quality.J Comput Assist Tomogr2020;44:161-7

[31] Kaplan S.Full-dose PET image estimation from low-dose PET image using deep learning: a pilot study.J Digit Imaging2019;32:773-8 PMCID:PMC6737135

[32] Gong E,Wintermark M.Deep learning enables reduced gadolinium dose for contrast-enhanced brain MRI.J Magn Reson Imaging2018;48:330-40

[33] Edelstein WA,Carrino JA.MRI: time is dose - and money and versatility.J Am Coll Radiol2010;7:650-2 PMCID:PMC3175640

[34] Mehdi Z. MRI wait times must be shortened to improve health care, cornell researchers say 2018. https://cornellsun.com/2018/02/08/mri-wait-times-must-be-shortened-to-improve-health-care-cornell-researchers-say/. (accessed 2025-02-11)

[35] McLean B.MRI and the critical care patient: clinical, operational, and financial challenges.Crit Care Res Pract2023;2023:2772181 PMCID:PMC10264715

[36] Meléndez JC.Anxiety-related reactions associated with magnetic resonance imaging examinations.JAMA1993;270:745-7

[37] Zaharchuk G,Wintermark M,Langlotz CP.Deep learning in neuroradiology.AJNR Am J Neuroradiol2018;39:1776-84 PMCID:PMC7410723

[38] Lundervold AS.An overview of deep learning in medical imaging focusing on MRI.Z Med Phys2019;29:102-27

[39] Zhang K,Chen Y,Zhang L.Beyond a Gaussian denoiser: residual learning of deep CNN for image denoising.IEEE Trans Image Process2017;26:3142-55

[40] Bash S,Gibbs W,Shankaranarayanan A.Deep learning image processing enables 40% faster spinal MR scans which match or exceed quality of standard of care: a prospective multicenter multireader study.Clin Neuroradiol2022;32:197-203

[41] Bash S,Airriess C.Deep learning enables 60% accelerated volumetric brain MRI while preserving quantitative performance: a prospective, multicenter, multireader trial.AJNR Am J Neuroradiol2021;42:2130-7 PMCID:PMC8805755

[42] Wiesinger F.Zero-TE MRI: principles and applications in the head and neck.Br J Radiol2022;95:20220059 PMCID:PMC10162052

[43] Ensle F,Lohezic M.Enhanced bone assessment of the shoulder using zero-echo time MRI with deep-learning image reconstruction.Skeletal Radiol2024;53:2597-606 PMCID:PMC11493801

[44] Aydıngöz Ü,Ergen FB.Zero echo time musculoskeletal MRI: technique, optimization, applications, and pitfalls.Radiographics2022;42:1398-414

[45] Morbée L,Herregods N,Jans LBO.MRI-based synthetic CT of the lumbar spine: geometric measurements for surgery planning in comparison with CT.Eur J Radiol2021;144:109999

[46] Spadea MF,Zaffino P.Deep learning based synthetic-CT generation in radiotherapy and PET: a review.Med Phys2021;48:6537-66

[47] Jans LBO,Elewaut D.MRI-based synthetic CT in the detection of structural lesions in patients with suspected sacroiliitis: comparison with MRI.Radiology2021;298:343-9

[48] van der Kolk BBYM,Nijholt IM.Bone visualization of the cervical spine with deep learning-based synthetic CT compared to conventional CT: a single-center noninferiority study on image quality.Eur J Radiol2022;154:110414

[49] Wiesinger F,Yang J.Zero TE-based pseudo-CT image conversion in the head and its application in PET/MR attenuation correction and MR-guided radiation therapy planning.Magn Reson Med2018;80:1440-51

[50] Leynes AP,Wiesinger F.Zero-echo-time and Dixon deep pseudo-CT (ZeDD CT): direct generation of pseudo-CT images for pelvic PET/MRI attenuation correction using deep convolutional neural networks with multiparametric MRI.J Nucl Med2018;59:852-8 PMCID:PMC5932530

[51] Kisinde S,Hesselbacher S.The predictive accuracy of surgical planning using pre-op planning software and a robotic guidance system.Eur Spine J2021;30:3676-87

[52] Wu H,Rasoulinejad P.Automated comprehensive adolescent idiopathic scoliosis assessment using MVC-Net.Med Image Anal2018;48:1-11

[53] Djurasovic M.Correlation of radiographic and clinical findings in spinal deformities.Neurosurg Clin N Am2007;18:223-7

[54] Weng CH,Huang YJ.Artificial intelligence for automatic measurement of sagittal vertical axis using ResUNet framework.J Clin Med2019;8:1826 PMCID:PMC6912675

[55] Wang X,Niu Y.Automatic vertebrae localization and identification by combining deep SSAE contextual features and structured regression forest.J Digit Imaging2019;32:336-48 PMCID:PMC6456738

[56] Suzani A,Liu Y,Rohling RN.Fast automatic vertebrae detection and localization in pathological CT scans - a deep learning approach. In: Navab N, Hornegger J, Wells WM, Frangi AF, editors. Medical image computing and computer-assisted intervention - MICCAI 2015. Cham: Springer International Publishing; 2015. pp. 678-86.

[57] Martín-Noguerol T,Amrhein TJ.The role of artificial intelligence in the assessment of the spine and spinal cord.Eur J Radiol2023;161:110726

[58] Miura J,Miyata K.Dynamic evaluation of the spinal cord in patients with cervical spondylotic myelopathy using a kinematic magnetic resonance imaging technique.J Spinal Disord Tech2009;22:8-13

[59] Hatem R,Thornton JE.A call to address AI “hallucinations” and how healthcare professionals can mitigate their risks.Cureus2023;15:e44720 PMCID:PMC10552880

[60] van Leeuwen KG, Schalekamp S, Rutten MJCM, van Ginneken B, de Rooij M. Artificial intelligence in radiology: 100 commercially available products and their scientific evidence.Eur Radiol2021;31:3797-804

[61] Kim DW,Kim KW,Park SH.Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: results from recently published papers.Korean J Radiol2019;20:405-10 PMCID:PMC6389801

[62] Liu X,Kale AU.A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis.Lancet Digit Health2019;1:e271-97

[63] Zech JR,Liu M,Titano JJ.Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study.PLoS Med2018;15:e1002683 PMCID:PMC6219764