Automatic Detection and Classification of Modic Changes in MRI Images Using Deep Learning: Intelligent Assisted Diagnosis System

Abstract

Objective:: Modic changes (MCs) are the most prevalent classification system for describing intravertebral MRI signal intensity changes. However, interpreting these intricate MRI images is a complex and time-consuming process. This study investigates the performance of single shot multibox detector (SSD) and ResNet18 network-based automatic detection and classification of MCs. Additionally, it compares the inter-observer agreement and observer-classifier agreement in MCs diagnosis to validate the feasibility of deep learning network-assisted detection of classified MCs.

Method:: A retrospective analysis of 140 patients with MCs who underwent MRI diagnosis and met the inclusion and exclusion criteria in Tianjin Hospital from June 2020 to June 2021 was used as the internal dataset. This group consisted of 55 males and 85 females, aged 25 to 89 years, with a mean age of (59.0 ± 13.7) years. An external test dataset of 28 patients, who met the same criteria and were assessed using different MRI equipment at Tianjin Hospital, was also gathered, including 11 males and 17 females, aged 31 to 84 years, with a mean age of 62.7 ± 10.9 years. After Physician 1 (with 15 years of experience) annotated all MRI images, the internal dataset was imported into the deep learning model for training. The model comprises an SSD network for lesion localization and a ResNet18 network for lesion classification. Performance metrics, including accuracy, recall, precision, F1 score, confusion matrix, and inter-observer agreement parameter Kappa value, were used to evaluate the model's performance on the internal and external datasets. Physician 2 (with 1 year of experience) re-labeled the internal and external test datasets to compare the inter-observer agreement and observer-classifier agreement.

Results:: In the internal dataset, when models were utilized for the detection and classification of MCs, the accuracy, recall, precision and F1 score reached 86.25%, 87.77%, 84.92% and 85.60%, respectively. The Kappa value of the inter-observer agreement was 0.768 (95% CI: 0.656, 0.847),while observer-classifier agreement was 0.717 (95% CI: 0.589, 0.809).In the external test dataset, the model's the accuracy, recall, precision and F1 scores for diagnosing MCs reached 75%, 77.08%, 77.80% and 74.97%, respectively. The inter-observer agreement was 0.681 (95% CI: 0.512, 0.677), and observer-classifier agreement was 0.519 (95% CI: 0.290, 0.690).

Conclusion:: The model demonstrated strong performance in detecting and classifying MCs, achieving high agreement with physicians in MCs diagnosis. These results suggest that deep learning models have the potential to facilitate the application of intelligent assisted diagnosis techniques in the field of spine research.

Keywords

End-plate osteochondritis / Magnetic resonance imaging / Modic changes / ResNet18 / SSD

References

[1] Saiklang P, Puntumetakul R, Selfe J, Yeowell G. An evaluation of an innovative exercise to relieve chronic low back pain in sedentary workers. Hum Factors. 2022;64:820–834.

[2] Murray CJ, Barber RM, Foreman KJ, Ozgoren AA, Abd-Allah F, Abera SF, et al. Global, regional,and national disability-adjusted life years (DALYs) for 306 diseases and injuries and healthy life expectancy (HALE) for 188 countries, 1990-2013: quantifying the epidemiological transition. Lancet. 2015;386:2145–2191.

[3] Shmagel A, Foley R, Ibrahim H. Epidemiology of chronic low back pain in US adults: data from the 2009–2010 National Health and nutrition examination survey. Arthritis Care Res. 2016;68:1688–1694.

[4] D'Antoni F, Russo F, Ambrosio L, Bacco L, Vollero L, Vadalà G. Artificial intelligence and computer aided diagnosis in chronic low back pain: a systematic review. Int J Environ Res Public Health. 2022;19:5971.

[5] Liu J, Hao L, Suyou L, Shan Z, Li S, Zhao F. Biomechanical properties of lumbar endplates and their correlation with MRI findings of lumbar degeneration. J Biomech. 2016;49:586–593.

[6] Brinjikji W, Diehn FE, Jarvik JG, Carr CM, Kallmes DF, Murad MH. MRI findings of disc degeneration are more prevalent in adults with low back pain than in asymptomatic controls: a systematic review and meta-analysis.AJNR. Am J Neuroradiol. 2015;36:2394–2399.

[7] Weishaupt D, Zanetti M, Hodler J, Min K, Fuchs B, Pfirrmann CW. Painful lumbar disk derangement: relevance of endplate abnormalities at MR imaging. Radiology. 2001;218:420–427.

[8] Kjaer P, Korsholm L, Bendix T, Sorensen JS, Leboeuf-Yde C. Modic changes and their associations with clinical findings. Eur Spine J. 2006;15:1312–1319.

[9] Karppinen J, Shen FH, Luk KD, Andersson GB, Cheung KM, Samartzis D. Management of degenerative disk disease and chronic low back pain. Orthop Clin North Am. 2011;42:513–528.

[10] Samartzis D, Borthakur A, Belfer I, Bow C, Lotz JC, Wang HQ. Novel diagnostic and prognostic methods for disc degeneration and low back pain. Spine J. 2015;15:1919–1932.

[11] Modic MT, Steinberg PM, Ross JS, Masaryk TJ, Carter JR. Degenerative disk disease: assessment of changes in vertebral body marrow with MR imaging. Radiology. 1988;166:193–199.

[12] Karchevsky M, Schweitzer ME, Carrino JA, Zoga A, Montgomery D, Parker L. Reactive endplate marrow changes: a systematic morphologic and epidemiologic evaluation. Skeletal Radiol. 2005;34:125–129.

[13] Mera Y, Teraguchi M, Hashizume H, Oka H, Muraki S, Akune T, et al. Association between types of Modic changes in the lumbar region and low back pain in a large cohort: the Wakayama spine study. Eur Spine J. 2021;30:1011–1017.

[14] Yang X, Karis DS, Vleggeert-Lankamp CL. Association between Modic changes, disc degeneration, and neck pain in the cervical spine: a systematic review of literature. Spine J. 2020;20:754–764.

[15] Jensen TS, Karppinen J, Sorensen JS, Niinimäki J, Leboeuf-Yde C. Vertebral endplate signal changes (Modic change): a systematic literature review of prevalence and association with non-specific low back pain. Eur Spine J. 2008;17:1407–1422.

[16] Conger A, Schuster NM, Cheng DS, Sperry BP, Joshi AB, Haring RS, et al. The effectiveness of intraosseous basivertebral nerve radiofrequency neurotomy for the treatment of chronic low back pain in patients with Modic changes: a systematic review. Pain Med. 2021;22:1039–1054.

[17] Määttä JH, Kraatari M, Wolber L, Niinimäki J, Wadge S, Karppinen J, et al. Vertebral endplate change as a feature of intervertebral disc degeneration: a heritability study. Eur Spine J. 2014;23:1856–1862.

[18] Setio AAA, Traverso A, De BT, Berens MS, Van Den Bogaard C, Cerello P, et al. Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge. Med Image Anal. 2017;42:1–13.

[19] Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60–88.

[20] Ye JJ. Artificial intelligence for pathologists is not near—it is here: description of a prototype that can transform how we practice pathology tomorrow. Arch Pathol Lab Med. 2015;139:929–935.

[21] Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542:115–118.

[22] Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA. 2016;316:2402–2410.

[23] Jamaludin A, Lootus M, Kadir T, Zisserman A, Urban J, Battié MC, et al. 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 J. 2017;26:1374–1383.

[24] Gao KT, Tibrewala R, Hess M, Bharadwaj UU, Inamdar G, Link TM, et al. Automatic detection and voxel-wise mapping of lumbar spine Modic changes with deep learning. JOR Spine. 2022;5:e1204.

[25] Windsor R, Jamaludin A, Kadir T, Zisserman A. SpineNetV2: automated detection, labelling and radiological grading of clinical MR scans. arXiv preprint arXiv:2205.01683. 2022.

[26] Wang L, Zhang S, Liu G, You SN, Wang Z, Zhu S, et al. Comparison of MRI diagnosis of 140 cases of MCs using intelligent network automatic detection and classification methods. J Shandong Univ (Health Sciences). 2023;61:71–79.

[27] Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CYet al,. Ssd: Single shot multibox detector. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part I 14. Springer International Publishing. 2016 pp. 21–37.

[28] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. 2014.

[29] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern Rrecognition. Las Vegas, NV: IEEE; 2016. p. 770–778.

[30] Yang L, Hanneke S, Carbonell J. A theory of transfer learning with applications to active learning. Mach Learn. 2013;90:161–189.

[31] Rosa G, Papa J, Marana A, Scheirer W, Cox D. Fine-tuning convolutional neural networks using harmony search. Progress in pattern recognition, image analysis, computer vision, and applications: 20th Iberoamerican congress. Volume 2013. Cham: Springer International Publishing; 2015. p. 683–690.

RIGHTS & PERMISSIONS

2023 2023 The Authors. Orthopaedic Surgery published by Tianjin Hospital and John Wiley & Sons Australia, Ltd.