Fully Automatic Deep Learning Model for Spine Refracture in Patients with OVCF: A Multi-Center Study

Abstract

Background: The reaserch of artificial intelligence (AI) model for predicting spinal refracture is limited to bone mineral density, X-ray and some conventional laboratory indicators, which has its own limitations. Besides, it lacks specific indicators related to osteoporosis and imaging factors that can better reflect bone quality, such as computed tomography (CT).

Objective: To construct a novel predicting model based on bone turn-over markers and CT to identify patients who were more inclined to suffer spine refracture.

Methods: CT images and clinical information of 383 patients (training set = 240 cases of osteoporotic vertebral compression fractures (OVCF), validation set = 63, test set = 80) were retrospectively collected from January 2015 to October 2022 at three medical centers. The U-net model was adopted to automatically segment ROI. Three-dimensional (3D) cropping of all spine regions was used to achieve the final ROI regions including 3D_Full and 3D_RoiOnly. We used the Densenet 121-3D model to model the cropped region and simultaneously build a T-NIPT prediction model. Diagnostics of deep learning models were assessed by constructing ROC curves. We generated calibration curves to assess the calibration performance. Additionally, decision curve analysis (DCA) was used to assess the clinical utility of the predictive models.

Results: The performance of the test model is comparable to its performance on the training set (dice coefficients of 0.798, an mIOU of 0.755, an SA of 0.767, and an OS of 0.017). Univariable and multivariable analysis indicate that T_P1NT was an independent risk factor for refracture. The performance of predicting refractures in different ROI regions showed that 3D_Full model exhibits the highest calibration performance, with a Hosmer–Lemeshow goodness-of-fit (HL) test statistic exceeding 0.05. The analysis of the training and test sets showed that the 3D_Full model, which integrates clinical and deep learning results, demonstrated superior performance with significant improvement (p-value < 0.05) compared to using clinical features independently or using only 3D_RoiOnly.

Conclusion: T_P1NT was an independent risk factor of refracture. Our 3D-FULL model showed better performance in predicting high-risk population of spine refracture than other models and junior doctors do. This model can be applicable to real-world translation due to its automatic segmentation and detection.

Keywords

Automatic Segmentation / Deep Learning / Osteoporotic Vertebral Compression Fractures / Predictive Modeling / Refracture

References

[1] Clynes MA, Harvey NC, Curtis EM, Fuggle NR, Dennison EM, Cooper C. The epidemiology of osteoporosis. Br Med Bull. 2020; 133(1): 105–117.

[2] Siris ES, Genant HK, Laster AJ, Chen P, Misurski DA, Krege JH. Enhanced prediction of fracture risk combining vertebral fracture status and BMD. Osteoporosis Int. 2007; 18(6): 761–770.

[3] Klotzbuecher CM, Ross PD, Landsman PB, Abbott TA 3rd, Berger M. Patients with prior fractures have an increased risk of future fractures: a summary of the literature and statistical synthesis. J Bone Miner Res. 2000; 15(4): 721–739.

[4] Ross PD, Davis JW, Epstein RS, Wasnich RD. Pre-existing fractures and bone mass predict vertebral fracture incidence in women. Ann Intern Med. 1991; 114(11): 919–923.

[5] Kanis JA, Johnell O, Oden A, Johansson H, McCloskey E. FRAX and the assessment of fracture probability in men and women from the UK. Osteoporosis Int. 2008; 19(4): 385–397.

[6] International Osteoporosis Foundation. IOF one-minute osteoporosis risk test [EB/OL]. https://www.iofbone-health.org/iof-oneminute-osteoporosis-risk-test.

[7] Koh LK, Sedrine WB, Torralba TP, Kung A, Fujiwara S, Chan SP, et al. A simple tool to identify asian women at increased risk of osteoporosis. Osteoporosis Int. 2001; 12(8): 699–705.

[8] Livingstone SJ, Guthrie B, McMinn M, Eke C, Donnan PT, Morales DR. Derivation and validation of the CFracture competing risk fracture prediction tool compared with QFracture in older people and people with comorbidity: a population cohort study. Lancet Healthy Longevity. 2023; 4(1): e43–e53.

[9] Lillholm M, Ghosh A, Pettersen PC, de Bruijne M, Dam EB, Karsdal MA, et al. Vertebral fracture risk (VFR) score for fracture prediction in postmenopausal women. Osteoporosis Int. 2011; 22(7): 2119–2128.

[10] Pothuaud L, Barthe N, Krieg MA, Mehsen N, Carceller P, Hans D. Evaluation of the potential use of trabecular bone score to complement bone mineral density in the diagnosis of osteoporosis: a preliminary spine BMD-matched, case-control study. J Clin Densitom. 2009; 12(2): 170–176.

[11] Kuo RYL, Harrison C, Curran TA, Jones B, Freethy A, Cussons D, et al. Artificial intelligence in fracture detection: a systematic review and meta-analysis. Radiology. 2022; 304(1): 50–62.

[12] Langerhuizen DWG, Janssen SJ, Mallee WH, van den Bekerom MPJ, Ring D, Kerkhoffs G, et al. What are the applications and limitations of artificial intelligence for fracture detection and classification in Orthopaedic trauma imaging? A systematic review. Clin Orthop Relat Res. 2019; 477(11): 2482–2491.

[13] Myers TG, Ramkumar PN, Ricciardi BF, Urish KL, Kipper J, Ketonis C. Artificial intelligence and Orthopaedics: an introduction for clinicians. J Bone Jt Surg Am. 2020; 102(9): 830–840.

[14] Zhang X, Yang Y, Shen YW, Zhang KR, Jiang ZK, Ma LT, et al. Diagnostic accuracy and potential covariates of artificial intelligence for diagnosing orthopedic fractures: a systematic literature review and meta-analysis. Eur Radiol. 2022; 32(10): 7196–7216.

[15] Chen Y, Yang T, Gao X, Xu A. Hybrid deep learning model for risk prediction of fracture in patients with diabetes and osteoporosis. Front Med. 2022; 16(3): 496–506.

[16] Hong N, Cho SW, Shin S, Lee S, Jang SA, Roh S, et al. Deep-learning-based detection of vertebral fracture and osteoporosis using lateral spine X-ray radiography. J Bone Miner Res. 2023; 38(6): 887–895.

[17] Hsieh CI, Zheng K, Lin C, Mei L, Lu L, Li W, et al. Automated bone mineral density prediction and fracture risk assessment using plain radiographs via deep learning. Nat Commun. 2021; 12(1): 5472.

[18] Lindsey R, Daluiski A, Chopra S, Lachapelle A, Mozer M, Sicular S, et al. Deep neural network improves fracture detection by clinicians. Proc Natl Acad Sci U S A. 2018; 115(45): 11591–11596.

[19] Kim KC, Cho HC, Jang TJ, Choi JM, Seo JK. Automatic detection and segmentation of lumbar vertebrae from X-ray images for compression fracture evaluation. Comput Methods Programs Biomed. 2021; 200: 105833.

[20] Kong SH, Lee JW, Bae BU, Sung JK, Jung KH, Kim JH, et al. Development of a spine X-ray-based fracture prediction model using a deep learning algorithm. Endocrinol Metab. 2022; 37(4): 674–683.

[21] Dong Q, Luo G, Lane NE, Lui LY, Marshall LM, Kado DM, et al. Deep learning classification of spinal osteoporotic compression fractures on radiographs using an adaptation of the Genant Semiquantitative criteria. Acad Radiol. 2022; 29(12): 1819–1832.

[22] Seo JW, Lim SH, Jeong JG, Kim YJ, Kim KG, Jeon JY. A deep learning algorithm for automated measurement of vertebral body compression from X-ray images. Sci Rep. 2021; 11(1): 13732.

[23] Dong Q, Luo G, Lane NE, Lui LY, Marshall LM, Johnston SK, et al. Generalizability of deep learning classification of spinal osteoporotic compression fractures on radiographs using an adaptation of the Modified-2 algorithm-based qualitative criteria. Acad Radiol. 2023; 30(12): 2973–2987.

[24] Carey JJ, Chih-Hsing WP, Bergin D. Risk assessment tools for osteoporosis and fractures in 2022. Best Pract Res Clin Rheumatol. 2022; 36(3): 101775.

[25] Lex JR, Di Michele J, Koucheki R, Pincus D, Whyne C, Ravi B. Artificial intelligence for hip fracture detection and outcome prediction: a systematic review and meta-analysis. JAMA Netw Open. 2023; 6(3): e233391.

[26] Bae J, Yu S, Oh J, Kim TH, Chung JH, Byun H, et al. External validation of deep learning algorithm for detecting and visualizing femoral neck fracture including displaced and non-displaced fracture on plain X-ray. J Digit Imaging. 2021; 34(5): 1099–1109.

[27] Kalmet PHS, Sanduleanu S, Primakov S, Wu G, Jochems A, Refaee T, et al. Deep learning in fracture detection: a narrative review. Acta Orthop. 2020; 91(2): 215–220.

[28] Tomita N, Cheung YY, Hassanpour S. Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Comput Biol Med. 2018; 98: 8–15.

[29] Xu G, Wang D, Zhang H, Xu C, Li H, Zhang W, et al. Prediction of osteoporosis from proximal femoral cortical bone thickness and Hounsfield unit value with clinical significance. Front Surg. 2022; 9: 1047603.

[30] Zou D, Li W, Deng C, Du G, Xu N. The use of CT Hounsfield unit values to identify the undiagnosed spinal osteoporosis in patients with lumbar degenerative diseases. Eur Spine J. 2019; 28(8): 1758–1766.

[31] Earp BE, Kallini JR, Collins JE, Benavent KA, Tintle SM, Rozental TD. Correlation of Hounsfield unit measurements on computed tomography of the shoulder with dual-energy X-ray absorptiometry scans and fracture risk assessment tool scores: a potential for opportunistic screening. J Orthop Trauma. 2021; 35(7): 384–390.

[32] Kelsey JL. Risk factors for osteoporosis and associated fractures. Public Health Rep. 1989; 104 Suppl(Suppl): 14–20.

[33] Song L. Calcium and bone metabolism indices. Adv Clin Chem. 2017; 82: 1–46.

[34] Sobh MM, Abdalbary M, Elnagar S, Nagy E, Elshabrawy N, Abdelsalam M, et al. Secondary osteoporosis and metabolic bone diseases. J Clin Med. 2022; 11(9): 2382.

[35] Watanabe H, Maishi N, Hoshi-Numahata M, Nishiura M, Nakanishi-Kimura A, Hida K, et al. Skeletal-vascular interactions in bone development, homeostasis, and pathological destruction. Int J Mol Sci. 2023; 24(13): 10912.

[36] Jia L, Cheng M. Correlation analysis between risk factors, BMD and serum osteocalcin, CatheK, PINP, β-crosslaps, TRAP, lipid metabolism and BMI in 128 patients with postmenopausal osteoporotic fractures. Eur Rev Med Pharmacol Sci. 2022; 26(21): 7955–7959.

[37] Hanusch B, Prediger M, Tuck SP, Walker J, McNally R, Datta HK. Bone turnover markers as determinants of bone density and fracture in men with distal forearm fractures: the pathogenesis examined in the Mr F study. Osteoporosis Int. 2021; 32(11): 2267–2277.

[38] Cann CE, Genant HK. Precise measurement of vertebral mineral content using computed tomography. J Comput Assist Tomogr. 1980; 4(4): 493–500.

[39] Rüegsegger P, Elsasser U, Anliker M, Gnehm H, Kind H, Prader A. Quantification of bone mineralization using computed tomography. Radiology. 1976; 121(1): 93–97.

[40] Engelke K, Adams JE, Armbrecht G, Augat P, Bogado CE, Bouxsein ML, et al. Clinical use of quantitative computed tomography and peripheral quantitative computed tomography in the management of osteoporosis in adults: the 2007 ISCD official positions. J Clin Densitom. 2008; 11(1): 123–162.

[41] Chen W, Liu X, Li K, Luo Y, Bai S, Wu J, et al. A deep-learning model for identifying fresh vertebral compression fractures on digital radiography. Eur Radiol. 2022; 32(3): 1496–1505.

RIGHTS & PERMISSIONS

2024 The Author(s). Orthopaedic Surgery published by Tianjin Hospital and John Wiley & Sons Australia, Ltd.