Development and validation of a machine learning-derived radiomics model for diagnosis of osteoporosis and osteopenia using quantitative computed tomography
Tóm tắt
To develop and validate a quantitative computed tomography (QCT) based radiomics model for discriminating osteoporosis and osteopenia.
A total of 635 patients underwent QCT were retrospectively included from November 2016 to November 2019. The patients with osteopenia or osteoporosis (N = 590) were divided into a training cohort (N = 414) and a test cohort (N = 176). Radiomics features were extracted from the QCT images of the third lumbar vertebra. Minimum redundancy and maximum relevance and least absolute shrinkage and selection operator were used for data dimensional reduction, features selection and radiomics model building. Multivariable logistic regression was applied to construct the combined clinical-radiomic model that incorporated radiomics signatures and clinical characteristics. The performance of the combined clinical-radiomic model was evaluated by the area under the curve of receiver operator characteristic curve (ROC–AUC), accuracy, specificity, sensitivity, positive predictive value, and negative predictive value. The patients with osteopenia or osteoporosis were randomly divided into training and test cohort with a ratio of 7:3. Six more predictive radiomics signatures, age, alkaline phosphatase and homocysteine were selected to construct the combined clinical-radiomic model for diagnosis of osteoporosis and osteopenia. The AUC of the combined clinical-radiomic model was 0.96 (95% confidence interval (CI), 0.95 to 0.98) in the training cohort and 0.96 (95% CI 0.92 to 1.00) in the test cohort, which were superior to the clinical model alone (training-AUC = 0.81, test-AUC = 0.79). The calibration curve demonstrated that the radiomics nomogram had good agreement between prediction and observation and decision curve analysis confirmed clinically useful. The combined clinical-radiomic model that incorporates the radiomics score and clinical risk factors, can serve as a reliable and powerful tool for discriminating osteoporosis and osteopenia.
Tài liệu tham khảo
Consensus development conference. diagnosis, prophylaxis, and treatment of osteoporosis. Am J Med. 1993;94(6):646–50.
Si L, Winzenberg TM, Jiang Q, Chen M, Palmer AJ. Projection of osteoporosis-related fractures and costs in China: 2010–2050. Osteoporos Int. 2015;26(7):1929–37.
Qaseem A, Forciea MA, McLean RM, Denberg TD. Clinical guidelines committee of the American college of P. Treatment of low bone density or osteoporosis to prevent fractures in men and women: a clinical practice guideline update from the American college of physicians. Ann Intern Med. 2017;166(11):818–39.
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):123–62.
Tagliafico AS, Cea M, Rossi F, Valdora F, Bignotti B, Succio G, et al. Differentiating diffuse from focal pattern on computed tomography in multiple myeloma: added value of a radiomics approach. Eur J Radiol. 2019;121: 108739.
Zhang B, Tian J, Dong D, Gu D, Dong Y, Zhang L, et al. Radiomics features of multiparametric MRI as novel prognostic factors in advanced nasopharyngeal carcinoma. Clin Cancer Res. 2017;23(15):4259–69.
Dong D, Tang L, Li ZY, Fang MJ, Gao JB, Shan XH, et al. Development and validation of an individualized nomogram to identify occult peritoneal metastasis in patients with advanced gastric cancer. Ann Oncol. 2019;30(3):431–8.
Lambin P, Rios-Velazquez E, Leijenaar R, Carvalho S, van Stiphout RG, Granton P, et al. Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer. 2012;48(4):441–6.
Ibrahim A, Primakov S, Beuque M, Woodruff HC, Halilaj I, Wu G, et al. Radiomics for precision medicine: current challenges, future prospects, and the proposal of a new framework. Methods. 2021;188:20–9.
Alongi P, Stefano A, Comelli A, Laudicella R, Scalisi S, Arnone G, et al. Radiomics analysis of 18F-Choline PET/CT in the prediction of disease outcome in high-risk prostate cancer: an explorative study on machine learning feature classification in 94 patients. Eur Radiol. 2021;31(7):4595–605.
Rastegar S, Vaziri M, Qasempour Y, Akhash MR, Abdalvand N, Shiri I, et al. Radiomics for classification of bone mineral loss: a machine learning study. Diagn Interv Imaging. 2020;101(9):599–610.
Zhang B, Yu K, Ning Z, Wang K, Dong Y, Liu X, et al. Deep learning of lumbar spine X-ray for osteopenia and osteoporosis screening: a multicenter retrospective cohort study. Bone. 2020;140: 115561.
Stephanakis, Ioannis, M., Anagnostopoulos, Christos-Nikolaos, Iliou, et al. A novel data preprocessing method for boosting neural network performance: A case study in osteoporosis prediction. Information Sciences: An International Journal. 2017;380:92–100.
van Griethuysen JJM, Fedorov A, Parmar C, Hosny A, Aucoin N, Narayan V, et al. Computational radiomics system to decode the radiographic phenotype. Cancer Res. 2017;77(21):e104–7.
Fornacon-Wood I, Mistry H, Ackermann CJ, Blackhall F, McPartlin A, Faivre-Finn C, et al. Reliability and prognostic value of radiomic features are highly dependent on choice of feature extraction platform. Eur Radiol. 2020;30(11):6241–50.
Peng H, Long F, Ding C. Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell. 2005;27(8):1226–38.
Baum T, Karampinos DC, Liebl H, Rummeny EJ, Waldt S, Bauer JS. High-resolution bone imaging for osteoporosis diagnostics and therapy monitoring using clinical MDCT and MRI. Curr Med Chem. 2013;20(38):4844–52.
Link TM. Osteoporosis imaging: state of the art and advanced imaging. Radiology. 2012;263(1):3–17.
Jeong H, Kim J, Ishida T, Akiyama M, Kim Y. Computerised analysis of osteoporotic bone patterns using texture parameters characterising bone architecture. Br J Radiol. 2013;86(1021):20101115.
Baum T, Grabeldinger M, Rath C, Garcia EG, Burgkart R, Patsch JM, et al. Trabecular bone structure analysis of the spine using clinical MDCT: can it predict vertebral bone strength? J Bone Miner Metab. 2014;32(1):56–64.
He L, Liu Z, Liu C, Gao Z, Ren Q, Lei L, et al. Radiomics based on lumbar spine magnetic resonance imaging to detect osteoporosis. Acad Radiol. 2021;28(6):e165–71.
Hepp T, Schmid M, Gefeller O, Waldmann E, Mayr A. Approaches to regularized regression - a comparison between gradient boosting and the lasso. Methods Inf Med. 2016;55(5):422–30.
Velazquez ER, Parmar C, Jermoumi M, Mak RH, van Baardwijk A, Fennessy FM, et al. Volumetric CT-based segmentation of NSCLC using 3D-Slicer. Sci Rep. 2013;3:3529.
Rastegar S, Vaziri M, Qasempour Y, Akhash MR, Abdalvand N, Shiri I, et al. Radiomics for classification of bone mineral loss: a machine learning study. Diagn Interv Imaging. 2020. https://doi.org/10.1016/j.diii.2020.01.008.
Lee KS, Jung SK, Ryu JJ, Shin SW, Choi J. Evaluation of transfer learning with deep convolutional neural networks for screening osteoporosis in dental panoramic radiographs. J Clin Med. 2020;9(2):392.
Hayashi T, Chen H, Miyamoto K, Zhou X, Hara T, Yokoyama R, et al. Analysis of bone mineral density distribution at trabecular bones in thoracic and lumbar vertebrae using X-ray CT images. J Bone Miner Metab. 2011;29(2):174–85.
Kennedy OD, Brennan O, Mahony NJ, Rackard SM, O’Brien FJ, Taylor D, Lee CT. Effects of high bone turnover on the biomechanical properties of the L3 vertebra in an ovine model of early stage osteoporosis. Spine (Phila Pa 1976). 2008;33(23):2518–23. https://doi.org/10.1097/BRS.0b013e318186b292.
Samelson EJ, Christiansen BA, Demissie S, Broe KE, Louie-Gao Q, Cupples LA, et al. QCT measures of bone strength at the thoracic and lumbar spine: the Framingham Study. J Bone Miner Res. 2012;27(3):654–63.
Mao SS, Li D, Syed YS, Gao Y, Luo Y, Flores F, et al. Thoracic quantitative computed tomography (QCT) can sensitively monitor bone mineral metabolism: comparison of thoracic QCT vs lumbar QCT and dual-energy X-ray absorptiometry in detection of age-relative change in bone mineral density. Acad Radiol. 2017;24(12):1582–7.
Dickerson CR, Saha S, Hotchkiss CE. Relationships between densitometric and morphological parameters as measured by peripheral computed tomography and the compressive behavior of lumbar vertebral bodies from macaques (Macaca fascicularis). Spine (Phila Pa 1976). 2008;33(4):366–72.
Yamamoto N, Sukegawa S, Kitamura A, Goto R, Noda T, Nakano K, et al. Deep learning for osteoporosis classification using hip radiographs and patient clinical covariates. Biomolecules. 2020;10(11):1534.
Shim JG, Kim DW, Ryu KH, Cho EA, Ahn JH, Kim JI, et al. Application of machine learning approaches for osteoporosis risk prediction in postmenopausal women. Arch Osteoporos. 2020;15(1):169.
Liu J, Wang J, Ruan W, Lin C, Chen D. Diagnostic and gradation model of osteoporosis based on improved deep U-Net network. J Med Syst. 2019;44(1):15.
Huynh E, Coroller TP, Narayan V, Agrawal V, Hou Y, Romano J, et al. CT-based radiomic analysis of stereotactic body radiation therapy patients with lung cancer. Radiother Oncol. 2016;120(2):258–66.
Choe J, Lee SM, Do KH, Lee G, Lee JG, Lee SM, et al. Deep learning-based image conversion of CT reconstruction kernels improves radiomics reproducibility for pulmonary nodules or masses. Radiology. 2019;292(2):365–73.
Xue Z, Huo J, Sun X, Sun X, Ai ST, LichiZhang, et al. Using radiomic features of lumbar spine CT images to differentiate osteoporosis from normal bone density. BMC Musculoskelet Disord. 2022;23(1):336.
Burian E, Subburaj K, Mookiah MRK, Rohrmeier A, Hedderich DM, Dieckmeyer M, et al. Texture analysis of vertebral bone marrow using chemical shift encoding-based water-fat MRI: a feasibility study. Osteoporos Int. 2019;30(6):1265–74.
Nardone V, Tini P, Croci S, Carbone SF, Sebaste L, Carfagno T, et al. 3D bone texture analysis as a potential predictor of radiation-induced insufficiency fractures. Quant Imaging Med Surg. 2018;8(1):14–24.
Kim BS, Kim SJ. Prognostic value of intratumoral heterogeneity of preoperative (18) F-FDG PET/CT in pancreatic cancer. Hell J Nucl Med. 2021;24(3):172–7.
Kuyumcu ME, Yesil Y, Ozturk ZA, Cinar E, Kizilarslanoglu C, Halil M, et al. The association between homocysteine (hcy) and serum natural antioxidants in elderly bone mineral densitometry (BMD). Arch Gerontol Geriatr. 2012;55(3):739–43.
Exton-Smith AN, Carlton-Ashton JR. Neurological and mental disturbances in the elderly. Proceedings of a conference held December 1977 in Jersey, Channel Islands. Age Ageing. 1978;Suppl:1–140.
Hamed SA, Moussa EM, Youssef AH, Abd ElHameed MA, NasrEldin E. Bone status in patients with epilepsy: relationship to markers of bone remodeling. Front Neurol. 2014;5:142.
Erjiang E, Wang T, Yang L, Dempsey M, Brennan A, Ming Y, et al. Machine learning can improve clinical detection of low BMD: the DXA-HIP study. J Clin Densitom. 2021;24(4):527–37. https://doi.org/10.1016/j.jocd.2020.10.004.
Kilic N, Hosgormez E. Automatic estimation of osteoporotic fracture cases by using ensemble learning approaches. J Med Syst. 2016;40(3):61.