Radiomics Based on Multimodal magnetic resonance imaging for the Differential Diagnosis of Benign and Malignant Vertebral Compression Fractures

Abstract

Objectives: Recent studies have indicated that radiomics may have excellent performance and clinical application prospects in the differential diagnosis of benign and malignant vertebral compression fractures (VCFs). However, multimodal magnetic resonance imaging (MRI)-based radiomics model is rarely used in the differential diagnosis of benign and malignant VCFs, and is limited to lumbar. Herein, this study intends to develop and validate MRI radiomics models for differential diagnoses of benign and malignant VCFs in patients.

Methods: This cross-sectional study involved 151 adult patients diagnosed with VCF in The First Affiliated Hospital of Soochow University in 2016–2021. The study was conducted in three steps: (i) the original MRI images were segmented, and the region of interest (ROI) was marked out; (ii) among the extracted features, those features with Pearson’s correlation coefficient lower than 0.9 and the top 15 with the highest variance and Lasso regression coefficient less than and more than 0 were selected; (iii) MRI images and combined data were studied by logistic regression, decision tree, random forest and extreme gradient boosting (XGBoost) models in training set and the test set (ratio of 8:2), respectively; and the models were further verified and evaluated for the differential diagnosis performance. The evaluated indexes included area under receiver (AUC) of operating characteristic curve, accuracy, sensitivity, specificity, negative predictive value (NPV), positive predictive value (PPV), and 95% confidence intervals (CIs). The AUCs were used to assess the predictive performance of different machine learning modes for benign and malignant VCFs.

Results: A total of 1144 radiomics features, and 14 clinical features were extracted. Finally, 12 radiomics features were included in the radiomics model, and 12 radiomics features with 14 clinical features were included in the combined model. In the radiomics model, the differential diagnosis performance in the logistic regression model with the AUC of 0.905 ± 0.026, accuracy of 0.817 ± 0.057, sensitivity of 0.831 ± 0.065, and negative predictive value of 0.813 ± 0.042, was superior to the other three. In the combined model, XGBoost model had the superior differential diagnosis performance with specificity (0.979 ± 0.026) and positive predictive value (0.971 ± 0.035).

Conclusion: The multimodal MRI-based radiomics model performed well in the differential diagnosis of benign and malignant VCFs, which may provide a tool for clinicians to differentially diagnose VCFs.

Keywords

Differential diagnosis / Multimodal magnetic resonance imaging / Radiomics / Vertebral compression fracture

References

[1] Pfeifle C, Kohut P, Jarvers JS, Spiegl UJ, Heyde CE, Osterhoff G. Does time-to-surgery affect mortality in patients with acute osteoporotic vertebral compression fractures? BMC Geriatr. 2021; 21(1): 714.

[2] Beall DP, De Leacy RA. Management of chronic vertebral compression fractures with vertebroplasty: focus on clinical symptoms. Radiology. 2023; 308(1): e231243.

[3] Adela A, Rangarajan L. Computational techniques to segment and classify lumbar compression fractures. Radiol Med. 2020; 125(6): 551–560.

[4] Khan MA, Jennings JW, Baker JC, Smolock AR, Shah LM, Pinchot JW, et al. ACR appropriateness criteria^® management of vertebral compression fractures: 2022 update. J Am Coll Radiol. 2023; 20(5S): S102–S124.

[5] Jackson A, Wasfie T, Brock C, Galovska S, Smalley M, Grundman K, et al. Fragility vertebral compression fractures in postmenopausal women: the role of a fracture liaison service program. Am Surg. 2020; 86(12): 1636–1639.

[6] Lv M, Zhou Z, Tang Q, Xu J, Huang Q, Lu L, et al. Differentiation of usual vertebral compression fractures using CT histogram analysis as quantitative biomarkers: a proof-of-principle study. Eur J Radiol. 2020; 131: 109264.

[7] Madassery S. Vertebral compression fractures: evaluation and management. Semin Intervent Radiol. 2020; 37(2): 214–219.

[8] Soultanis K, Thano A, Soucacos PN. Outcome of thoracolumbar compression fractures following non-operative treatment. Injury. 2021; 52(12): 3685–3690.

[9] Hameed M, Siddiqui F, Khan MK, Ali AA, Hussain W. The role of diffusion-weighted MRI in the accurate diagnosis of vertebral compression fractures: a comparative study. Radiography (Lond). 2024; 30(1): 353–358.

[10] Omari EA, Zhang Y, Ahunbay E, Paulson E, Amjad A, Chen X, et al. Multi-parametric magnetic resonance imaging for radiation treatment planning. Med Phys. 2022; 49(4): 2836–2845.

[11] Frighetto-Pereira L, Rangayyan RM, Metzner GA, de Azevedo-Marques PM, Nogueira-Barbosa MH. Shape, texture and statistical features for classification of benign and malignant vertebral compression fractures in magnetic resonance images. Comput Biol Med. 2016; 73: 147–156.

[12] Romeo V, Ugga L, Stanzione A, Cocozza S, Cuocolo R, Brunetti A. Differential diagnosis of benign and malignant vertebral compression fractures using conventional and advanced MRI techniques. BJR Open. 2019; 1(1): 20180033.

[13] Sozzi C, Trentadue M, Nicoli L, Tavani F, Piovan E. Utility of vertebral biopsy before vertebroplasty in patients with diagnosis of vertebral compression fracture. Radiol Med. 2021; 126(7): 956–962.

[14] Bezzi C, Mapelli P, Presotto L, Neri I, Scifo P, Savi A, et al. Radiomics in pancreatic neuroendocrine tumors: methodological issues and clinical significance. Eur J Nucl Med Mol Imaging. 2021; 48(12): 4002–4015.

[15] Taha B, Boley D, Sun J, Chen C. Potential and limitations of radiomics in neuro-oncology. J Clin Neurosci. 2021; 90: 206–211.

[16] Chee CG, Yoon MA, Kim KW, Ko Y, Ham SJ, Cho YC, et al. Combined radiomics-clinical model to predict malignancy of vertebral compression fractures on CT. Eur Radiol. 2021; 31(9): 6825–6834.

[17] Jiang J, Qiu J, Yin J, Wang J, Jiang X, Yi Z, et al. Automated detection of hippocampal sclerosis using real-world clinical MRI images. Front Neurosci. 2023; 17: 1180679.

[18] Zheng Y, Han X, Jia X, Ding C, Zhang K, Li H, et al. Dual-energy CT-based radiomics for predicting invasiveness of lung adenocarcinoma appearing as ground-glass nodules. Front Oncologia. 2023; 13: 1208758.

[19] Yan Q, Wang W, Zhao W, Zuo L, Wang D, Chai X, et al. Differentiating nontuberculous mycobacterium pulmonary disease from pulmonary tuberculosis through the analysis of the cavity features in CT images using radiomics. BMC Pulm Med. 2022; 22(1): 4.

[20] Kim SJ, Lee JS. Diagnostic performance of F-18 fluorodeoxyglucose positron emission tomography or positron emission tomography/computed tomography for differentiation of benign and malignant vertebral compression fractures: a meta-analysis. World Neurosurg. 2020; 137: e626–e633.

[21] Shi YJ, Li XT, Zhang XY, Liu YL, Tang L, Sun YS. Differential diagnosis of hemangiomas from spinal osteolytic metastases using 3.0 T MRI: comparison of T1-weighted imaging, chemical-shift imaging, diffusion-weighted and contrast-enhanced imaging. Oncotarget. 2017; 8(41): 71095–71104.

[22] Gui C, Chen X, Sheikh K, Mathews L, Lo SL, Lee J, et al. Radiomic modeling to predict risk of vertebral compression fracture after stereotactic body radiation therapy for spinal metastases. J Neurosurg Spine. 2021; 36: 1–9.

[23] Dong ST, Zhu J, Yang H, Huang G, Zhao C, Yuan B. Development and internal validation of supervised machine learning algorithm for predicting the risk of recollapse following minimally invasive kyphoplasty in osteoporotic vertebral compression fractures. Front Public Health. 2022; 10: 874672.

[24] Wang X, You X, Zhang L, Huang D, Aramini B, Shabaturov L, et al. A radiomics model combined with XGBoost may improve the accuracy of distinguishing between mediastinal cysts and tumors: a multicenter validation analysis. Ann Transl Med. 2021; 9(23): 1737.

[25] Le NQK, Hung TNK, Do DT, Lam LHT, Dang LH, Huynh TT. Radiomics-based machine learning model for efficiently classifying transcriptome subtypes in glioblastoma patients from MRI. Comput Biol Med. 2021; 132: 104320.

[26] Zhang H, Yuan G, Wang C, Zhao H, Zhu K, Guo J, et al. Differentiation of benign versus malignant indistinguishable vertebral compression fractures by different machine learning with MRI-based radiomic features. Eur Radiol. 2023; 33(7): 5069–5076.

[27] Feng Q, Xu S, Gong X, Wang T, He X, Liao D, et al. An MRI-based radiomics nomogram for differentiation of benign and malignant vertebral compression fracture. Acad Radiol. 2024; 31(2): 605–616.

[28] Cheung CY, Ran AR, Wang S, Chan VTT, Sham K, Hilal S, et al. A deep learning model for detection of Alzheimer’s disease based on retinal photographs: a retrospective, multicentre case-control study. Lancet Digit Health. 2022; 4(11): e806–e815.

[29] Xu Z, Zhao L, Yin L, Liu Y, Ren Y, Yang G, et al. MRI-based machine learning model: a potential modality for predicting cognitive dysfunction in patients with type 2 diabetes mellitus. Front Bioeng Biotechnol. 2022; 10: 1082794.

[30] Aghnia Farda N, Lai JY, Wang JC, Lee PY, Liu JW, Hsieh IH. Sanders classification of calcaneal fractures in CT images with deep learning and differential data augmentation techniques. Injury. 2021; 52(3): 616–624.

[31] Winter NR, Blanke J, Leenings R, Ernsting J, Fisch L, Sarink K, et al. A systematic evaluation of machine learning-based biomarkers for major depressive disorder. JAMA Psychiatry. 2024; 81(4): 386–395.

RIGHTS & PERMISSIONS

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