Share：
Share this content in WeChat
X
[Chinese][PDF]2915
• Clinical Article •
Diagnosis of osteoporosis by radiomics on T2WI sequence of lumbar magnetic resonance imaging
KANG Siru  TIAN Ronghua 

Cite this article as: KANG S R, TIAN R H. Diagnosis of osteoporosis by radiomics on T2WI sequence of lumbar magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2023, 14(11): 121-127. DOI:10.12015/issn.1674-8034.2023.11.020.


[Abstract] Objective To investigate efficacy of radiomics on the lumbar spine MRI based on T2WI sequences in identifying osteoporosis.Materials and Methods A retrospective analysis was conducted on a total of 291 patients who underwent lumbar spine MRI examinations at our hospital between December 2022 and March 2023. Regions of interest (ROI) were delineated layer by layer on the sagittal T2WI images. Radiomic features were extracted from the MR images of 1455 lumbar vertebrae. The samples were randomly divided into a training group (n=233) and a test group (n=58) at an 8∶2 ratio. The least absolute shrinkage and selection operator (LASSO) was used to reduce data dimensionality and select features. Logistic regression (LR) was employed to establish clinical models, radiomic models, and a combined model for predicting osteoporosis. The performance of the composite models was evaluated using metrics such as the area under the curve (AUC) of receiver operating characteristic (ROC), accuracy, specificity, sensitivity, positive predictive value, and negative predictive value. DeLong test was used to compare the predictive performance among the models. Calibration curves for the models were plotted, and Hosmer-Lemeshow test was applied to assess model fit. Decision curve analysis (DCA) was used to evaluate the clinical utility of each model.Results In the training group, the AUCs for the clinical model, radiomic model, and combined model were 0.791 [95% confidence interval (CI): 0.733-0.849], 0.879 (95% CI: 0.833-0.925), and 0.893 (95% CI: 0.853-0.934), respectively. In the test group, the AUCs were 0.805 (95% CI: 0.676-0.935), 0.913 (95% CI: 0.841-0.985), and 0.904 (95% CI: 0.825-0.984), respectively. DeLong test results indicated that there was a statistically significant difference between the combined model and the clinical model (P＜0.05), while there was no statistically significant difference between the combined model and the radiomic model (P＞0.05). The Hosmer-Lemeshow test showed that the models were well calibrated (P=0.250, 0.753, 0.575). The results of DCA demonstrated that both the radiomic model and the combined model had better clinical value for predicting osteoporosis compared to the clinical model.Conclusions An image-based radiomics model constructed from lumbar T2WI has the potential for objective and accurate osteoporosis diagnosis.
[Keywords] lumbar spine；osteoporosis；magnetic resonance imaging；radiomics

KANG Siru   TIAN Ronghua*  

Department of Radiology, Xiaogan Hospital Affiliated to Wuhan University of Science and Technology, Xiaogan 432000, China

Corresponding author: TIAN R H, E-mail: 423623105@qq.com

Conflicts of interest   None.

ACKNOWLEDGMENTS Xiaogan City Natural Science Project (No. XGKJ2022010002).
Received  2023-06-06
Accepted  2023-11-07
DOI: 10.12015/issn.1674-8034.2023.11.020
Cite this article as: KANG S R, TIAN R H. Diagnosis of osteoporosis by radiomics on T2WI sequence of lumbar magnetic resonance imaging[J]. Chin J Magn Reson Imaging, 2023, 14(11): 121-127. DOI:10.12015/issn.1674-8034.2023.11.020.

[1]
Bonr and Joint Group of Chinese Society of Radiology of Chinese Medical Association, Musculoskeletal Group of Radiology Society of Radiology of Chinese Medical Doctors Association, Osteoporosis Group of Chinese Society of Orthopedic of Chinese Medical Association, et al. Consensus on the diagnosis of osteoporosis by imaging and bone mineral density measurement[J]. Chin J Radiol, 2020, 54(8): 745-752. DOI: 10.3760/cma.j.cn112149-20200331-00485.
[2]
Workgroup of 2018 Chinese Guideline for the Diagnosis and Treatment of Senile Osteoporosis, Osteoporosis Society of China Association Gerontology and Geriatries, MA Y Z, et al. 2018 China guideline for diagnosis and treatment of senile osteoporosis[J]. Chin J Osteoporos, 2018, 24(12): 1541-1565. DOI: 10.3969/j.issn.1006-7108.2018.12.001.
[3]
AIBAR-ALMAZÁN A, VOLTES-MARTÍNEZ A, CASTELLOTE-CABALLERO Y, et al. Current status of the diagnosis and management of osteoporosis[J/OL]. Int J Mol Sci, 2022, 23(16): 9465 [2023-05-25]. https://pubmed.ncbi.nlm.nih.gov/36012730/. DOI: 10.3390/ijms23169465.
[4]
LEBOFF M S, GREENSPAN S L, INSOGNA K L, et al. The clinician's guide to prevention and treatment of osteoporosis[J]. Osteoporos Int, 2022, 33(10): 2049-2102. DOI: 10.1007/s00198-021-05900-y.
[5]
HALIN M, ALLADO E, ALBUISSON E, et al. Prevalence of osteoporosis assessed by DXA and/or CT in severe obese patients[J/OL]. J Clin Med, 2022, 11(20): 6114 [2023-05-25]. https://pubmed.ncbi.nlm.nih.gov/36294434/. DOI: 10.3390/jcm11206114.
[6]
DENG X L, YANG L, CHEN S H, et al. The value of routine MRI examination for evaluating osteoporosis[J]. Chin J Magn Reson Imag, 2020, 11(8): 663-665. DOI: 10.12015/issn.1674-8034.2020.08.014.
[7]
MARTEL D, MONGA A, CHANG G. Osteoporosis imaging[J]. Radiol Clin N Am, 2022, 60(4): 537-545. DOI: 10.1016/j.rcl.2022.02.003.
[8]
LIU J, CHEN J D, LI P, et al. Comprehensive assessment of osteoporosis in lumbar spine using compositional MR imaging of trabecular bone[J]. Eur Radiol, 2023, 33(6): 3995-4006. DOI: 10.1007/s00330-022-09368-0.
[9]
TAN H, YANG Z, FAN Q J, et al. Magnetic transfer imaging and multi-echo Dixon technique in diagnosis of primary osteoporosis[J]. Chin J Med Imag Technol, 2022, 38(11): 1694-1698. DOI: 10.13929/j.issn.1003-3289.2022.11.022.
[10]
YUN J S, LEE H D, KWACK K S, et al. Use of proton density fat fraction MRI to predict the radiographic progression of osteoporotic vertebral compression fracture[J]. Eur Radiol, 2021, 31(6): 3582-3589. DOI: 10.1007/s00330-020-07529-7.
[11]
ZHANG H N, SONG Q W, ZHANG N, et al. Application of compressed sensing technology in rapid lumbar magnetic resonance imaging[J]. Chin J Magn Reson Imag, 2023, 14(2): 132-137, 144. DOI: 10.12015/issn.1674-8034.2023.02.022.
[12]
PAHATI·TUXUNJIANG, YANG L H, HE X, et al. Application of radiomics in spinal diseases[J]. Chin J Magn Reson Imag, 2022, 13(5): 162-166. DOI: 10.12015/issn.1674-8034.2022.05.035.
[13]
ZHENG Y L, ZHOU D, LIU H, et al. CT-based radiomics analysis of different machine learning models for differentiating benign and malignant parotid tumors[J]. Eur Radiol, 2022, 32(10): 6953-6964. DOI: 10.1007/s00330-022-08830-3.
[14]
RICHARDSON M L, AMINI B, KINAHAN P E. Bone and soft tissue tumors: horizons in radiomics and artificial intelligence[J]. Radiol Clin North Am, 2022, 60(2): 339-358. DOI: 10.1016/j.rcl.2021.11.011.
[15]
LAFATA K J, WANG Y Q, KONKEL B, et al. Radiomics: a primer on high-throughput image phenotyping[J]. Abdom Radiol (NY), 2022, 47(9): 2986-3002. DOI: 10.1007/s00261-021-03254-x.
[16]
LI Y L, WONG K H, LAW M W, et al. Opportunistic screening for osteoporosis in abdominal computed tomography for Chinese population[J/OL]. Arch Osteoporos, 2018, 13(1): 76 [2023-05-25]. https://link.springer.com/article/10.1007/s11657-018-0492-y. DOI: 10.1007/s11657-018-0492-y.
[17]
WANG J L, ZHOU S W, CHEN S P, et al. Prediction of osteoporosis using radiomics analysis derived from single source dual energy CT[J/OL]. BMC Musculoskelet Disord, 2023, 24(1): 100 [2023-05-25]. https://pubmed.ncbi.nlm.nih.gov/36750927/. DOI: 10.1186/s12891-022-06096-w.
[18]
BIAN T T, WU Z J, LIN Q, et al. Evaluating tumor-infiltrating lymphocytes in breast cancer using preoperative MRI-based radiomics[J]. J Magn Reson Imaging, 2022, 55(3): 772-784. DOI: 10.1002/jmri.27910.
[19]
PEI Q, YI X P, CHEN C, et al. Pre-treatment CT-based radiomics nomogram for predicting microsatellite instability status in colorectal cancer[J]. Eur Radiol, 2022, 32(1): 714-724. DOI: 10.1007/s00330-021-08167-3.
[20]
JIANG Y W, XU X J, WANG R, et al. Radiomics analysis based on lumbar spine CT to detect osteoporosis[J]. Eur Radiol, 2022, 32(11): 8019-8026. DOI: 10.1007/s00330-022-08805-4.
[21]
ZHANG J, LIU J Y, LIANG Z P, et al. Differentiation of acute and chronic vertebral compression fractures using conventional CT based on deep transfer learning features and hand-crafted radiomics features[J/OL]. BMC Musculoskelet Disord, 2023, 24(1): 165 [2023-05-25]. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9987077. DOI: 10.1186/s12891-023-06281-5.
[22]
XUE Z H, HUO J Y, SUN X J, et al. Using radiomic features of lumbar spine CT images to differentiate osteoporosis from normal bone density[J/OL]. BMC Musculoskelet Disord, 2022, 23(1): 336 [2023-05-25]. https://pubmed.ncbi.nlm.nih.gov/35395769/. DOI: 10.1186/s12891-022-05309-6.
[23]
WANG M M, CHEN X, CUI W J, et al. A computed tomography-based radiomics nomogram for predicting osteoporotic vertebral fractures: a longitudinal study[J]. J Clin Endocrinol Metab, 2023, 108(6): e283-e294 [2023-05-25]. https://pubmed.ncbi.nlm.nih.gov/36494103/. DOI: 10.1210/clinem/dgac722.
[24]
YAP F Y, VARGHESE B A, CEN S Y, et al. Shape and texture-based radiomics signature on CT effectively discriminates benign from malignant renal masses[J]. Eur Radiol, 2021, 31(2): 1011-1021. DOI: 10.1007/s00330-020-07158-0.
[25]
REIAZI R, ABBAS E, FAMIYEH P, et al. The impact of the variation of imaging parameters on the robustness of Computed Tomography radiomic features: A review[J/OL]. Comput Biol Med, 2021, 133: 104400 [2023-05-25]. https://www.sciencedirect.com/science/article/pii/S0010482521001943?via%3Dihub. DOI: 10.1016/j.compbiomed.2021.104400.
[26]
BIAMONTE E, LEVI R, CARRONE F, et al. Artificial intelligence-based radiomics on computed tomography of lumbar spine in subjects with fragility vertebral fractures[J]. J Endocrinol Invest, 2022, 45(10): 2007-2017. DOI: 10.1007/s40618-022-01837-z.
[27]
SEBRO R, DE LA GARZA-RAMOS C. Opportunistic screening for osteoporosis and osteopenia from CT scans of the abdomen and pelvis using machine learning[J]. Eur Radiol, 2023, 33(3): 1812-1823. DOI: 10.1007/s00330-022-09136-0.
[28]
YAO Q Q, LIU M K, YUAN K M, et al. Radiomics nomogram based on dual-energy spectral CT imaging to diagnose low bone mineral density[J/OL]. BMC Musculoskelet Disord, 2022, 23(1): 424 [2023-05-25]. https://pubmed.ncbi.nlm.nih.gov/35524240/. DOI: 10.1186/s12891-022-05389-4.
[29]
XIE Q R, CHEN Y, HU Y M, et al. Development and validation of a machine learning-derived radiomics model for diagnosis of osteoporosis and osteopenia using quantitative computed tomography[J/OL]. BMC Med Imaging, 2022, 22(1): 140 [2023-05-25]. https://pubmed.ncbi.nlm.nih.gov/35941568/. DOI: 10.1186/s12880-022-00868-5.
[30]
WEI Q, ZHENG M, WENG C W, et al. Early numerical rating scale and Oswestry disability index in postmenopausal osteoporosis treated with denosumab[J]. Chin J Orthop, 2022, 42(12): 768-775. DOI: 10.3760/cma.j.cn121113-20220126-00047.
[31]
CHEN Z, LEI F, YE F, et al. MRI-based vertebral bone quality score for the assessment of osteoporosis in patients undergoing surgery for lumbar degenerative diseases[J/OL]. J Orthop Surg Res, 2023, 18(1): 257 [2023-05-25]. https://pubmed.ncbi.nlm.nih.gov/36991471/.
[32]
LIN M M, WEN X M, HUANG Z W, et al. A nomogram for predicting residual low back pain after percutaneous kyphoplasty in osteoporotic vertebral compression fractures[J]. Osteoporos Int, 2023, 34(4): 749-762. DOI: 10.1007/s00198-023-06681-2.
[33]
FADLI D, KIND M, MICHOT A, et al. Natural changes in radiological and radiomics features on MRIs of soft-tissue sarcomas Naïve of treatment: correlations with histology and patients' outcomes[J]. J Magn Reson Imaging, 2022, 56(1): 77-96. DOI: 10.1002/jmri.28021.
[34]
LI C W, XIAO Z B, HE Z M, et al. Value of radiomics stacking ensemble learning model based on T2WI and CE-T1WI in predicting the efficacy of HIFU ablation of uterine fibroid[J]. Chin J Magn Reson Imag, 2023, 14(6): 45-51. DOI: 10.12015/issn.1674-8034.2023.06.007.
[35]
GAO W X, CHEN Y G, WANG X Y, et al. Establishment and verification of a predictive nomogram for new vertebral compression fracture occurring after bone cement injection in middle-aged and elderly patients with vertebral compression fracture[J]. Orthop Surg, 2023, 15(4): 961-972. DOI: 10.1111/os.13655.
[36]
ZHONG Y, LIU X, XIAO Y D, et al. Research progress of medical image texture analysis in musculoskeletal diseases[J]. Chin J Magn Reson Imag, 2020, 11(5): 394-397. DOI: 10.12015/issn.1674-8034.2020.05.018.

PREV A nomogram model for diagnosing axial spondyloarthritis based on sacroiliac joint MRI radiomics features and clinical parameters
NEXT Value of intravoxel incoherent motion magnetic resonance imaging in evaluating renal fibrosis in rabbits with renal artery stenosis
  


LINK


Tel & Fax: +8610-67113815    E-mail: editor@cjmri.cn