Share：
Share this content in WeChat
X
[Chinese][PDF]5383
• Clinical Article •
A nomogram model for diagnosing axial spondyloarthritis based on sacroiliac joint MRI radiomics features and clinical parameters
XIN Peijin  REN Cui  QIN Siyuan  ZHAO Weili  LIU Ke  YAN Ruixin  WANG Qizheng  CHEN Yongye  LANG Ning 

Cite this article as: XIN P J, REN C, QIN S Y, et al. A nomogram model for diagnosing axial spondyloarthritis based on sacroiliac joint MRI radiomics features and clinical parameters[J]. Chin J Magn Reson Imaging, 2023, 14(11): 113-120. DOI:10.12015/issn.1674-8034.2023.11.019.


[Abstract] Objective To establish a joint nomogram model based on sacroiliac joint MRI radiomics features and clinical parameters to assist in the diagnosis of axial spondyloarthritis (axSpA).Materials and Methods A retrospective analysis was performed for a cohort of 204 patients suspected of having axSpA, who visited our institution from April 2019 to September 2021. One hundred and two of these patients were diagnosed with axSpA and 102 were healthy controls. Their clinical features were subjected to univariate and multivariate analysis, and features with statistically significance were utilized to construct a clinical signature using machine learning algorithms. Regions of interest were delineated from the sacroiliac joint MRI T1-weighted (T1WI) and fat-suppressed T2-weighted (FS-T2WI) sequences taken by these patients, and radiomics features were extracted from these sequences. Intraclass correlation coefficient, Pearson correlation coefficient, least absolute shrinkage and selection operator were used to select features with strong relevance, and five machine learning models (logistic regression, RandomForest, ExtraTrees, XGBoost, multivariate logistic regression) were used to construct radiomics signatures for judging sacroiliac joint changes. Finally, the clinical and radiomics signatures were integrated to establish a comprehensive nomogram model.Results The clinical signature was constructed using C-reactive protein and erythrocyte sedimentation rate. A total of 1834 radiomics features were extracted from each sequence of the sacroiliac joint MRI. After merging the features of different sequences, a total of 3368 features were obtained, from which the most relevant features were selected to construct radiomics signatures. For T1WI, FS-T2WI and fusion models, the best performing machine learning model was logistic regression. Radiomics signatures derived from fusion models displayed the best diagnostic performance. The final nomogram model exhibited excellent diagnostic performance in both the training set area under the curve (AUC) was 0.997 [95% confidence interval (CI): 0.992-1.000] and the testing set AUC was 0.944 (95% CI: 0.889-1.000). Decision curve also demonstrated that the nomogram model showed better predictive performance and clinical application value.Conclusions The nomogram model, incorporating sacroiliac joint MRI radiomics features and clinical parameters, demonstrates a strong capability to differentiate axSpA patients from healthy controls, which might facilitate clinical decision-making process.
[Keywords] axial spondyloarthritis；magnetic resonance imaging；machine learning；nomograms；radiomics

XIN Peijin   REN Cui   QIN Siyuan   ZHAO Weili   LIU Ke   YAN Ruixin   WANG Qizheng   CHEN Yongye   LANG Ning*  

Department of Radiology, Peking University Third Hospital, Beijing 100191, China

Corresponding author: LANG N, E-mail: langning800129@126.com

Conflicts of interest   None.

ACKNOWLEDGMENTS National Natural Science Foundation of China (No. 81971578); Clinical Key Program of Peking University Third Hospital (No. BYSYZD2021018).
Received  2023-08-05
Accepted  2023-10-31
DOI: 10.12015/issn.1674-8034.2023.11.019
Cite this article as: XIN P J, REN C, QIN S Y, et al. A nomogram model for diagnosing axial spondyloarthritis based on sacroiliac joint MRI radiomics features and clinical parameters[J]. Chin J Magn Reson Imaging, 2023, 14(11): 113-120. DOI:10.12015/issn.1674-8034.2023.11.019.

[1]
RUDWALEIT M. Classification and epidemiology of spondyloarthritis[M]//HOCHBERG M C, SILMAN A J, SMOLEN J S, et al. Rheumatology (Sixth Edition), Philadelphia: Mosby, 2015: 941-945. DOI: 10.1016/B978-0-323-09138-1.00113-3.
[2]
REDEKER I, CALLHOFF J, HOFFMANN F, et al. Determinants of diagnostic delay in axial spondyloarthritis: an analysis based on linked claims and patient-reported survey data[J]. Rheumatology, 2019, 58(9): 1634-1638. DOI: 10.1093/rheumatology/kez090.
[3]
ROBINSON P C, VAN DER LINDEN S, KHAN M A, et al. Axial spondyloarthritis: concept, construct, classification and implications for therapy[J]. Nat Rev Rheumatol, 2021, 17(2): 109-118. DOI: 10.1038/s41584-020-00552-4.
[4]
LIN J. Interpretation of "china expert consensus on the application of imaging technology in spinal arthritis (2021 edition)"[J]. Mod Pract Med, 2021, 33(12): 1541-1543. DOI: 10.3969/j.issn.1671-0800.2021.12.001.
[5]
WINTER J D, HOOGE M D, VAN DE SANDE M, et al. Magnetic resonance imaging of the sacroiliac joints indicating sacroiliitis according to the assessment of SpondyloArthritis international society definition in healthy individuals, runners, and women with postpartum back pain[J]. Arthritis Rheumatol, 2018, 70(7): 1042-1048. DOI: 10.1002/art.40475.
[6]
BARALIAKOS X, RICHTER A, FELDMANN D, et al. Which factors are associated with bone marrow oedema suspicious of axial spondyloarthritis as detected by MRI in the sacroiliac joints and the spine in the general population?[J]. Ann Rheum Dis, 2021, 80(4): 469-474. DOI: 10.1136/annrheumdis-2020-218669.
[7]
WEBER U, JURIK A G, LAMBERT R G W, et al. Imaging in axial spondyloarthritis: what is relevant for diagnosis in daily practice?[J/OL]. Curr Rheumatol Rep, 2021, 23(8): 66 [2023-10-16]. https://link.springer.com/article/10.1007/s11926-021-01030-w. DOI: 10.1007/s11926-021-01030-w.
[8]
JIBRI Z, GAZEL U, SOLMAZ D, et al. Correspondence on 'MRI lesions in the sacroiliac joints of patients with spondyloarthritis: an update of definitions and validation by the ASAS MRI working group'[J/OL]. Ann Rheum Dis, 2023, 82(5): e121 [2023-10-16]. https://ard.bmj.com/content/82/5/e121.long. DOI: 10.1136/annrheumdis-2021-220008.
[9]
LAMBIN P, RIOS-VELAZQUEZ E, LEIJENAAR R, et al. Radiomics: extracting more information from medical images using advanced feature analysis[J]. Eur J Cancer, 2012, 48(4): 441-446. DOI: 10.1016/j.ejca.2011.11.036.
[10]
GILLIES R J, KINAHAN P E, HRICAK H. Radiomics: images are more than pictures, they are data[J]. Radiology, 2016, 278(2): 563-577. DOI: 10.1148/radiol.2015151169.
[11]
TENÓRIO A P M, FERREIRA-JUNIOR J R, DALTO V F, et al. Radiomic quantification for MRI assessment of sacroiliac joints of patients with spondyloarthritis[J]. J Digit Imaging, 2022, 35(1): 29-38. DOI: 10.1007/s10278-021-00559-7.
[12]
FALEIROS M C, NOGUEIRA-BARBOSA M H, DALTO V F, et al. Machine learning techniques for computer-aided classification of active inflammatory sacroiliitis in magnetic resonance imaging[J/OL]. Adv Rheumatol, 2020, 60(1): 25 [2023-10-16]. https://advancesinrheumatology.biomedcentral.com/articles/10.1186/s42358-020-00126-8. DOI: 10.1186/s42358-020-00126-8.
[13]
YUSHKEVICH P A, PIVEN J, HAZLETT H C, et al. User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability[J]. Neuroimage, 2006, 31(3): 1116-1128. DOI: 10.1016/j.neuroimage.2006.01.015.
[14]
VAN GRIETHUYSEN J J M, FEDOROV A, PARMAR C, et al. Computational radiomics system to decode the radiographic phenotype[J/OL]. Cancer Res, 2017, 77(21): e104-e107 [2023-10-16]. https://aacrjournals.org/cancerres/article/77/21/e104/662617/Computational-Radiomics-System-to-Decode-the. DOI: 10.1158/0008-5472.CAN-17-0339.
[15]
ZWANENBURG A, VALLIÈRES M, ABDALAH M A, et al. The image biomarker standardization initiative: standardized quantitative radiomics for high-throughput image-based phenotyping[J]. Radiology, 2020, 295(2): 328-338. DOI: 10.1148/radiol.2020191145.
[16]
JONES A, BRAY T J P, MANDL P, et al. Performance of magnetic resonance imaging in the diagnosis of axial spondyloarthritis: a systematic literature review[J]. Rheumatology, 2019, 58(11): 1955-1965. DOI: 10.1093/rheumatology/kez172.
[17]
BARNETT R, INGRAM T, SENGUPTA R. Axial spondyloarthritis 10 years on: still looking for the lost tribe[J]. Rheumatology, 2020, 59(Suppl4): iv25-iv37. DOI: 10.1093/rheumatology/keaa472.
[18]
BROWN M A, LI Z X, CAO K A L. Biomarker development for axial spondyloarthritis[J]. Nat Rev Rheumatol, 2020, 16(8): 448-463. DOI: 10.1038/s41584-020-0450-0.
[19]
RUDWALEIT M, VAN DER HEIJDE D, KHAN M A, et al. How to diagnose axial spondyloarthritis early[J]. Ann Rheum Dis, 2004, 63(5): 535-543. DOI: 10.1136/ard.2003.011247.
[20]
YE L S, MIAO S L, XIAO Q Q, et al. A predictive clinical-radiomics nomogram for diagnosing of axial spondyloarthritis using MRI and clinical risk factors[J]. Rheumatology, 2022, 61(4): 1440-1447. DOI: 10.1093/rheumatology/keab542.
[21]
REVEILLE J D. Biomarkers in axial spondyloarthritis and low back pain: a comprehensive review[J]. Clin Rheumatol, 2022, 41(3): 617-634. DOI: 10.1007/s10067-021-05968-1.
[22]
BRAUN J, SIEPER J. Fifty years after the discovery of the association of HLA B27 with ankylosing spondylitis[J/OL]. RMD Open, 2023, 9(3): e003102 [2023-10-16]. https://rmdopen.bmj.com/content/9/3/e003102. DOI: 10.1136/rmdopen-2023-003102.
[23]
DIEKHOFF T, LAMBERT R, HERMANN K G. MRI in axial spondyloarthritis: understanding an 'ASAS-positive MRI' and the ASAS classification criteria[J]. Skeletal Radiol, 2022, 51(9): 1721-1730. DOI: 10.1007/s00256-022-04018-4.
[24]
MAKSYMOWYCH W P, LAMBERT R G, ØSTERGAARD M, et al. MRI lesions in the sacroiliac joints of patients with spondyloarthritis: an update of definitions and validation by the ASAS MRI working group[J]. Ann Rheum Dis, 2019, 78(11): 1550-1558. DOI: 10.1136/annrheumdis-2019-215589.
[25]
HUANG F, ZHU J, WANG Y H, et al. Recommendations for diagnosis and treatment of ankylosing spondylitis[J]. Chin J Intern Med, 2022, 61(8): 893-900. DOI: 10.3760/cma.j.cn112138-20211226-00913.
[26]
SUDO-SZOPIŃSKA I, JURIK A G, ESHED I, et al. Recommendations of the ESSR arthritis subcommittee for the use of magnetic resonance imaging in musculoskeletal rheumatic diseases[J]. Semin Musculoskelet Radiol, 2015, 19(4): 396-411. DOI: 10.1055/s-0035-1564696.
[27]
HERMANN K G A, BRAUN J, FISCHER T, et al. Magnetic resonance tomography of sacroiliitis: anatomy, histological pathology, MR-morphology, and grading[J]. Radiologe, 2004, 44(3): 217-228. DOI: 10.1007/s00117-003-0992-6.
[28]
GREESE J, DIEKHOFF T, SIEPER J, et al. Detection of sacroiliitis by short-tau inversion recovery and T2-weighted turbo spin echo sequences: results from the SIMACT study[J]. J Rheumatol, 2019, 46(4): 376-383. DOI: 10.3899/jrheum.171425.
[29]
MAKSYMOWYCH W P. The role of imaging in the diagnosis and management of axial spondyloarthritis[J]. Nat Rev Rheumatol, 2019, 15(11): 657-672. DOI: 10.1038/s41584-019-0309-4.
[30]
WEBER U, LAMBERT R G, PEDERSEN S J, et al. Assessment of structural lesions in sacroiliac joints enhances diagnostic utility of magnetic resonance imaging in early spondylarthritis[J]. Arthritis Care Res, 2010, 62(12): 1763-1771. DOI: 10.1002/acr.20312.
[31]
CURTIS J R. The promise and perils of 'Big Data': focus on spondyloarthritis[J]. Curr Opin Rheumatol, 2019, 31(4): 355-361. DOI: 10.1097/BOR.000000000000061.
[32]
TENÓRIO A P M, FALEIROS M C, JUNIOR J R F, et al. A study of MRI-based radiomics biomarkers for sacroiliitis and spondyloarthritis[J]. Int J Comput Assist Radiol Surg, 2020, 15(10): 1737-1748. DOI: 10.1007/s11548-020-02219-7.
[33]
KEPP F H, HUBER F A, WURNIG M C, et al. Differentiation of inflammatory from degenerative changes in the sacroiliac joints by machine learning supported texture analysis[J/OL]. Eur J Radiol, 2021, 140 [2023-10-16]. https://www.sciencedirect.com/science/article/pii/S0720048X21002369:109755. DOI: 10.1016/j.ejrad.2021.109755.
[34]
YU S, SU J W, LIN M G, et al. A preliminary study on the efficacy of tumor necrosis factor alpha antagonists in the treatment of axial spondyloarthropathy by T1-mapping technique[J]. Chin J Magn Reson Imag, 2022, 13(1): 21-25, 36. DOI: 10.12015/issn.1674-8034.2022.01.005.
[35]
LIU D, LIN C R, LIU B D, et al. Quantification of fat Metaplasia in the sacroiliac joints of patients with axial spondyloarthritis by chemical shift-encoded MRI: a diagnostic trial[J/OL]. Front Immunol, 2021, 12: 811672 [2023-10-16]. https://www.frontiersin.org/articles/10.3389/fimmu.2021.811672/full. DOI: 10.3389/fimmu.2021.811672.
[36]
KUCYBAŁA I, TABOR Z, POLAK J, et al. The semi-automated algorithm for the detection of bone marrow oedema lesions in patients with axial spondyloarthritis[J]. Rheumatol Int, 2020, 40(4): 625-633. DOI: 10.1007/s00296-020-04511-w.

PREV Analysis of the use of MRI and CT in the diagnosis of SAPHO syndrome
NEXT Diagnosis of osteoporosis by radiomics on T2WI sequence of lumbar magnetic resonance imaging
  


LINK


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