Advertisement

Radiomics in multiple sclerosis and neuromyelitis optica spectrum disorder

  • Yaou LiuEmail author
  • Di Dong
  • Liwen Zhang
  • Yali Zang
  • Yunyun Duan
  • Xiaolu Qiu
  • Jing Huang
  • Huiqing Dong
  • Frederik Barkhof
  • Chaoen Hu
  • Mengjie Fang
  • Jie TianEmail author
  • Kuncheng Li
Magnetic Resonance
  • 220 Downloads

Abstract

Objective

To develop and validate an individual radiomics nomogram for differential diagnosis between multiple sclerosis (MS) and neuromyelitis optica spectrum disorder (NMOSD).

Methods

We retrospectively collected 67 MS and 68 NMOSD with spinal cord lesions as a primary cohort and prospectively recruited 28 MS and 26 NMOSD patients as a validation cohort. Radiomic features were extracted from the spinal cord lesions. A prediction model for differentiating MS and NMOSD was built by combining the radiomic features with several clinical and routine MRI measurements. The performance of the model was assessed with respect to its calibration plot and clinical discrimination in the primary and validation cohorts.

Results

Nine radiomics features extracted from an initial set of 485, predominantly reflecting lesion heterogeneity, combined with lesion length, patient sex, and EDSS, were selected to build the model for differentiating MS and NMOSD. The areas under the ROC curves (AUC) for differentiating the two diseases were 0.8808 and 0.7115, for the primary and validation cohort, respectively. This model demonstrated good calibration (C-index was 0.906 and 0.802 in primary and validation cohort).

Conclusions

A validated nomogram that incorporates the radiomic signature of spinal cord lesions, as well as cord lesion length, sex, and EDSS score, can usefully differentiate MS and NMOSD.

Key Points

• Radiomic features of spinal cord lesions in MS and NMOSD were different.

• Radiomic signatures can capture pathological alterations and help differentiate MS and NMOSD.

Keywords

Multiple sclerosis Neuromyelitis optica spectrum disorder Radiomics Nomogram Magnetic resonance imaging 

Abbreviations

AUC

Areas under the ROC curves

EDSS

Expanded disability status scale

LASSO

Least absolute shrinkage and selection operator

LETM

Longitudinal extensive transverse myelitis

MS

Multiple sclerosis

NMOSD

Neuromyelitis optica spectrum disorder

ROC

Receiver operating characteristic

ROI

Region of interest

RRMS

Relapsing-remitting MS

Notes

Acknowledgements

We thank our patients in this study and members of the neuroimmunology team and staffs of the department of radiology for various supports.

Funding

This work was supported by the ECTRIMS-MAGNMIS Fellowship from ECTRIMS (Y.L), the National Science Foundation of China (Nos. 81101038, 81227901, 81771924, 81501736, 61231004, 81401377, 81471221 and 81230028), the National Basic Research Program of China (2013CB966900), National Key R&D Program of China (2017YFA0205200, 2017YFC1308700, 2017YFC1308701), the Beijing Natural Science fund (No.7133244), the Beijing Nova Programme (xx2013045), Beijing Municipal Administration of Hospital Clinical Medicine Development of Special Funding Support (code:ZYLX201609), the Science and Technology Service Network Initiative of the Chinese Academy of Sciences (KFJ-SW-STS-160), and Key Projects in the National Science & Technology Pillar Program during the Twelfth Five-year Plan Period (2012BAI10B04).

Compliance with ethical standards

Guarantor

The scientific guarantor of this publication is Yaou Liu.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was obtained from all subjects (patients) in this study.

Ethical approval

Institutional Review Board approval was obtained.

Methodology

• retrospective

• diagnostic or prognostic study

• performed at one institution

Supplementary material

330_2019_6026_MOESM1_ESM.doc (1.3 mb)
ESM 1 (DOC 1333 kb)

References

  1. 1.
    Noseworthy JH, Lucchinetti C, Rodriguez M, Weinshenker BG (2000) Multiple sclerosis. N Engl J Med 343:938–952CrossRefGoogle Scholar
  2. 2.
    Wingerchuk DM, Lennon VA, Lucchinetti CF, Pittock SJ, Weinshenker BG (2007) The spectrum of neuromyelitis optica. Lancet Neurol 6:805–815CrossRefGoogle Scholar
  3. 3.
    Palace J, Leite MI, Nairne A, Vincent A (2010) Interferon Beta treatment in neuromyelitis optica: increase in relapses and aquaporin 4 antibody titers. Arch Neurol 67:1016–1017CrossRefGoogle Scholar
  4. 4.
    Shimizu J, Hatanaka Y, Hasegawa M et al (2010) IFNbeta-1b may severely exacerbate Japanese optic-spinal MS in neuromyelitis optica spectrum. Neurology 75:1423–1427CrossRefGoogle Scholar
  5. 5.
    Thompson AJ, Banwell BL, Barkhof F et al (2017) Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. Lancet Neurol 17:162–173Google Scholar
  6. 6.
    Wingerchuk DM, Banwell B, Bennett JL et al (2015) International consensus diagnostic criteria for neuromyelitis optica spectrum disorders. Neurology 85:177–189CrossRefPubMedCentralGoogle Scholar
  7. 7.
    Min JH, Kim BJ, Lee KH (2012) Development of extensive brain lesions following fingolimod (FTY720) treatment in a patient with neuromyelitis optica spectrum disorder. Mult Scler 18:113–115CrossRefGoogle Scholar
  8. 8.
    Jarius S, Ruprecht K, Wildemann B et al (2012) Contrasting disease patterns in seropositive and seronegative neuromyelitis optica: a multicentre study of 175 patients. J Neuroinflammation 9:14CrossRefPubMedCentralGoogle Scholar
  9. 9.
    Gass A, Rocca MA, Agosta F et al (2015) MRI monitoring of pathological changes in the spinal cord in patients with multiple sclerosis. Lancet Neurol 14:443–454CrossRefGoogle Scholar
  10. 10.
    Lambin P, Rios-Velazquez E, Leijenaar R et al (2012) Radiomics: extracting more information from medical images using advanced feature analysis. Eur J Cancer 48:441–446CrossRefPubMedCentralGoogle Scholar
  11. 11.
    Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: images are more than pictures, they are data. Radiology 278:563–577CrossRefGoogle Scholar
  12. 12.
    Iasonos A, Schrag D, Raj GV, Panageas KS (2008) How to build and interpret a nomogram for cancer prognosis. J Clin Oncol 26:1364–1370CrossRefGoogle Scholar
  13. 13.
    Polman CH, Reingold SC, Banwell B et al (2011) Diagnostic criteria for multiple sclerosis: 2010 revisions to the McDonald criteria. Ann Neurol 69:292–302CrossRefPubMedCentralGoogle Scholar
  14. 14.
    Aerts HJ, Velazquez ER, Leijenaar RT et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 5:4006CrossRefPubMedCentralGoogle Scholar
  15. 15.
    Tibshirani R (1996) Regression shrinkage and selection via the lasso. J R Stat Soc Series B Stat Methodol 58:267–288Google Scholar
  16. 16.
    Lukas C, Knol DL, Sombekke MH et al (2015) Cervical spinal cord volume loss is related to clinical disability progression in multiple sclerosis. J Neurol Neurosurg Psychiatry 86:410–418CrossRefGoogle Scholar
  17. 17.
    Liu Y, Wang J, Daams M et al (2015) Differential patterns of spinal cord and brain atrophy in NMO and MS. Neurology 84:1465–1472CrossRefGoogle Scholar
  18. 18.
    Fan M, Fu Y, Su L et al (2017) Comparison of brain and spinal cord magnetic resonance imaging features in neuromyelitis optica spectrum disorders patients with or without aquaporin-4 antibody. Mult Scler Relat Disord 13:58–66CrossRefGoogle Scholar
  19. 19.
    Kumar V, Gu Y, Basu S et al (2012) Radiomics: the process and the challenges. Magn Reson Imaging 30:1234–1248CrossRefPubMedCentralGoogle Scholar
  20. 20.
    Zhang Y, Moore GR, Laule C et al (2013) Pathological correlates of magnetic resonance imaging texture heterogeneity in multiple sclerosis. Ann Neurol 74:91–99CrossRefGoogle Scholar
  21. 21.
    Kawachi I, Lassmann H (2017) Neurodegeneration in multiple sclerosis and neuromyelitis optica. J Neurol Neurosurg Psychiatry 88:137–145CrossRefGoogle Scholar
  22. 22.
    Filippi M, Rocca MA, Barkhof F et al (2012) Association between pathological and MRI findings in multiple sclerosis. Lancet Neurol 11:349–360CrossRefGoogle Scholar
  23. 23.
    Wang Y, Li J, Xia Y et al (2013) Prognostic nomogram for intrahepatic cholangiocarcinoma after partial hepatectomy. J Clin Oncol 31:1188–1195CrossRefGoogle Scholar
  24. 24.
    Spelman T, Meyniel C, Rojas JI et al (2017) Quantifying risk of early relapse in patients with first demyelinating events: prediction in clinical practice. Mult Scler 23:1346–1357CrossRefGoogle Scholar
  25. 25.
    Schoonheim MM, Vigeveno RM, Rueda Lopes FC et al (2014) Sex-specific extent and severity of white matter damage in multiple sclerosis: implications for cognitive decline. Hum Brain Mapp 35:2348–2358CrossRefGoogle Scholar
  26. 26.
    Borisow N, Kleiter I, Gahlen A et al (2017) Influence of female sex and fertile age on neuromyelitis optica spectrum disorders. Mult Scler 23:1092–1103CrossRefGoogle Scholar
  27. 27.
    Huang YQ, Liang CH, He L et al (2016) Development and validation of a radiomics nomogram for preoperative prediction of lymph node metastasis in colorectal cancer. J Clin Oncol 34(18):2157–2164Google Scholar
  28. 28.
    Zhang B, Tian J, Dong D et al (2017) Radiomics features of multiparametric MRI as novel prognostic factors in advanced nasopharyngeal carcinoma. Clin Cancer Res 23:4259–4269Google Scholar
  29. 29.
    Yip SS, Aerts HJ (2016) Applications and limitations of radiomics. Phys Med Biol 61:R150–R166CrossRefPubMedCentralGoogle Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  • Yaou Liu
    • 1
    • 2
    • 3
    • 4
    Email author
  • Di Dong
    • 5
    • 6
  • Liwen Zhang
    • 5
    • 6
  • Yali Zang
    • 5
    • 6
  • Yunyun Duan
    • 1
    • 2
  • Xiaolu Qiu
    • 4
  • Jing Huang
    • 4
  • Huiqing Dong
    • 7
  • Frederik Barkhof
    • 3
    • 8
  • Chaoen Hu
    • 5
    • 6
  • Mengjie Fang
    • 5
    • 6
  • Jie Tian
    • 5
    • 6
    Email author
  • Kuncheng Li
    • 1
    • 4
  1. 1.Department of Radiology, Beijing Tiantan HospitalCapital Medical UniversityBeijingPeople’s Republic of China
  2. 2.Tiantan Image Research CenterChina National Clinical Research Center for Neurological DiseasesBeijingPeople’s Republic of China
  3. 3.Department of Radiology and Nuclear Medicine, Neuroscience Campus AmsterdamVU University Medical CenterAmsterdamThe Netherlands
  4. 4.Department of Radiology, Xuanwu HospitalCapital Medical UniversityBeijingPeople’s Republic of China
  5. 5.CAS Key Laboratory of Molecular Imaging, Institute of AutomationChinese Academy of SciencesBeijingChina
  6. 6.University of Chinese Academy of SciencesBeijingChina
  7. 7.Department of Neurology, Xuanwu HospitalCapital Medical UniversityBeijingPeople’s Republic of China
  8. 8.Institutes of Neurology and Healthcare Engineering, UCLLondonUK

Personalised recommendations