Skip to main content
SpringerLink
Log in

Prognosis of a second clinical event from baseline MRI in patients with a CIS: a multicenter study using a machine learning approach

  • Diagnostic Neuroradiology
  • Published:
Neuroradiology Aims and scope Submit manuscript

Abstract

Purpose

To predict the occurrence of a second clinical event in patients with a CIS suggestive of MS, from baseline magnetic resonance imaging (MRI), by means of a pattern recognition approach.

Methods

Two hundred sixty-six patients with a CIS were recruited from four participating centers. Over a follow-up of 3 years, 130 patients had a second clinical episode and 136 did not. Grey matter and white matter T1-hypointensities masks segmented from 3D T1-weighted images acquired on 3 T scanners were used as features for the classification approach. Differences between CIS that remained CIS and those that developed a second event were assessed at a global level and at a regional level, arranging the regions according to their contribution to the classification model.

Results

All classification metrics were around or even below 50% for both global and regional approaches. Accuracies did not change when T1-hypointensity maps were added to the model; just the specificity was increased up to 80%. Among the 30 regions with the largest contribution, 26 were grey matter and 4 were white matter regions. For grey matter, regions contributing showed either a larger or a smaller volume in the group of patients that remained CIS, compared to those with a second event. The volume of T1-hypointensities was always larger for the group that presented a second event.

Conclusions

Prediction of a second clinical event in CIS patients from baseline MRI seems to present a highly heterogeneous pattern, leading to very low classification accuracies. Adding the T1-hypointensity maps does not seem to improve the accuracy of the classification model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1

We’re sorry, something doesn't seem to be working properly.

Please try refreshing the page. If that doesn't work, please contact support so we can address the problem.

References

  1. Miller DH, Chard DT, Ciccarelli O (2012) Clinically isolated syndromes. Lancet Neurol 11(2):157–169

    Article  Google Scholar 

  2. Lassmann H (2008) The pathologic substrate of magnetic resonance alterations in multiple sclerosis. Neuroimaging Clin N Am 18(4):563–576

    Article  Google Scholar 

  3. Filippi M, Preziosa P, Banwell BL et al (2019) Assessment of lesions on magnetic resonance imaging in multiple sclerosis: practical guidelines. Brain 142(7):1858–1875

    Article  Google Scholar 

  4. Sastre-Garriga J, Pareto D, Battaglini M et al (2020) MAGNIMS consensus recommendations on the use of brain and spinal cord atrophy measures in clinical practice. Nat Rev Neurol 16(3):171–182

    Article  Google Scholar 

  5. Kuhle J, Disanto G, Dobson R et al (2015) Conversion from clinically isolated syndrome to multiple sclerosis: a large multicentre study. Mult Scler 21(8):1013–1024

    Article  CAS  Google Scholar 

  6. Tintoré M, Rovira A, Río J et al (2006) Baseline MRI predicts future attacks and disability in clinically isolated syndromes. Neurology 67(6):968–972

    Article  Google Scholar 

  7. Zhang H, Alberts E, Pongratz V et al (2018) Predicting conversion from clinically isolated syndrome to multiple sclerosis-an imaging-based machine learning approach. Neuroimage Clin S2213–1582(18):30341–30343

    Google Scholar 

  8. Wottschel V, Alexander DC, Kwok PP et al (2014) Predicting outcome in clinically isolated syndrome using machine learning. Neuroimage Clin 7:281–287

    Article  Google Scholar 

  9. Wottschel V, Chard DT, Enzinger C et al (2019) SVM recursive feature elimination analyses of structural brain MRI predicts near-term relapses in patients with clinically isolated syndromes suggestive of multiple sclerosis. Neuroimage Clin. 24:102011

    Article  Google Scholar 

  10. Bendfeldt K, Taschler B, Gaetano L et al (2019) MRI-based prediction of conversion from clinically isolated syndrome to clinically definite multiple sclerosis using SVM and lesion geometry. Brain Imaging Behav 13(5):1361–2137

    Article  Google Scholar 

  11. Schrouff J, Rosa MJ, Rondina JM et al (2013) PRoNTo: pattern recognition for neuroimaging toolbox. Neuroinformatics 11(3):319–337

    Article  CAS  Google Scholar 

  12. Schrouff J, Monteiro JM, Portugal L et al (2018) Embedding anatomical or functional knowledge in whole-brain multiple kernel learning models. Neuroinformatics 16(1):117–143

    Article  Google Scholar 

  13. Tzourio-Mazoyer N, Landeau B, Papathanassiou D et al (2002) Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. Neuroimage 15(1):273–289

    Article  CAS  Google Scholar 

  14. Mori S, Oishi K, Jiang H et al (2008) Stereotaxic white matter atlas based on diffusion tensor imaging in an ICBM template. Neuroimage 40(2):570–582

    Article  Google Scholar 

  15. Henry RG, Shieh M, Okuda DT et al (2008) Regional grey matter atrophy in clinically isolated syndromes at presentation. J Neurol Neurosurg Psychiatry 79(11):1236–1244

    Article  CAS  Google Scholar 

  16. Pérez-Miralles F, Sastre-Garriga J, Tintoré M et al (2013) Clinical impact of early brain atrophy in clinically isolated syndromes. Mult Scler 19(14):1878–1886

    Article  Google Scholar 

  17. Audoin B, Zaaraoui W, Reuter F et al (2010) Atrophy mainly affects the limbic system and the deep grey matter at the first stage of multiple sclerosis. J Neurol Neurosurg Psychiatry 81(6):690–695

    Article  Google Scholar 

  18. Pareto D, Sastre-Garriga J, Alberich M et al (2019) Brain regional volume estimations with NeuroQuant and FIRST: a study in patients with a clinically isolated syndrome. Neuroradiology 61(6):667–767

    Article  Google Scholar 

Download references

Acknowledgements

We thank C. Cavallo for English writing support.

Funding

We would like to acknowledge funding received from the “Red Española de Esclerosis Múltiple (REEM)” (RD07/0060; RD12/0032) and the project, PI18/00823, which are sponsored by the Fondo de Investigación Sanitaria (FIS), the Instituto de Salud Carlos III and the Ministry of Economy and Competitiveness in Spain, as well as the “Ajuts per Donar Suport als Grups de Recerca de Catalunya (2009 SGR 0793)”, which is sponsored by the “Agència de Gestió d’Ajuts Universitaris i de Recerca” (AGAUR) of the Generalitat de Catalunya in Spain.

Instituto de Salud Carlos III,PI18/00823,Deborah Pareto

Author information

Authors and Affiliations

  1. Department of Radiology (IDI), Neuroradiology Section, Hospital Universitari Vall d’Hebron and Institut de Recerca (VHIR), Universitat Autònoma de Barcelona, Barcelona, Spain

    Deborah Pareto, Aran Garcia-Vidal & Àlex Rovira

  2. Department of Neurology, University Medical Center of the Johannes Gutenberg University Mainz, Mainz, Germany

    Sergiu Groppa & Gabriel Gonzalez-Escamilla

  3. Neuroimaging Research Unit, Institute of Experimental Neurology, Division of Neuroscience, IRCCS San Raffaele Scientific Institute, Milan, Italy

    Mara Rocca & Massimo Filippi

  4. Neurology Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy

    Mara Rocca & Massimo Filippi

  5. Neurophysiology Unit, IRCCS San Raffaele Scientific Institute, Milan, Italy

    Massimo Filippi

  6. Vita-Salute San Raffaele University, Milan, Italy

    Massimo Filippi

  7. Department of Neurology, Medical University of Graz, Graz, Austria

    Christian Enzinger & Michael Khalil

  8. Center of Neuroimmunology, Advanced Imaging in Neuroimmunological Diseases (ImaginEM) Group, Hospital Clinic, IDIBAPS and Universitat de Barcelona, Barcelona, Spain

    Sara Llufriu

  9. Department of Neurology/Neuroimmunology, Multiple Sclerosis Center of Catalonia (Cemcat), Hospital Universitari Vall d’Hebron, Universitat Autònoma de Barcelona, Barcelona, Spain

    Mar Tintoré & Jaume Sastre-Garriga

Authors
  1. Deborah Pareto
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Aran Garcia-Vidal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Sergiu Groppa
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gabriel Gonzalez-Escamilla
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mara Rocca
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Massimo Filippi
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Christian Enzinger
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Michael Khalil
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Sara Llufriu
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Mar Tintoré
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Jaume Sastre-Garriga
    View author publications

    You can also search for this author in PubMed Google Scholar

  12. Àlex Rovira
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Deborah Pareto.

Ethics declarations

Ethics approval

The study was approved by the local ethics committee, under the standards of the 1964 Declaration of Helsinki.

Consent to participate

All patients signed an informed consent for participation.

Conflict of interest

DP has received speaking honoraria from Novartis and Sanofi-Genzyme and a research contract from Biogen.

AG-V has nothing to disclose.

SG has nothing to disclose.

GG-E has nothing to disclose.

MR received speaker honoraria from Biogen Idec, Novartis, Genzyme, Teva, Merck Serono, Roche, Celgene and Bayer and receives research support from the Italian Ministry of Health, MS Society of Canada and Fondazione Italiana Sclerosi Multipla.

MF: Editor-in-Chief of the Journal of Neurology received compensation for consulting services and/or speaking activities from Bayer, Biogen Idec, Merck-Serono, Novartis, Roche, Sanofi Genzyme, Takeda, and Teva Pharmaceutical Industries; and receives research support from Biogen Idec, Merck-Serono, Novartis, Roche, Teva Pharmaceutical Industries, Italian Ministry of Health, Fondazione Italiana Sclerosi Multipla, and ARiSLA (Fondazione Italiana di Ricerca per la SLA).

MK has received funding for travel and speaker honoraria from Bayer Schering Pharma, Novartis Genzyme, Merck Serono, Biogen Idec and Teva Pharmaceutical Industries Ltd. and serves on scientific advisory boards for Biogen Idec, Merck Serono and Roche.

CH received funding for travel and speaker honoraria from Bayer, Biogen, Genzyme, Merck, Novartis, Roche, Shire, and Teva Pharmaceutical Industries Ltd./sanofi-aventis, research support from Biogen, Merck, and Teva Pharmaceutical Industries Ltd./sanofi-aventis and serving on scientific advisory boards for Bayer, Biogen, Merck, Novartis, Roche and Teva Pharmaceutical Industries Ltd./sanofi- Aventis.

SL received compensation for consulting services and speaker honoraria from Biogen Idec, Novartis, TEVA, Genzyme, Sanofi, Roche, and Merck.

MT has received speaking honoraria and travel expenses for scientific meetings with Amirall, Bayer, Biogen Idec, Genzyme, Merck Serono, Novartis, Sanofi-Aventis, Roche, and Teva.

JSG is Director of Revista de Neurología and serves on the Editorial Board of MSJ. In the last 36 months he has received compensation for serving on scientific advisory boards or on speaker’s bureaus from Biogen, Merck, Almirall, Novartis, Teva, Roche, Celgene, and Genzyme.

ÀR has served on scientific advisory boards for Novartis, Sanofi-Genzyme, Icometrix, Bayer SyntheticMR, and OLEA Medical and has received speaking honoraria from Bayer, Sanofi-Genzyme, Bracco, Merck-Serono, Teva Pharmaceutical Industries Ltd, Novartis, Roche, and Biogen Idec.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

ESM 1

(DOCX 42.9 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Pareto, D., Garcia-Vidal, A., Groppa, S. et al. Prognosis of a second clinical event from baseline MRI in patients with a CIS: a multicenter study using a machine learning approach. Neuroradiology 64, 1383–1390 (2022). https://doi.org/10.1007/s00234-021-02885-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00234-021-02885-7

Keywords

Search

Navigation