Follow-up MRI in multiple sclerosis patients: automated co-registration and lesion color-coding improves diagnostic accuracy and reduces reading time

  • David ZopfsEmail author
  • Kai R. Laukamp
  • Stefanie Paquet
  • Simon Lennartz
  • Daniel Pinto dos Santos
  • Christoph Kabbasch
  • Alexander Bunck
  • Marc Schlamann
  • Jan Borggrefe



In multiple sclerosis (MS), the heterogeneous and numerous appearances of lesions may impair diagnostic accuracy. This study investigates if a combined automated co-registration and lesion color-coding method (AC) improves assessment of MS follow-up MRI compared with conventional reading (CR).


We retrospectively assessed 70 follow-up MRI of 53 patients. Heterogeneous datasets of diverse scanners and institutions were used. Two readers determined presence of (a) progression, (b) regression, (c) mixed change, or (d) stable disease between the two examinations using corresponding FLAIR sequences in CR and AC-assisted reading. Consensus reference reading was provided by two blinded radiologists. Kappa statistics tested interrater agreement, McNemar’s test dichotomous variables, and Wilcoxon’s test continuous variables (statistical significance p ≤ 0.05).


The cohort comprised 41 female and 12 male patients with a mean age of 40 (± 14) years. Average rating time was reduced from 78 (± 36) to 44 (±22) s with the AC approach (p < 0.001). The time needed to start and match datasets with AC was 14 (± 1) s. Compared with CR, AC improved interrater agreement, both between raters (0.52 vs. 0.67) and between raters and consensus reference reading (0.47/0.5 vs. 0.83/0.78). Compared with CR, the diagnostic accuracy increased from 67 to 90% (reader 1, p < 0.01) and from 70 to 87% (reader 2, p < 0.05) in the AC-assisted reading.


Compared with CR, automated co-registration and lesion color-coding of MS-associated FLAIR-lesions in follow-up MRI increased diagnostic accuracy and reduced the time required for follow-up evaluation significantly. The AC algorithm therefore appears to be helpful to improve MS follow-up assessments in clinical routine.

Key Points

Automated co-registration and lesion color-coding increases diagnostic accuracy in the assessment of MRI follow-up examinations in patients with multiple sclerosis.

Automated co-registration and lesion color-coding reduces reading time of MRI follow-up examinations in patients with multiple sclerosis.

Automated co-registration and lesion color-coding improved interrater agreement in the assessment of MRI follow-up examinations in patients with multiple sclerosis.


Multiple sclerosis Magnetic resonance imaging Disease progression Brain Image processing, computer-assisted 



Automated co-registration and lesion color-coding image reading approach


Conventional reading


Fluid-attenuated inversion recovery


Magnetic resonance imaging


Multiple sclerosis


Picture archiving and communication system


Radiological information system


Standard deviation.



The authors state that this work has not received any funding.

Compliance with ethical standards


The scientific guarantor of this publication is Jan Borggrefe.

Conflict of interest

The authors of this manuscript declare relationships with the following companies:

Jan Borggrefe received speaker honoraria from Philips.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.


• Retrospective

• Diagnostic or prognostic study

• Performed at one institution


  1. 1.
    Karussis D (2014) The diagnosis of multiple sclerosis and the various related demyelinating syndromes: a critical review. J Autoimmun 48-49:134–142CrossRefGoogle Scholar
  2. 2.
    Ramagopalan SV, Sadovnick AD (2011) Epidemiology of multiple sclerosis. Neurol Clin 29(2):207–217CrossRefGoogle Scholar
  3. 3.
    Dilokthornsakul P, Valuck RJ, Nair KV, Corboy JR, Allen RR, Campbell JD (2016) Multiple sclerosis prevalence in the United States commercially insured population. Neurology 86(11):1014–1021CrossRefGoogle Scholar
  4. 4.
    Simpson S Jr, Blizzard L, Otahal P, van der Mei I, Taylor B (2011) Latitude is significantly associated with the prevalence of multiple sclerosis: a meta-analysis. J Neurol Neurosurg Psychiatry 82(10):1132–1141Google Scholar
  5. 5.
    Danelakis A, Theoharis T, Verganelakis DA (2018) Survey of automated multiple sclerosis lesion segmentation techniques on magnetic resonance imaging. Comput Med Imaging Graph 70:83–100CrossRefGoogle Scholar
  6. 6.
    Gramsch C, Nensa F, Kastrup O et al (2015) Diagnostic value of 3D fluid attenuated inversion recovery sequence in multiple sclerosis. Acta Radiol 56(5):622–627CrossRefGoogle Scholar
  7. 7.
    Thompson AJ, Banwell BL, Barkhof F et al (2018) Diagnosis of multiple sclerosis: 2017 revisions of the McDonald criteria. Lancet Neurol 17(2):162–173CrossRefGoogle Scholar
  8. 8.
    Katz Sand IB, Lublin FD (2013) Diagnosis and differential diagnosis of multiple sclerosis. Continuum (Minneap Minn) 19(4 Multiple Sclerosis):922–943Google Scholar
  9. 9.
    Battaglini M, Rossi F, Grove RA et al (2014) Automated identification of brain new lesions in multiple sclerosis using subtraction images. J Magn Reson Imaging 39(6):1543–1549CrossRefGoogle Scholar
  10. 10.
    Patel N, Horsfield MA, Banahan C et al (2017) Detection of focal longitudinal changes in the brain by subtraction of MR images. AJNR Am J Neuroradiol 38(5):923–927CrossRefGoogle Scholar
  11. 11.
    Galletto Pregliasco A, Collin A, Guéguen A et al (2018) Improved detection of new MS lesions during follow-up using an automated MR coregistration-fusion method. AJNR Am J Neuroradiol 39(7):1226–1232CrossRefGoogle Scholar
  12. 12.
    Sweeney EM, Shinohara RT, Shea CD, Reich DS, Crainiceanu CM (2013) Automatic lesion incidence estimation and detection in multiple sclerosis using multisequence longitudinal MRI. AJNR Am J Neuroradiol 34(1):68–73CrossRefGoogle Scholar
  13. 13.
    Roura E, Oliver A, Cabezas M et al (2015) A toolbox for multiple sclerosis lesion segmentation. Neuroradiology 57(10):1031–1043CrossRefGoogle Scholar
  14. 14.
    García-Lorenzo D, Francis S, Narayanan S, Arnold DL, Collins DL (2013) Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging. Med Image Anal 17(1):1–18CrossRefGoogle Scholar
  15. 15.
    Horsfield MA, Rocca MA, Pagani E et al (2016) Estimating brain lesion volume change in multiple sclerosis by subtraction of magnetic resonance images. J Neuroimaging 26(4):395–402CrossRefGoogle Scholar
  16. 16.
    Cabezas M, Corral JF, Oliver A et al (2016) Improved automatic detection of new T2 lesions in multiple sclerosis using deformation fields. AJNR Am J Neuroradiol.
  17. 17.
    Jain S, Sima DM, Ribbens A et al (2015) Automatic segmentation and volumetry of multiple sclerosis brain lesions from MR images. Neuroimage Clin 8:367–375CrossRefGoogle Scholar
  18. 18.
    Tan IL, van Schijndel RA, Fazekas F et al (2002) Image registration and subtraction to detect active T(2) lesions in MS: an interobserver study. J Neurol 249(6):767–773CrossRefGoogle Scholar
  19. 19.
    Ganiler O, Oliver A, Diez Y et al (2014) A subtraction pipeline for automatic detection of new appearing multiple sclerosis lesions in longitudinal studies. Neuroradiology 56(5):363–374CrossRefGoogle Scholar
  20. 20.
    Laukamp KR, Thiele F, Shakirin G et al (2018) Fully automated detection and segmentation of meningiomas using deep learning on routine multiparametric MRI. Eur Radiol.
  21. 21.
    Salem M, Cabezas M, Valverde S et al (2018) A supervised framework with intensity subtraction and deformation field features for the detection of new T2-w lesions in multiple sclerosis. Neuroimage Clin 17:607–615CrossRefGoogle Scholar
  22. 22.
    Nguyen TD, Zhang S, Gupta A, Zhao Y, Gauthier SA, Wang Y (2018) Fast and robust unsupervised identification of MS lesion change using the statistical detection of changes algorithm. AJNR Am J Neuroradiol 39(5):830–833CrossRefGoogle Scholar
  23. 23.
    van Heerden J, Rawlinson D, Zhang AM et al (2015) Improving multiple sclerosis plaque detection using a semiautomated assistive approach. AJNR Am J Neuroradiol 36(8):1465–1471CrossRefGoogle Scholar
  24. 24.
    Castellino RA (2005) Computer aided detection (CAD): an overview. Cancer Imaging 5:17–19CrossRefGoogle Scholar
  25. 25.
    Bilello M, Arkuszewski M, Nasrallah I, Wu X, Erus G, Krejza J (2012) Multiple sclerosis lesions in the brain: computer-assisted assessment of lesion load dynamics on 3D FLAIR MR images. Neuroradiol J 25(1):17–21CrossRefGoogle Scholar
  26. 26.
    Krauss W, Gunnarsson M, Nilsson M, Thunberg P (2017) Conventional and synthetic MRI in multiple sclerosis: a comparative study. Eur Radiol 28(4):1692–1700CrossRefGoogle Scholar
  27. 27.
    Wang W, van Heerden J, Tacey MA, Gaillard F (2017) Neuroradiologists compared with non-neuroradiologists in the detection of new multiple sclerosis plaques. AJNR Am J Neuroradiol 38(7):1323–1327CrossRefGoogle Scholar
  28. 28.
    Chokshi FH, Hughes DR, Wang JM, Mullins ME, Hawkins CM, Duszak R Jr (2015) Diagnostic radiology resident and fellow workloads: a 12-year longitudinal trend analysis using national Medicare aggregate claims data. J Am Coll Radiol 12(7):664–669Google Scholar

Copyright information

© European Society of Radiology 2019

Authors and Affiliations

  • David Zopfs
    • 1
    Email author
  • Kai R. Laukamp
    • 1
    • 2
    • 3
  • Stefanie Paquet
    • 1
  • Simon Lennartz
    • 1
  • Daniel Pinto dos Santos
    • 1
  • Christoph Kabbasch
    • 1
  • Alexander Bunck
    • 1
  • Marc Schlamann
    • 1
  • Jan Borggrefe
    • 1
  1. 1.Faculty of Medicine and University Hospital Cologne, Institute for Diagnostic and Interventional RadiologyUniversity of CologneCologneGermany
  2. 2.Department of RadiologyUniversity Hospitals Cleveland Medical CenterClevelandUSA
  3. 3.Department of RadiologyCase Western Reserve UniversityClevelandUSA

Personalised recommendations