Shallow vs Deep Learning Architectures for White Matter Lesion Segmentation in the Early Stages of Multiple Sclerosis

  • Francesco La RosaEmail author
  • Mário João Fartaria
  • Tobias Kober
  • Jonas Richiardi
  • Cristina Granziera
  • Jean-Philippe Thiran
  • Meritxell Bach Cuadra
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11383)


In this work, we present a comparison of a shallow and a deep learning architecture for the automated segmentation of white matter lesions in MR images of multiple sclerosis patients. In particular, we train and test both methods on early stage disease patients, to verify their performance in challenging conditions, more similar to a clinical setting than what is typically provided in multiple sclerosis segmentation challenges. Furthermore, we evaluate a prototype naive combination of the two methods, which refines the final segmentation. All methods were trained on 32 patients, and the evaluation was performed on a pure test set of 73 cases. Results show low lesion-wise false positives (30%) for the deep learning architecture, whereas the shallow architecture yields the best Dice coefficient (63%) and volume difference (19%). Combining both shallow and deep architectures further improves the lesion-wise metrics (69% and 26% lesion-wise true and false positive rate, respectively).



The work is supported by the Centre d’Imagerie BioMédicale (CIBM) of the University of Lausanne (UNIL), the Swiss Federal Institute of Technology Lausanne (EPFL), the University of Geneva (UniGe), the Centre Hospitalier Universitaire Vaudois (CHUV), the Hôpitaux Universitaires de Genève (HUG), and the Leenaards and Jeantet Foundations. This project is also supported by the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie project TRABIT (agreement No. 765148). CG is supported by the Swiss National Science Foundation grant SNSF Professorship PP00P3-176984.


  1. 1.
    Garcia-Lorenzo, D., et al.: Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging. Med. Image Anal. 17(1), 1–18 (2013)CrossRefGoogle Scholar
  2. 2.
    Styner, M., et al.: 3D segmentation in the clinic: a grand challenge II: MS lesion segmentation. MIDAS J. 2008, 1–6 (2008)Google Scholar
  3. 3.
    Carass, A., et al.: Longitudinal multiple sclerosis lesion segmentation: resource and challenge. NeuroImage 148, 77–102 (2017)CrossRefGoogle Scholar
  4. 4.
    Commowick, O., Cervenansky, F., Ameli, R.: MSSEG challenge proceedings: multiple sclerosis lesions segmentation challenge using a data management and processing infrastructure. In: MICCAI 2016 (2016)Google Scholar
  5. 5.
    Valverde, S., et al.: Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach. NeuroImage 155, 159–168 (2017)CrossRefGoogle Scholar
  6. 6.
    Brosch, T., et al.: Deep 3D convolutional encoder networks with shortcuts for multiscale feature integration applied to multiple sclerosis lesion segmentation. Trans. Med. Imaging 35(5), 1229–1239 (2016)CrossRefGoogle Scholar
  7. 7.
    Roy, S., et al.: Multiple sclerosis lesion segmentation from brain MRI via fully convolutional neural networks. arXiv:1803.09172 (2018)
  8. 8.
    Grahl, S., et al.: Defining a minimal meaningful lesion size in multiple sclerosis. Mult. Scler. J. 23, P538-237 (2017)Google Scholar
  9. 9.
    Fartaria, M.J., et al.: Partial volume-aware assessment of multiple sclerosis lesions. NeuroImage: Clin. 18, 245–253 (2018)CrossRefGoogle Scholar
  10. 10.
    Fartaria, M.J., Roche, A., Meuli, R., Granziera, C., Kober, T., Bach Cuadra, M.: Segmentation of cortical and subcortical multiple sclerosis lesions based on constrained partial volume modeling. In: Descoteaux, M., Maier-Hein, L., Franz, A., Jannin, P., Collins, D.L., Duchesne, S. (eds.) MICCAI 2017. LNCS, vol. 10435, pp. 142–149. Springer, Cham (2017). Scholar
  11. 11.
  12. 12.
    Klein, S., et al.: Elastix: a toolbox for intensity-based medical image registration. IEEE Trans. Med. Imaging 29(1), 196–205 (2010)CrossRefGoogle Scholar
  13. 13.
    Smith, S.M.: Fast robust automated brain extraction. Hum. Brain Mapp. 17(3), 143–155 (2002)CrossRefGoogle Scholar
  14. 14.
    Tustison, N.J., et al.: N4ITK: improved N3 bias correction. IEEE Trans. Med. Imaging 29(6), 1310–1320 (2010)CrossRefGoogle Scholar
  15. 15.
    Kikinis, R., Pieper, S.D., Vosburgh, K.G.: 3D slicer: a platform for subject-specific image analysis, visualization, and clinical support. In: Jolesz, F.A. (ed.) Intraoperative Imaging and Image-Guided Therapy, pp. 277–289. Springer, New York (2014). ISBN 978-1-4614-7656-6CrossRefGoogle Scholar
  16. 16.
    Fartaria, M.J., et al.: Automated detection of white matter and cortical lesions in early stages of multiple sclerosis. J. Magn. Reson. Imaging 43(6), 1445–1454 (2016)CrossRefGoogle Scholar
  17. 17.
    Crimi, A., Commowick, O., Ferré, J.C., Maarouf, A., Edan, G., Barillot, C.: Semi-automatic classification of lesion patterns in patients with clinically isolated syndrome. In: 2013 IEEE 10th International Symposium on Biomedical Imaging (ISBI), pp. 1102–1105. IEEE, April 2013Google Scholar
  18. 18.
  19. 19.
    Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv:1212.5701 (2012)
  20. 20.
    Luo, K., et al.: A CNN-based segmentation model for segmenting foreground by a probability map. In: Intelligent Signal Processing and Communication Systems (ISPACS), IEEE ISBI 2017 (2017)Google Scholar
  21. 21.
    Zotti, C., et al.: GridNet with automatic shape prior registration for automatic MRI cardiac segmentation. arXiv:1705.08943 (2017)
  22. 22.
    Kotsiantis, S.B., Zaharakis, I.D., Pintelas, P.E.: Machine learning: a review of classification and combining techniques. Artif. Intell. Rev. 26(3), 159–190 (2006)CrossRefGoogle Scholar
  23. 23.
    Fartaria, M.J., et al.: An ensemble of 3D convolutional neural networks for central vein detection in white matter lesions. In: MIDL 2018 Abstract Submission (2018)Google Scholar
  24. 24.
    Kamnitsas, K., et al.: Ensembles of multiple models and architectures for robust brain tumour segmentation. arXiv:1711.01468 (2017)
  25. 25.
    Geremia, E., Clatz, O., Menze, B.H., Konukoglu, E., Criminisi, A., Ayache, N.: Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images. NeuroImage 57, 378–390 (2011)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Francesco La Rosa
    • 1
    • 3
    Email author
  • Mário João Fartaria
    • 1
    • 2
    • 4
  • Tobias Kober
    • 1
    • 2
    • 4
  • Jonas Richiardi
    • 2
    • 4
  • Cristina Granziera
    • 5
    • 6
  • Jean-Philippe Thiran
    • 1
    • 4
  • Meritxell Bach Cuadra
    • 1
    • 3
    • 4
  1. 1.LTS5Ecole Polytechnique Fédérale de LausanneLausanneSwitzerland
  2. 2.Siemens Healthcare AGLausanneSwitzerland
  3. 3.Medical Image Analysis Laboratory, CIBMUniversity of LausanneLausanneSwitzerland
  4. 4.Radiology DepartmentLausanne University HospitalLausanneSwitzerland
  5. 5.Translational Imaging in Neurology Basel, Department of Medicine and Biomedical EngineeringUniversity Hospital Basel and University of BaselBaselSwitzerland
  6. 6.Neurologic Clinic and Policlinic, Departments of Medicine, Clinical Research and Biomedical EngineeringUniversity Hospital Basel and University of BaselBaselSwitzerland

Personalised recommendations