, Volume 56, Issue 5, pp 363–374 | Cite as

A subtraction pipeline for automatic detection of new appearing multiple sclerosis lesions in longitudinal studies

  • Onur Ganiler
  • Arnau Oliver
  • Yago Diez
  • Jordi Freixenet
  • Joan C. Vilanova
  • Brigitte Beltran
  • Lluís Ramió-Torrentà
  • Àlex Rovira
  • Xavier Lladó
Diagnostic Neuroradiology



Time-series analysis of magnetic resonance images (MRI) is of great value for multiple sclerosis (MS) diagnosis and follow-up. In this paper, we present an unsupervised subtraction approach which incorporates multisequence information to deal with the detection of new MS lesions in longitudinal studies.


The proposed pipeline for detecting new lesions consists of the following steps: skull stripping, bias field correction, histogram matching, registration, white matter masking, image subtraction, automated thresholding, and postprocessing. We also combine the results of PD-w and T2-w images to reduce false positive detections.


Experimental tests are performed in 20 MS patients with two temporal studies separated 12 (12M) or 48 (48M) months in time. The pipeline achieves very good performance obtaining an overall sensitivity of 0.83 and 0.77 with a false discovery rate (FDR) of 0.14 and 0.18 for the 12M and 48M datasets, respectively. The most difficult situation for the pipeline is the detection of very small lesions where the obtained sensitivity is lower and the FDR higher.


Our fully automated approach is robust and accurate, allowing detection of new appearing MS lesions. We believe that the pipeline can be applied to large collections of images and also be easily adapted to monitor other brain pathologies.


Multiple sclerosis Brain MRI longitudinal analysis Lesion change detection 3D subtraction 


Conflict of interest

We declare that we have no conflict of interest.


  1. 1.
    Battaglini M, Rossi F, Grove RA, Stromillo ML, Whitcher B, Matthews PM, De Stefano N (2013) Automated identification of brain new lesions in multiple sclerosis using subtraction images. J Magn Reson Imag to appearGoogle Scholar
  2. 2.
    Bosc M, Heitz F, Armspach J, Namer I, Gounot D, Rumbachc L (2003) Automatic change detection in multimodal serial MRI: application to multiple sclerosis lesion evolution. NeuroImage 20(2):643–656PubMedCrossRefGoogle Scholar
  3. 3.
    Cabezas M, BachCuadra M, Oliver A, Lladó X, Freixenet J, Vilanova JC, Valls L, Ramió-Torrentà L, Huerga E, Pareto D, Rovira A (2011) A pipeline approach with spatial information for segmenting multiple sclerosis lesions on brain magnetic resonance imaging. In: Proc Europ Comm Treatm Res Mult Scl 381.Google Scholar
  4. 4.
    Curati WL, Williams EJ, Oatridge A, Hajnal JV, Saeed N, Bydder GM (1996) Use of subvoxel registration and subtraction to improve demonstration of contrast enhancement in MRI of the brain. Neuroradiology 38:717–723PubMedCrossRefGoogle Scholar
  5. 5.
    Elliott C, Arnold DL, Collins DL, Arbel T (2013) Temporally consistent probabilistic detection of new multiple sclerosis lesions in brain MRI. IEEE Trans Med Imaging 32(8):1490–1503PubMedCrossRefGoogle Scholar
  6. 6.
    Garc a-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
  7. 7.
    Lemieux L, Wieshmann U, Moran N, Fish D, Shorvon S (1998) The detection and significance of subtle changes in mixed-signal brain lesions by serial MRI scan matching and spatial normalization. Med Image Anal 2(3):227–242PubMedCrossRefGoogle Scholar
  8. 8.
    Lladó X, Ganiler O, Oliver A, Mart R, Freixenet J, Valls L, Vilanova JC, Ramio-Torrent L, Rovira A (2012) Automated detection of multiple sclerosis lesions in serial brain MRI. Neuroradiology 54(8):787–807PubMedCrossRefGoogle Scholar
  9. 9.
    Lladó X, Oliver A, Cabezas M, Freixenet J, Vilanova JC, Quiles A, Valls L, Ramio-Torrenta L, Rovira A (2012) Segmentation of multiple sclerosis lesions in brain MRI: a review of automated approaches. Inf Sci 186(1):164–185CrossRefGoogle Scholar
  10. 10.
    Mattes D, Haynor DR, Vesselle H, Lewellen T, Eubank W (2001) Non-rigid multimodality image registration. Proc SPIE Med Imaging 4322:1609–1620CrossRefGoogle Scholar
  11. 11.
    Moraal B, Meier DS, Poppe PA (2009) Subtraction MR images in a multiple sclerosis multicenter clinical trial setting. Radiology 250:506–514PubMedCentralPubMedCrossRefGoogle Scholar
  12. 12.
    Moraal B, Wattjes MP, Geurts JJG (2010) Improved detection of active multiple sclerosis lesions: 3D subtraction imaging. Radiology 255(1)Google Scholar
  13. 13.
    Mortazavi D, Kouzani AZ, Soltanian-Zadeh H (2012) Segmentation of multiple sclerosis lesions in MR images: a review. Neuroradiology 54(4):299–320PubMedCrossRefGoogle Scholar
  14. 14.
    Nyul LG, Udupa JK, Zhang X (2000) New variants of a method of MRI scale standardization. IEEE Trans Med Imaging 19(2):143–150PubMedCrossRefGoogle Scholar
  15. 15.
    Sled J, Zijdenbos A, Evans A (1998) A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging 17(1):87–97PubMedCrossRefGoogle Scholar
  16. 16.
    Smith S (2002) Fast robust automated brain extraction. Hum Brain Map-ping 17(3):143–155CrossRefGoogle Scholar
  17. 17.
    Souplet JC, Lebrun C, Ayache N, Malandain G (2008) An automatic segmentation of T2-FLAIR multiple sclerosis lesions. In: MICCAI—Challenge, 1–11Google Scholar
  18. 18.
    Sweeney EM, Shinohara RT, Shea CD, Reich DS, Crainiceanu CM (2013) Automatic lesion incidence estimation and detection in multiple sclerosis using multisequence longitudinal MRI. Am J Neuroradiol 34(1):68–73PubMedCentralPubMedCrossRefGoogle Scholar
  19. 19.
    Tan IL, van Schijndel RA, Fazekas F, Filippi M, Freitag P, Miller DH, Yousry TA, Pouwels PJW, Adr HJ, Barkhof F (2002) Image registration and subtraction to detect active T2 lesions in MS: an interobserver study. J Neurol 249:767–773PubMedCrossRefGoogle Scholar
  20. 20.
    Tan IL, van Schijndel RA, van Walderveen MAA, Quist M, Bos R, Pouwels PJW, Desmedt P, Ader HJ, Barkhof F (2002) Magnetic resonance image registration in multiple sclerosis: comparison with repositioning error and observer-based variability. J Magn Reson Imaging 15(5):505–510PubMedCrossRefGoogle Scholar
  21. 21.
    Tustison N, Avants B, Cook P, Zheng Y, Egan A, Yushkevich P, Gee J (2010) N4ITK: improved N3 bias correction. IEEE Trans Med Imaging 29(6):1310–1320PubMedCentralPubMedCrossRefGoogle Scholar
  22. 22.
    Vrenken H, Jenkinson M, Hors eld MA, Battaglini M, Van Schijndel RA, Ros-trup E, Geurts JJG, Fisher E, Zijdenbos A, Ashburner J, Miller DH, Filippi M, Fazekas F, Rovaris M, Rovira A, Barkhof F, De Stefano N (2013) Recommendations to improve imaging and analysis of brain lesion load and atrophy in longitudinal studies of multiple sclerosis. J Neurol 260(10):2458–2471PubMedCentralPubMedCrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2014

Authors and Affiliations

  • Onur Ganiler
    • 1
  • Arnau Oliver
    • 1
  • Yago Diez
    • 1
  • Jordi Freixenet
    • 1
  • Joan C. Vilanova
    • 2
  • Brigitte Beltran
    • 3
  • Lluís Ramió-Torrentà
    • 4
  • Àlex Rovira
    • 5
  • Xavier Lladó
    • 1
  1. 1.VICOROB Computer Vision and Robotics GroupUniversity of GironaGironaSpain
  2. 2.Girona Magnetic Resonance CenterGironaSpain
  3. 3.Institut d’Investigació Biomèdica de GironaDr. Josep Trueta University HospitalGironaSpain
  4. 4.Multiple Sclerosis and Neuroimmunology UnitDr. Josep Trueta University Hospital, Institut d’Investigació Biomèdica de GironaGironaSpain
  5. 5.Magnetic Resonance Unit, Department of RadiologyVall d’Hebron University HospitalBarcelonaSpain

Personalised recommendations