Skip to main content

Advertisement

SpringerLink
Log in

Automatic segmentation and volumetric quantification of white matter hyperintensities on fluid-attenuated inversion recovery images using the extreme value distribution

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

Abstract

Introduction

This study aims to develop an automatic segmentation framework on the basis of extreme value distribution (EVD) for the detection and volumetric quantification of white matter hyperintensities (WMHs) on fluid-attenuated inversion recovery (FLAIR) images.

Methods

Two EVD-based segmentation methods, namely the Gumbel and Fréchet segmentation, were developed to detect WMHs on FLAIR (slice thickness = 5 mm; TR/TE/TI = 11,000/120/2,800 ms; flip angle = 90°) images. Another automatic segmentation method using a trimmed likelihood estimator (TLE) was implemented for comparison with our proposed segmentation framework. The performances of the three automatic segmentation methods were evaluated by comparing with the manual segmentation method.

Results

The Dice similarity coefficients (DSCs) of the two EVD-based segmentation methods were larger than those of the TLE-based segmentation method (Gumbel, 0.823 ± 0.063; Fréchet, 0.843 ± 0.057; TLE, 0.817 ± 0.068), demonstrating that the EVD-based segmentation outperformed the TLE-based segmentation. The Fréchet segmentation obtained larger DSCs on patients with moderate to severe lesion loads and a comparable performance on patients with mild lesion loads, indicating that the Fréchet segmentation was superior to the Gumbel segmentation. The Gumbel segmentation underestimated the lesion volumes of all patients, whereas the Fréchet and TLE-based segmentation methods obtained overestimated lesion volumes (Manual, 13.71 ± 14.02 cc; Gumbel, 12.73 ± 13.21 cc; Fréchet, 13.88 ± 13.96 cc; TLE, 13.54 ± 12.27 cc). Moreover, the EVD-based segmentation was demonstrated to be comparable to other state-of-the-art methods on a publicly available dataset.

Conclusion

The proposed EVD-based segmentation framework is a promising, effective, and convenient tool for volumetric quantification and further study of WMHs in aging and dementia.

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
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

Abbreviations

WMHs:

White matter hyperintensities

FLAIR:

Fluid-attenuated inversion recovery

MRI:

Magnetic resonance imaging

TLE:

Trimmed likelihood estimator

EVD:

Extreme value distribution

UND:

Unilateral normal distribution

PDF:

Probability density function

DSC:

Dice similarity coefficient

FPR:

False-positive rate

FNR:

False-negative rate

References

  1. Debette S, Markus H (2010) The clinical importance of white matter hyperintensities on brain magnetic resonance imaging: systematic review and meta-analysis. BMJ 341:c3666

    Article  PubMed Central  PubMed  Google Scholar 

  2. 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 17:1–18

    Article  PubMed  Google Scholar 

  3. Barkhof F, Scheltens P (2002) Imaging of white matter lesions. Cerebrovasc Dis 13:21–30

    Article  PubMed  Google Scholar 

  4. Au R, Massaro JM, Wolf PA et al (2006) Association of white matter hyperintensity volume with decreased cognitive functioning: the Framingham Heart Study. Arch Neurol 63:246–250

    Article  PubMed  Google Scholar 

  5. Whitman G, Tang T, Lin A, Baloh R (2001) A prospective study of cerebral white matter abnormalities in older people with gait dysfunction. Neurology 57:990–994

    Article  CAS  PubMed  Google Scholar 

  6. Smith CD, Snowdon DA, Wang H, Markesbery WR (2000) White matter volumes and periventricular white matter hyperintensities in aging and dementia. Neurology 54:838–842

    Article  CAS  PubMed  Google Scholar 

  7. Herrmann LL, Le Masurier M, Ebmeier KP (2008) White matter hyperintensities in late life depression: a systematic review. J Neurol Neurosurg Psychiatry 79:619–624

    Article  CAS  PubMed  Google Scholar 

  8. Pantoni L, Garcia JH (1997) Pathogenesis of leukoaraiosis a review. Stroke 28:652–659

    Article  CAS  PubMed  Google Scholar 

  9. Lladó X, Oliver A, Cabezas M et al (2012) Segmentation of multiple sclerosis lesions in brain MRI: a review of automated approaches. Inf Sci 186:164–185

    Article  Google Scholar 

  10. Neumann Haefelin T (2006) Leukoaraiosis is a risk factor for symptomatic intracerebral hemorrhage after thrombolysis for acute stroke. Stroke 37:2463–2466

    Article  PubMed  Google Scholar 

  11. Palumbo V (2007) Leukoaraiosis and intracerebral hemorrhage after thrombolysis in acute stroke. Neurology 68:1020–1024

    Article  CAS  PubMed  Google Scholar 

  12. Brickman AM, Siedlecki KL, Muraskin J et al (2011) White matter hyperintensities and cognition: testing the reserve hypothesis. Neurobiol Aging 32:1588–1598

    Article  PubMed Central  PubMed  Google Scholar 

  13. Prins ND, van Dijk EJ, den Heijer T et al (2004) Cerebral white matter lesions and the risk of dementia. Arch Neurol 61:1531–1534

    Article  PubMed  Google Scholar 

  14. Bedell BJ, Narayana PA (1998) Automatic segmentation of gadolinium enhanced multiple sclerosis lesions. Magn Reson Med 39:935–940

    Article  CAS  PubMed  Google Scholar 

  15. Boudraa A-O, Dehak SMR, Zhu Y-M, Pachai C, Bao Y-G, Grimaud J (2000) Automated segmentation of multiple sclerosis lesions in multispectral MR imaging using fuzzy clustering. Comput Biol Med 30:23–40

    Article  CAS  PubMed  Google Scholar 

  16. Datta S, Sajja BR, He R, Gupta RK, Wolinsky JS, Narayana PA (2007) Segmentation of gadolinium-enhanced lesions on MRI in multiple sclerosis. J Magn Reson Imaging 25:932–937

    Article  PubMed  Google Scholar 

  17. Van Leemput K, Maes F, Vandermeulen D, Colchester A, Suetens P (2001) Automated segmentation of multiple sclerosis lesions by model outlier detection. IEEE Trans Med Imaging 20:677–688

    Article  PubMed  Google Scholar 

  18. Aït-Ali LS, Prima S, Hellier P, Carsin B, Edan G, Barillot C (2005) STREM: a robust multidimensional parametric method to segment MS lesions in MRI. Medical Image Computing and Computer-Assisted Intervention–MICCAI 2005. Springer, pp 409–416

  19. Bricq S, Collet C, Armspach J-P (2008) Lesions detection on 3D brain MRI using trimmed likelihood estimator and probabilistic atlas. Biomedical Imaging: From Nano to Macro, 2008 ISBI 2008 5th IEEE International Symposium on. IEEE, pp 93–96

  20. García-Lorenzo D, Prima S, Arnold DL, Collins DL, Barillot C (2011) Trimmed-likelihood estimation for focal lesions and tissue segmentation in multisequence MRI for multiple sclerosis. IEEE Trans Med Imaging 30:1455–1467

    Article  PubMed Central  PubMed  Google Scholar 

  21. Zhang Y, Brady M, Smith S (2001) Segmentation of brain MR images through a hidden Markov random field model and the expectation-maximization algorithm. IEEE Trans Med Imaging 20:45–57

    Article  CAS  PubMed  Google Scholar 

  22. Neykov N, Filzmoser P, Dimova R, Neytchev P (2007) Robust fitting of mixtures using the trimmed likelihood estimator. Comput Stat Data Anal 52:299–308

    Article  Google Scholar 

  23. Simões R, Mönninghoff C, Dlugaj M et al (2013) Automatic segmentation of cerebral white matter hyperintensities using only 3D FLAIR images. Magn Reson Imaging 31:1182–1189

    Article  PubMed  Google Scholar 

  24. Gibson E, Gao F, Black SE, Lobaugh NJ (2010) Automatic segmentation of white matter hyperintensities in the elderly using FLAIR images at 3T. J Magn Reson Imaging 31:1311–1322

    Article  PubMed Central  PubMed  Google Scholar 

  25. Khayati R, Vafadust M, Towhidkhah F, Nabavi M (2008) Fully automatic segmentation of multiple sclerosis lesions in brain MR FLAIR images using adaptive mixtures method and Markov random field model. Comput Biol Med 38:379–390

    Article  PubMed  Google Scholar 

  26. de Haan L, Ferreira A (2006) Extreme value theory: an introduction. Springer, New York

    Book  Google Scholar 

  27. Kotz S, Nadarajah S (2000) Extreme value distributions. Imperial College Press, London

    Book  Google Scholar 

  28. Roberts SJ (2000) Extreme value statistics for novelty detection in biomedical data processing. Science, Measurement and Technology, IEE Proceedings-. IET, pp 363–367

  29. Sled JG, Zijdenbos AP, Evans AC (1998) A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging 17:87–97

    Article  CAS  PubMed  Google Scholar 

  30. Smith SM (2002) Fast robust automated brain extraction. Hum Brain Mapp 17:143–155

    Article  PubMed  Google Scholar 

  31. Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66

    Article  Google Scholar 

  32. MacDonald A, Scarrott CJ, Lee D, Darlow B, Reale M, Russell G (2011) A flexible extreme value mixture model. Comput Stat Data Anal 55:2137–2157

    Article  Google Scholar 

  33. Park JS, Chung MS, Hwang SB, Lee YS, Har D-H (2005) Technical report on semiautomatic segmentation using the Adobe Photoshop. J Digit Imaging 18:333–343

    Article  PubMed Central  PubMed  Google Scholar 

  34. Admiraal-Behloul F, Van Den Heuvel D, Olofsen H et al (2005) Fully automatic segmentation of white matter hyperintensities in MR images of the elderly. Neuroimage 28:607–617

    Article  CAS  PubMed  Google Scholar 

  35. Anbeek P, Vincken KL, van Osch MJ, Bisschops RH, van der Grond J (2004) Probabilistic segmentation of white matter lesions in MR imaging. Neuroimage 21:1037–1044

    Article  PubMed  Google Scholar 

  36. Dice LR (1945) Measures of the amount of ecologic association between species. Ecology 26:297–302

    Article  Google Scholar 

  37. Shiee N, Bazin P-L, Ozturk A, Reich DS, Calabresi PA, Pham DL (2010) A topology-preserving approach to the segmentation of brain images with multiple sclerosis lesions. Neuroimage 49:1524–1535

    Article  PubMed Central  PubMed  Google Scholar 

  38. Wack DS, Dwyer MG, Bergsland N et al (2012) Improved assessment of multiple sclerosis lesion segmentation agreement via detection and outline error estimates. BMC Med Imaging 12:17

    Article  PubMed Central  PubMed  Google Scholar 

  39. Steenwijk MD, Pouwels PJ, Daams M et al (2013) Accurate white matter lesion segmentation by k nearest neighbor classification with tissue type priors (kNN-TTPs). Neuroimage Clin 3:462–469

    Article  PubMed Central  PubMed  Google Scholar 

  40. Altman DG, Bland JM (1983) Measurement in medicine: the analysis of method comparison studies. Stat 32:307–317

    Google Scholar 

  41. Bland JM, Altman DG (1999) Measuring agreement in method comparison studies. Stat Methods Med Res 8:135–160

    Article  CAS  PubMed  Google Scholar 

  42. Geremia E (2011) Spatial decision forests for MS lesion segmentation in multi-channel magnetic resonance images. Neuroimage 57:378–390

    Article  PubMed  Google Scholar 

  43. Abdullah BA, Younis AA, John NM (2012) Multi-sectional views textural based SVM for MS lesion segmentation in multi-channels MRIs. Open Biomed Eng J 6:56

    Article  PubMed Central  PubMed  Google Scholar 

  44. Hodge VJ, Austin J (2004) A survey of outlier detection methodologies. Artif Intell Rev 22:85–126

    Article  Google Scholar 

  45. Wu Y, Warfield SK, Tan IL et al (2006) Automated segmentation of multiple sclerosis lesion subtypes with multichannel MRI. Neuroimage 32:1205–1215

    Article  PubMed  Google Scholar 

  46. Cerasa A, Bilotta E, Augimeri A et al (2012) A cellular neural network methodology for the automated segmentation of multiple sclerosis lesions. J Neurosci Methods 203:193–199

    Article  PubMed  Google Scholar 

  47. Yamamoto D, Arimura H, Kakeda S et al (2010) Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: false positive reduction scheme consisted of rule-based, level set method, and support vector machine. Comput Med Imaging Graph 34:404–413

    Article  PubMed  Google Scholar 

  48. Madabhushi A, Udupa JK (2005) Interplay between intensity standardization and inhomogeneity correction in MR image processing. IEEE Trans Med Imaging 24:561–576

    Article  PubMed  Google Scholar 

  49. Zhuge Y, Udupa JK (2009) Intensity standardization simplifies brain MR image segmentation. Comput Vis Image Underst 113:1095–1103

    Article  PubMed Central  PubMed  Google Scholar 

  50. Ong KH, Ramachandram D, Mandava R, Shuaib IL (2012) Automatic white matter lesion segmentation using an adaptive outlier detection method. Magn Reson Imaging 30:807–823

    Article  PubMed  Google Scholar 

Download references

Acknowledgments

This study has received funding by National Basic Research Program of China (973 Program, No. 2010CB732506), National Natural Science Foundation of China (No. 81301213), National Natural Science Foundation of China (No. 81000609), National Natural Science Foundation of China (No. 60972110), and Major Program of Social Science Foundation of China (No. 11&ZD174).

Ethical standards and patient consent

We declare that all human studies have been approved by the Institutional Review Board of Shanghai Jiao Tong University Sixth Affiliated People’s Hospital and have therefore been performed in accordance with the ethical standards laid down in the 1964 Declaration of Helsinki and its later amendments. We declare that all patients gave informed consent prior to inclusion in this study.

Conflict of interest

We declare that we have no conflict of interest.

Author information

Authors and Affiliations

  1. School of Biomedical Engineering and Med-X Research Institute, Shanghai Jiao Tong University, Room 123, 3 Teaching Building, No. 1954, Huashan Road, Shanghai, China, 200030

    Rui Wang, Chao Li, Jie Wang & Su Zhang

  2. Institute of Diagnostic and Interventional Radiology, Sixth Affiliated People’s Hospital, Shanghai Jiao Tong University, Shanghai, China

    Xiaoer Wei & Yuehua Li

  3. CREATICS, CNRS UMR 5220, Inserm 1044, INSA, Lyon, Villeurbanne, France

    Yuemin Zhu

Authors
  1. Rui Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Chao Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jie Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Xiaoer Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Yuehua Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yuemin Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Su Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Su Zhang.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wang, R., Li, C., Wang, J. et al. Automatic segmentation and volumetric quantification of white matter hyperintensities on fluid-attenuated inversion recovery images using the extreme value distribution. Neuroradiology 57, 307–320 (2015). https://doi.org/10.1007/s00234-014-1466-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00234-014-1466-4

Keywords

Search

Navigation