Skip to main content
SpringerLink
Log in

Accurate Pathology Segmentation in FLAIR MRI for Robust Shape Characterization

  • Chapter
  • First Online:
Shape Analysis in Medical Image Analysis

Part of the book series: Lecture Notes in Computational Vision and Biomechanics ((LNCVB,volume 14))

Abstract

Shape analysis of pathology requires an accurate initial segmentation. However, in magnetic resonance images (MRI) of the brain, an artifact known as partial volume averaging (PVA) pathology severely impedes segmentation accuracy. Traditional MRI brain segmentation techniques rely on Gaussianmixture models to handle noise and PVA, or high-dimensional feature sets that exploit redundancy in multispectral datasets. Unfortunately, model-based techniques have limited performance on images with non-Gaussian noise distributions and pathology, and multispectral techniques do not make efficient use of imaging resources. For robust segmentation, a generalized PVA modeling approach is developed for FLAIR MRI with white matter lesion (WML) pathology that does not depend on predetermined intensity distribution models or multispectral scans. Instead, PVA is estimated directly from each image using an adaptively defined global edge map constructed by exploiting a mathematical relationship between edge content and PVA. The final PVA map is used to segment WML with sub-voxel accuracy. Using the highly accurately segmented WML, shape analysis experiments were conducted to characterize the types of lesions in the brain. Currently, WML are divided into periventricular white matter lesions (PVWML) and deep white matter lesions (DWML) and radiologists differentiate between them manually. It is important classify these two types of WML since the pathogenic mechanisms between them provide clues regarding the pathophysiology of many diseases (such as MS, stroke, etc.). In this work, we used boundary-based and Fourier descriptors to automatically classify the WML into PVWML and DWML classes. A supervised, linear discriminant classifier was used, where a leave-one-out training and testing strategy was employed. It was found that circularity features alone provided the highest classification rate (90%).

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

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Hardcover Book
USD 109.99
Price excludes VAT (USA)
  • Durable hardcover edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    Mobility refers to how mobile the protons are. Large mobility produces large T2 times (intense regions) and small mobility results in short T2 times (dark regions).

  2. 2.

    Experimental images do not possess significant bias field.

  3. 3.

    As noted in [55], there is a discrepancy with the partial volume model used in BrainWeb. Since we are particularly interested in validating the performance of the partial volume model, we simulate our own images.

  4. 4.

    http://www.pathcore.ca/sedeen/

  5. 5.

    \(\xi _{WML} \ge \) 0.5.

References

  1. Martini FH (2001) Fundamentals of anatomy and physiology, 5th edn. Prentice Hall, New Jersey

    Google Scholar 

  2. Canadian Hearth and Stroke Association (2011) Statistics. World Wide Web, 2011. http://www.heartandstroke.com/site/c.ikIQLcMWJtE/b.3483991/k.34A8/Statistic.htm.

  3. Fox AJ, Hachinski VC, Barnett HJM, Streifler JY, Eliasziw M, Benavente OR, Alamowitch S (2002) Prognostic importance of leukoaraiosis in patients with symptomatic internal carotid artery stenosis. Stroke 33:1651–1655

    Article  Google Scholar 

  4. Malloy P, Correia S, Stebbins G, Laidlaw DH (2007) Neuroimaging of white matter in aging and dementia. Clin Neuropsychol 21:73–109

    Article  Google Scholar 

  5. Kim KW, MacFall JR, Payne ME (2008) Classification of white matter lesions on magnetic resonance imaging in the elderly. Biol Psychiatr 64(4):273–280

    Google Scholar 

  6. Khademi A, Hosseinzadeh D, Venetsanopoulos A, Moody AR (2009) Nonparametric statistical tests for exploration of correlation and nonstationarity in images. In: International conference on digital signal processing (DSP), 2009, pp 1–6

    Google Scholar 

  7. Chang R (2007) Chemistry, 9th edn. McGraw-Hill, New York

    Google Scholar 

  8. Haase A, Frahm J, Matthaei D, Hanicke W, Merboldt KD (1986) Flash imaging: rapid NMR imaging using low flip angle pulses. J Magn Reson 67(2):258–266

    Google Scholar 

  9. Mansfield P (1977) Multi-planar image formation using NMR spin echoes. J Phys C 10:L55–L58

    Article  Google Scholar 

  10. Salvolini U, Scarabino T (2006) High field brain MRI: use in clinical practice. Springer Berlin Heidelberg, Printed in Germany

    Google Scholar 

  11. Dietrich O (2011) Parallel imaging in clinical MR applications, Part I, chapter MRI from k-Space to parallel imaging. Medical Radiology, Springer Berlin Heidelberg, Printed in Germany, pp 3–17

    Google Scholar 

  12. Griswold MA (2011) Parallel imaging in clinical MR applications, Part I, chapter basic reconstruction algorithms for parallel imaging, Medical Radiology, Springer Berlin Heidelberg, Printed in Germany, pp 19–36

    Google Scholar 

  13. Murphy RE, Moody AR, Morgan PS, Martel AL (2008) Brain white matter hyperintensities are associated with carotid intraplaque hemorrhage. Radiology 248(1):202–209

    Article  Google Scholar 

  14. Altaf N, Daniels L, Morgan PS, Lowe J, Gladman J, MacSweeney ST, Moody A, Auer DP (2006) Cerebral white matter hyperintense lesions are associated with unstable carotid plaques. Eur J Vasc Endovasc Surg 31:8–13

    Article  Google Scholar 

  15. Jack CR, O’Brien PC, Rettman DW, Shiung MM, Xu YC, Muthupillai R, Manduca A, Avula R, Erickson BJ (2001) FLAIR histogram segmentation for measurement of leukoaraiosis volume. J Magn Reson Imaging 14(6):668–676

    Article  Google Scholar 

  16. Cuadra MB, Platel B, Solanas E, Butz T, Thiran J-P (2002) Validation of tissue modelization and classification techniques in T1-weighted MR brain images, Lecture notes in computer science (LCNS). In: Medical image computing and computer-assisted intervention (MICCAI) Conference, vol 2488, pp 290–297

    Google Scholar 

  17. Cuadra MB, Cammoun L, Butz T, Cuisenaire O, Thiran J-P (2005) Comparison and validation of tissue modelization and statistical classification methods in T1-weighted MR brain images. IEEE Trans Med Imaging 24(12):1548–1565

    Article  Google Scholar 

  18. Suri J, Singh S, Reden L (2002) Computer vision and pattern recognition techniques for 2-D and 3-D MR cerebral cortical segmentation (part I): a state-of-the-art review. Pattern Anal Appl 5(1):46–76

    Article  MathSciNet  Google Scholar 

  19. Sled JG, Zijdenbos AP, Evans AC (1998) A nonparametric method for automatic correction of intensity nonuniformity in MRI data. IEEE Trans Med Imaging 17(1):87–97

    Article  Google Scholar 

  20. Sijbers J, Poot D, den Dekker AJ, Pintjens W (2007) Automatic estimation of the noise variance from the histogram of a magnetic resonance image. Phys Med Biol 52:1335–1348

    Article  Google Scholar 

  21. Nowak RD (1999) Wavelet-based Rician noise removal for magnetic resonance imaging. IEEE Trans Image Process 8(10):1408–1419

    Article  Google Scholar 

  22. Chang L-C, Rohde GK, Pierpaoli C (2005) An automatic method for estimating noise-induced signal variance in magnitude-reconstructed magnetic resonance images. In: SPIE, medical imaging conference, vol 5747, pp 1136–1142

    Google Scholar 

  23. Wood JC, Johnson KM (1999) Wavelet packet denoising of magnetic resonance images: importance of Rician noise at low SNR. Magn Reson Med 41:631–635

    Article  Google Scholar 

  24. Lin P, Yang Y, Zheng C-X, Gu J-W (2004) An efficient automatic framework for segmentation of MRI brain image. In: International conference on computer and IT, 2004, vol 00, pp 896–900

    Google Scholar 

  25. Yang J, Huang S-C (1999) Method for evaluation of different MRI segmentation approaches. IEEE Trans Nucl Sci 46(6):2259–2265

    Article  Google Scholar 

  26. Clarke LP, Velthuizen RP, Phuphanich S, Schellenberg JD, Arrington JA, Silbiger M (1993) MRI: stability of three supervised semgentation algorithms. Magn Reson Imaging 11(1):95–106

    Article  Google Scholar 

  27. 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(1):45–57

    Article  Google Scholar 

  28. Kellman P, McVeigh ER (2005) Image reconstruction in SNR units: a general method for SNR measurement. Magn Reson Med 54(6):1439–1447

    Article  Google Scholar 

  29. Roemer PB, Edelstein WA, Hayes CE, Souza SP, Mueller OM (1990) The NMR phased array. Magn Reson Med 16(2):192–225

    Article  Google Scholar 

  30. Pruessmann KP, Weiger M, Scheidegger MB, Boesiger P (1999) Sense: sensitivity encoding for fast MRI. Magn Reson Med 42:952–962

    Article  Google Scholar 

  31. Thunberg P, Zetterberg P (2007) Noise distribution in SENSE-and GRAPPA-reconstructed images: a computer simulation study. Magn Reson Imaging 25(7):1089–1094

    Article  Google Scholar 

  32. Sodickson DK, Manning WJ (1997) Simultaneous acquisition of spatial harmonics (SMASH): fast imaging with radiofrequency coil arrays. Magn Reson Med 38:591–603

    Article  Google Scholar 

  33. Griswold MA, Jakob PM, Heidemann RM, Nittka M, Jellus V, Wang J, Kiefer B, Haase A (2002) Generalized autocalibrating partially parallel acquisitions (GRAPPA). Magn Reson Med 47:1202–1210

    Google Scholar 

  34. Newbould R, Liu C, Bammer R (2006) Colored noise and effective resolution: data considerations for non-uniform k-space sampling reconstructions. In: Proceedings of the international society of magnetic resonance in medicine, vol 14, pp 2939

    Google Scholar 

  35. Lowe M, Sorenson J (1997) Spatially filtering functional magnetic resonance imaging data. Magn Reson Med 37(5):723–729

    Article  Google Scholar 

  36. Samsonov A, Johnson C (2004) Noise-adaptive nonlinear diffusion filtering of MR images with spatially varying noise levels. Magn Reson Med 52:798–806

    Article  Google Scholar 

  37. Van Leemput K, Maes F, Vandermeulen D, Suetens P (2003) A unifying framework for partial volume segmentation of brain MR images. IEEE Trans Med Imaging 22(1):105–119

    Article  Google Scholar 

  38. Ballester MAG, Zisserman AP,Brady M (2002) Estimation of the partial volume effect in MRI. Med Image Anal 6(4):389–405

    Google Scholar 

  39. Khademi A, Venetsanopoulos A, Moody AR (2009) Automatic contrast enhancement of white matter lesions in FLAIR MRI. In: IEEE international symposium on biomedical imaging, 2009, pp 322–325, \(\copyright \) 2009 IEEE. Reprinted with permission

    Google Scholar 

  40. Ruan S, Jaggi C, Xue J, Fadili J, Bloyet D (2000) Brain tissue classification of magnetic resonance images using partial volume modeling. IEEE Trans Med Imaging 19(12):1179–1187

    Article  Google Scholar 

  41. Santago P, Gage HD (1993) Quantification of MR brain images by mixture density and partial volume modeling. IEEE Trans Med Imaging 12(3):566–574

    Article  Google Scholar 

  42. Santago P, Gage H (2003) Statistical models of partial volume effect. IEEE Trans Image Process 4(11):1531–1540

    Article  Google Scholar 

  43. Dugas-Phocion G, Ballester MAG,Malandain G, Lebrun C, Ayache N (2003) Improved em-based tissue segmentation and partial volume effect quantification in multi-sequence brain MRI. In: Lecture notes in computer science (LCNS): medical image computing and computer-assisted intervention (MICCAI) Conference, 2003, vol 3216, pp 26–33

    Google Scholar 

  44. Chiverton JP, Wells K (2003) Adaptive partial volume classification of MRI data. Phys Med Biol 53(20):5577–5594

    Article  Google Scholar 

  45. Anbeek P, Vincken K, van Osch M, Bisschops R, van der Grond J (2004) Probabilistic segmentation of white matter lesions in MR imaging. NeuroImage 21(3):1037–1044

    Article  Google Scholar 

  46. Lao Z, Shen D, Jawad A, Karacali B, Liu D, Melhem ER, Bryan RN, Davatzikos C (2006) Automated segmentation of white matter lesions in 3D brain MRI, using multivariate pattern classification. In: IEEE international symposium on biomedical imaging (ISBI), 2006, pp 307–310

    Google Scholar 

  47. de Boer R, van der Lijn F, Vrooman HA, Vernooij MW, Ikram MA, Breteler MMB, Niessen WJ (2007) Automatic segmentation of brain tissue and white matter lesions in MRI. In: IEEE international symposium on biomedical, imaging, 2007, pp 652–655

    Google Scholar 

  48. Khademi A, Venetsanopoulos A, Moody AR (2012) Robust white matter lesion segmentation in flair mri. IEEE Trans Biomed Eng 59(3):860–871

    Article  Google Scholar 

  49. Meer P, Georgescu B (2001) Edge detection with embedded confidence. IEEE Trans Pattern Anal Mach Intell 23(12):1351–1365

    Article  Google Scholar 

  50. Khademi A, Venetsanopoulos A, Moody AR (2010) Edge-based partial volume averaging estimation in FLAIR MRI with white matter lesions. In: IEEE engineering in medicine and biology conference, 2010, pp 6114–6117

    Google Scholar 

  51. Kvam PH, Vidakovic B (2007) Nonparametric statistics with applications to science and engineering. Whiley-Interscience, USA

    Book  MATH  Google Scholar 

  52. Loncarica S (1988) A survey of shape analysis techniques. Pattern Recognit 31(8):983–1001

    Google Scholar 

  53. Kwan RK-S, Evans AC, Pike GB (1996) An extensible MRI simulator for post-processing evaluation. In: Lecture notes in computer science (LCNS): visualization in biomedical computing (VBC), 1996, vol 1131, pp 135–140

    Google Scholar 

  54. Collins DL, Zijdenbos AP, Kollokian V, Sled JG, Kabani NJ, Holmes CJ, Evans AC (1998) Design and construction of a realistic digital brain phantom. IEEE Trans Med Imaging 17(3):463–468

    Article  Google Scholar 

  55. Bromiley PA (2008) Problems with the brainweb MRI simulator in the evaluation of medical image segmentation algorithms, and an alternative methodology. Technical report, Imaging Science and Biomedical Engineering Division, University of Manchester Medical School, Tina Memo No. 2008–002, Internal Memo

    Google Scholar 

  56. Pham DL, Prince JL (2000) Unsupervised partial volume estimation in single-channel image data. In: IEEE workshop on mathematical methods in biomedical image analysis (MMBIA), 2000, pp 170–177

    Google Scholar 

  57. Anbeek P, Vincken KL, van Osch MJ, Bisschops RH, van der Grond J (2004) Automatic segmentation of different-sized white matter lesions by voxel probability estimation. Med Image Anal 8(3):205–215

    Article  Google Scholar 

  58. Popovic A, de la Fuente M, Engelhardt M, Radermacher K (2007) Statistical validation metric for accuracy assessment in medical image segmentation. Int J Comput Assist Radiol Surg 2:169–181

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Biomedical Engineering, University of Guelph, 50 Stone Rd E, Guelph, ON, N1G 2W1, Canada

    April Khademi

  2. Department of Medical Imaging, University of Toronto, 263 McCaul Street, Toronto, ON, M5T 1W7, Canada

    Alan R. Moody

  3. Department of Electrical and Computer Engineering, University of Toronto, 10 King’s College Road, Toronto, ON, M5S 3G4, Canada

    Anastasios Venetsanopoulos

Authors
  1. April Khademi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Alan R. Moody
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Anastasios Venetsanopoulos
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to April Khademi .

Editor information

Editors and Affiliations

  1. GE Healthcare and University of Western Ontario, London, Ontario, Canada

    Shuo Li

  2. Departamento de Engenharia Mecânica, Universidade do Porto, Porto, Portugal

    João Manuel R. S. Tavares

Rights and permissions

Reprints and permissions

Copyright information

© 2014 Springer International Publishing Switzerland

About this chapter

Cite this chapter

Khademi, A., Moody, A.R., Venetsanopoulos, A. (2014). Accurate Pathology Segmentation in FLAIR MRI for Robust Shape Characterization. In: Li, S., Tavares, J. (eds) Shape Analysis in Medical Image Analysis. Lecture Notes in Computational Vision and Biomechanics, vol 14. Springer, Cham. https://doi.org/10.1007/978-3-319-03813-1_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-03813-1_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-03812-4

  • Online ISBN: 978-3-319-03813-1

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation