Fuzzy-based Vascular Structure Enhancement in Time-of-Flight MRA Images for Improved Segmentation

N. D. Forkert; A. Schmidt-Richberg; J. Fiehler; T. Illies; D. Möller; H. Handels; D. Säring

doi:10.3414/ME10-02-0003

Methods of Information in Medicine, Table of Contents

Methods Inf Med 2011; 50(01): 74-83
DOI: 10.3414/ME10-02-0003

Special Topic – Original Articles

Schattauer GmbH

Fuzzy-based Vascular Structure Enhancement in Time-of-Flight MRA Images for Improved Segmentation

N. D. Forkert

¹Department of Medical Informatics, University Medical Center Hamburg-Eppendorf, Hamburg, Germany

,

A. Schmidt-Richberg

¹Department of Medical Informatics, University Medical Center Hamburg-Eppendorf, Hamburg, Germany

,

J. Fiehler

²Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany

,

T. Illies

²Department of Diagnostic and Interventional Neuroradiology, University Medical Center Hamburg-Eppendorf, Hamburg, Germany

,

D. Möller

³Department Computer Engineering, Faculty of Mathematics, Informatics and Natural Sciences, University of Hamburg, Hamburg, Germany

,

H. Handels

¹Department of Medical Informatics, University Medical Center Hamburg-Eppendorf, Hamburg, Germany

,

D. Säring

¹Department of Medical Informatics, University Medical Center Hamburg-Eppendorf, Hamburg, Germany

› Author Affiliations

Abstract

Summary

Objectives: Cerebral vascular malformations might lead to strokes due to occurrence of ruptures. The rupture risk is highly related to the individual vascular anatomy. The 3D Time-of-Flight (TOF) MRA technique is a commonly used non-invasive imaging technique for exploration of the vascular anatomy. Several clinical applications require exact cerebrovascular segmentations from this image sequence. For this purpose, intensity-based segmentation approaches are widely used. Since small low-contrast vessels are often not detected, vesselness filter-based segmentation schemes have been proposed, which contrari-wise have problems detecting malformed vessels. In this paper, a fuzzy logic-based method for fusion of intensity and vesselness information is presented, allowing an improved segmentation of malformed and small vessels at preservation of advantages of both approaches.

Methods: After preprocessing of a TOF dataset, the corresponding vesselness image is computed. The role of the fuzzy logic is to voxel-wisely fuse the intensity information from the TOF dataset with the corresponding vesselness information based on an analytically designed rule base. The resulting fuzzy parame ter image can then be used for improved cerebrovascular segmentation.

Results: Six datasets, manually segmented by medical experts, were used for evaluation. Based on TOF, vesselness and fused fuzzy parameter images, the vessels of each patient were segmented using optimal thresholds computed by maximizing the agreement to manual segmentations using the Tanimoto coefficient. The results showed an overall improvement of 0.054 (fuzzy vs. TOF) and 0.079 (fuzzy vs. vesselness). Furthermore, the evaluation has shown that the method proposed yields better results than statistical Bayes classification.

Conclusion: The proposed method can automatically fuse the benefits of intensity and vesselness information and can improve the results of following cerebrovascular segmentations.

Keywords

Magnetic resonance imaging - computer-assisted image analysis - cerebrovascular disorders - fuzzy logic - image enhancement

Full Text

References

References
1 Thrift A, Dewey H, Macdonell R, McNeil J, Donnan G. Incidence of the major stroke subtypes – initial findings from the north east Melbourne stroke incidence study (NEMESIS). Stroke 2001; 32 (08) 1732-1738.
2 Choi J, Mohr J. Brain arteriovenous malformations in adults. Lancet Neurol 2005; 4: 299-308.
3 Fiehler J, Illies T, Piening M, Säring D, Forkert ND, Regelsberger J, Grzyska U, Handels H, Byrne JV. Territorial and Microvascular Perfusion Impairment in Brain Arteriovenous Malformations. Am J Neuroradiol 2009; 30: 356-361.
4 Handels H, Ehrhardt J. Medical image computing for computer-supported diagnostics and therapy. Methods Inf Med 2009; 48 (01) 11-17.
5 Wilson D, Noble J. An adaptive segmentation algorithm for time-of-flight MRA data. IEEE Trans Med Imaging 1999; 18 (10) 938-945.
6 Hassouna MS, Farag A, Hushek S, Moriarty T. Cerebrovascular segmentation from TOF using stochastic models. Med Image Anal 2006; 10 (01) 2-18.
7 Chapman B, Stapelton J, Parker D. Intracranial vessel segmentation from time-of-flight MRA using pre-processing of the MIP Z-buffer: accuracy of the ZBS algorithm. Med Image Anal 2004; 8 (02) 113-126.
8 Sato Y, Nakajima S, Shiraga N, Atsumi H, Yoshida S, Koller T, Gerig G, Kikinis R. Three-dimensional multi-scale line filter for segmentation and visualization of curvelinear structures in medical images. Med Image Anal 1998; 2 (02) 143-168.
9 Frangi AF, Niessen WJ, Vincken KL, Viergever MA. Multiscale vessel enhancement filtering. Lect Notes Comp Sci 1998; 1496: 130-137.
10 Lorenz C, Carlsen IC, Buzug TM, Fassnacht C, Weese J. A multi-scale line filter with automatic scale selection based on the Hessian matrix for medical image segmentation. In: Proceedings of Scale-Space Theory in Computer Vision; 1997. pp 152-163.
11 Suri JS, Liu K, Reden L, Laxminarayan S. A review on MR vascular image processing algorithms: Skeleton vs. nonskeleton approaches. IEEE Trans Inf Tech Biomed 2002; 6 (04) 338-350.
12 Kirbas C, Quek FKH. A review of vessel extraction techniques and algorithms. ACM Computing Surveys 2004; 36 (02) 81-121.
13 Kholmovski E, Alexander A, Parker D. Correction of slab boundary artifact using histogram matching. J Magn Reson Imaging 2002; 15: 610-617.
14 Whitaker R, Xue X. Variable-conductance, level-set curvature for image denoising. In: Proceedings of International Conference on Image Processing; 2001. pp 142-145.
15 Forkert ND, Säring D, Fiehler J, Illies T, Möller D, Handels H. Automatic brain segmentation in Time-of-Flight MRA images. Methods Inf Med 2009; 48 (05) 399-407.
16 Lalande A, Jaulent MC, Cherrak I, Brunotte F, Degoulet P. Quantifying stenosis in renal arterio-grams: A fuzzy syntactic analysis. Methods Inf Med 1999; 38: 207-213.
17 Mamdani EH, Assilian S. An experiment in linguistic synthesis with a fuzzy logic controller. Int J Man Mach Stud 1975; 7 (01) 135-147.
18 Ciofolo C, Barillot C, Hellier P. Combining fuzzy logic and level set methods for 3D MRI brain segmentation. In: of IEEE International Symposium on Biomedical Imaging 2004. pp 161-164.
19 Ibanez L, Schroeder W. The ITK Software Guide 2.4. Kitware; 2005
20 Schroeder W, Martin K, Lorensen B. Visualization Toolkit: An Object-Oriented Approach to 3D Graphics. 4th edition. Kitware; 2006
21 Sakai S, Kobayashi K, Nakamura J, Toyabe S, Akazawa K. Accuracy in the diagnostic prediction of acute appendicitis based on the bayesian network model. Methods Inf Med 2007; 46 (06) 723-726.
22 Duda RO, Hart PE, Stork DG. Pattern Classification. 2nd edition. New York: John Wiley & Sons; 2000
23 Schmidt-Richberg A, Handels H, Ehrhardt J. Integrated segmentation and non-linear registration for organ segmentation and motion field estimation in 4D CT data. Methods Inf Med 2009; 48 (04) 344-349.