Automatic 3D Segmentation and Quantification of Lenticulostriate Arteries from High-Resolution 7 Tesla MRA Images
Pages 400 - 413
Abstract
We propose a novel hybrid approach for automatic 3D segmentation and quantification of high-resolution 7 Tesla magnetic resonance angiography (MRA) images of the human cerebral vasculature. Our approach consists of two main steps. First, a 3D model-based approach is used to segment and quantify thick vessels and most parts of thin vessels. Second, remaining vessel gaps of the first step in low-contrast and noisy regions are completed using a 3D minimal path approach, which exploits directional information. We present two novel minimal path approaches. The first is an explicit approach based on energy minimization using probabilistic sampling, and the second is an implicit approach based on fast marching with anisotropic directional prior. We conducted an extensive evaluation with over 2300 3D synthetic images and 40 real 3D 7 Tesla MRA images. Quantitative and qualitative evaluation shows that our approach achieves superior results compared with a previous minimal path approach. Furthermore, our approach was successfully used in two clinical studies on stroke and vascular dementia.
References
[1]
G. Román, T. Erkinjuntti, A. Wallin, L. Pantoni, and H. C. Chui, “Subcortical ischaemic vascular dementia,” Lancet Neurol., vol. 1, no. 7, pp. 426–436, 2002.
[2]
Z.-H. Cho et al., “Observation of the lenticulostriate arteries in the human brain in vivo using 7.0T MR angiography,” Stroke, vol. 39, no. 5, pp. 1604–1606, 2008.
[3]
A. I. Qureshi, S. Tuhrim, J. P. Broderick, H. H. Batjer, H. Hondo, and D. F. Hanley, “Spontaneous intracerebral hemorrhage,” New England J. Med., vol. 344, pp. 1450–1460, 2001.
[4]
J. T. Heverhagen, E. Bourekas, S. Sammet, M. V. Knopp, and P. Schmalbrock, “Time-of-flight magnetic resonance angiography at 7 Tesla,” Invest. Radiol., vol. 43, no. 8, pp. 568–573, 2008.
[5]
A. F. Frangi, W. J. Niessen, K. L. Vincken, and M. A. Viergever, “Multiscale vessel enhancement filtering,” in Proc. 1st Int. Conf. Med. Image Comput. Comput.-Assist. Intervent. (MICCAI) ser. Lecture Notes in Computer Science, vol. 1496. Cambridge, MA, USA, Oct. 1998, pp. 130–137.
[6]
Y. Sato et al., “Three-dimensional multi-scale line filter for segmentation and visualization of curvilinear structures in medical images,” Med. Image Anal., vol. 2, no. 2, pp. 143–168, 1998.
[7]
A. Vasilevskiy and K. Siddiqi, “Flux maximizing geometric flows,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 24, no. 12, pp. 1565–1578, Dec. 2002.
[8]
R. Manniesing, M. A. Viergever, and W. J. Niessen, “Vessel enhancing diffusion: A scale space representation of vessel structures,” Med. Image Anal., vol. 10, no. 6, pp. 815–825, 2006.
[9]
M. W. K. Law and A. C. S. Chung, “Three dimensional curvilinear structure detection using optimally oriented flux,” in Proc. 10th Eur. Conf. Comput. Vis. (ECCV) ser. Lecture Notes in Computer Science, vol. 5305. Marseille, France, Oct. 2008, pp. 368–382.
[10]
L. M. Lorigo et al., “CURVES: Curve evolution for vessel segmentation,” Med. Image Anal., vol. 5, no. 3, pp. 195–206, 2001.
[11]
M. Holtzman-Gazit, R. Kimmel, N. Peled, and D. Goldsher, “Segmentation of thin structures in volumetric medical images,” IEEE Trans. Image Process., vol. 15, no. 2, pp. 354–363, Feb. 2006.
[12]
M. Hernandez and A. F. Frangi, “Non-parametric geodesic active regions: Method and evaluation for cerebral aneurysms segmentation in 3DRA and CTA,” Med. Image Anal., vol. 11, no. 3, pp. 224–241, 2007.
[13]
S. Wörz and K. Rohr, “Segmentation and quantification of human vessels using a 3D cylindrical intensity model,” IEEE Trans. Image Process., vol. 16, no. 8, pp. 1994–2004, Aug. 2007.
[14]
X. Wu, V. Luboz, K. Krissian, S. Cotin, and S. Dawson, “Segmentation and reconstruction of vascular structures for 3D real-time simulation,” Med. Image Anal., vol. 15, no. 1, pp. 22–34, 2011.
[15]
L. D. Cohen and R. Kimmel, “Global minimum for active contour models: A minimal path approach,” Int. J. Comput. Vis., vol. 24, no. 1, pp. 57–78, 1997.
[16]
J. A. Sethian, “A fast marching level set method for monotonically advancing fronts,” Proc. Nat. Acad. Sci. USA, vol. 93, no. 4, pp. 1591–1595, 1996.
[17]
Q. Lin, “Enhancement, extraction, and visualization of 3D volume data,” Ph.D. dissertation, Dept. Elect. Eng., Linköping Univ., Linköping, Sweden, 2003.
[18]
M. Poon, G. Hamarneh, and R. Abugharbieh, “Live-vessel: Extending livewire for simultaneous extraction of optimal medial and boundary paths in vascular images,” in Proc. 10th Int. Conf. Med. Image Comput. Comput.-Assist. Intervent. (MICCAI) ser. Lecture Notes in Computer Science, vol. 4792. Brisbane, Australia, Nov. 2007, pp. 444–451.
[19]
H. Li and A. Yezzi, “Vessels as 4D curves: Global minimal 4D paths to extract 3D tubular surfaces and centerlines,” IEEE Trans. Med. Imag., vol. 26, no. 9, pp. 1213–1223, Sep. 2007.
[20]
S. Jbabdi, P. Bellec, R. Toro, J. Daunizeau, M. Pélégrini-Issac, and H. Benali, “Accurate anisotropic fast marching for diffusion-based geodesic tractography,” Int. J. Biomed. Imag., vol. 2008, pp. 1–12, Jan. 2008.
[21]
M. Pechaud, R. Keriven, and G. Peyre, “Extraction of tubular structures over an orientation domain,” in Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. (CVPR), vol. 1. Miami, FL, USA, Jun. 2009, pp. 336–342.
[22]
F. Benmansour and L. D. Cohen, “Fast object segmentation by growing minimal paths from a single point on 2D or 3D images,” J. Math. Imag. Vis., vol. 33, no. 2, pp. 209–221, 2009.
[23]
P. Lo, B. van Ginneken, and M. de Bruijne, “Vessel tree extraction using locally optimal paths,” in Proc. 7th IEEE Int. Symp. Biomed. Imag., Nano Macro (ISBI), Rotterdam, The Netherlands, Apr. 2010, pp. 680–683.
[24]
V. S. Joshi, M. K. Garvin, J. M. Reinhardt, and M. D. Abramoff, “Identification and reconnection of interrupted vessels in retinal vessel segmentation,” in Proc. 8th IEEE Int. Symp. Biomed. Imag., Nano Macro (ISBI), Chicago, IL, USA, Mar./Apr. 2011, pp. 1416–1420.
[25]
F. Benmansour and L. D. Cohen, “Tubular structure segmentation based on minimal path method and anisotropic enhancement,” Int. J. Comput. Vis., vol. 92, no. 2, pp. 192–210, 2011.
[26]
M. Freiman et al., “Vessels-Cut: A graph based approach to patient-specific carotid arteries modeling,” in Proc. 3D Physiol. Human Workshop (3DPH) ser. Lecture Notes in Computer Science, vol. 5903. Zermatt, Switzerland, Nov. 2009, pp. 1–12.
[27]
N. D. Forkert, A. Schmidt-Richberg, D. Säring, T. Illies, J. Fiehler, and H. Handels, “Closing of interrupted vascular segmentations: An automatic approach based on shortest paths and level sets,” Proc. SPIE, vol. 7623, p. 76233G, Feb. 2010.
[28]
S. Esneault, C. Lafon, and J.-L. Dillenseger, “Liver vessels segmentation using a hybrid geometrical moments/graph cuts method,” IEEE Trans. Biomed. Eng., vol. 57, no. 2, pp. 276–283, Feb. 2010.
[29]
Y. Shang et al., “Vascular active contour for vessel tree segmentation,” IEEE Trans. Biomed. Eng., vol. 58, no. 4, pp. 1023–1032, Apr. 2011.
[30]
C. Kirbas and F. Quek, “A review of vessel extraction techniques and algorithms,” ACM Comput. Surv., vol. 36, no. 2, pp. 81–121, 2004.
[31]
D. Lesage, E. D. Angelini, I. Bloch, and G. Funka-Lea, “A review of 3D vessel lumen segmentation techniques: Models, features and extraction schemes,” Med. Image Anal., vol. 13, no. 6, pp. 819–845, 2009.
[32]
M. Niethammer and C. Zach, “Segmentation with area constraints,” Med. Image Anal., vol. 17, no. 1, pp. 101–112, 2013.
[33]
A. Blake, P. Kohli, and C. Rother, Eds., Markov Random Fields for Vision and Image Processing. Cambridge, MA, USA: MIT Press, 2011.
[34]
W. L. Nowinski, B. C. Chua, Y. Marchenko, F. Puspitsari, I. Volkau, and M. V. Knopp, “Three-dimensional reference and stereotactic atlas of human cerebrovasculature from 7 Tesla,” NeuroImage, vol. 55, no. 3, pp. 986–998, 2011.
[35]
P. van Ooij et al., “Quantification and visualization of flow in the Circle of Willis: Time-resolved three-dimensional phase contrast MRI at 7 T compared with 3 T,” Magn. Reson. Med., vol. 69, no. 3, pp. 868–876, 2013.
[36]
P. J. Koopmans, R. Manniesing, W. J. Niessen, M. A. Viergever, and M. Barth, “MR venography of the human brain using susceptibility weighted imaging at very high field strength,” Magn. Reson. Mater. Phys., Biol. Med., vol. 21, no. 1, pp. 149–158, 2008.
[37]
G. Grabner, A. Dal-Bianco, S. Hametner, H. Lassmann, and S. Trattnig, “Group specific vein-atlasing: An application for analyzing the venous system under normal and multiple sclerosis conditions,” J. Magn. Reson. Imag., vol. 40, no. 3, pp. 655–661, 2014.
[38]
K. T. Diedrich, J. A. Roberts, R. H. Schmidt, C.-K. Kang, Z.-H. Cho, and D. L. Parker, “Validation of an arterial tortuosity measure with application to hypertension collection of clinical hypertensive patients,” BMC Bioinform., vol. 12, no. 10, p. S15, 2011.
[39]
W. Liao, K. Rohr, C.-K. Kang, Z.-H. Cho, and S. Wörz, “A generative MRF approach for automatic 3D segmentation of cerebral vasculature from 7 Tesla MRA images,” in Proc. 8th IEEE Int. Symp. Biomed. Imag., Nano Macro (ISBI), Chicago, IL, USA, Mar./Apr. 2011, pp. 2041–2044.
[40]
W. Liao, K. Rohr, C.-K. Kang, Z.-H. Cho, and S. Wörz, “Automatic human brain vessel segmentation from 3D 7 Tesla MRA images using fast marching with anisotropic directional prior,” in Proc. 9th IEEE Int. Symp. Biomed. Imag., Nano Macro (ISBI), Barcelona, Spain, May 2012, pp. 1140–1143.
[41]
S. Wörz and K. Rohr, “3D adaptive model-based segmentation of human vessels,” Proc. SPIE, vol. 6511, p. 65110Q, Feb. 2007.
[42]
C.-K. Kang et al., “Three dimensional model-based analysis of the lenticulostriate arteries and identification of the vessels correlated to the infarct area: Preliminary results,” Int. J. Stroke, vol. 7, no. 7, pp. 558–563, 2012.
[43]
S. W. Seo et al., “Measurements of lenticulostriate arteries using 7T MRI: New imaging markers for subcortical vascular dementia,” J. Neurol. Sci., vol. 322, nos. 1–2, pp. 200–205, 2012.
Index Terms
- Automatic 3D Segmentation and Quantification of Lenticulostriate Arteries from High-Resolution 7 Tesla MRA Images
Index terms have been assigned to the content through auto-classification.
Recommendations
Vasculature Segmentation in MRA Images Using Gradient Compensated Geodesic Active Contours
Precise segmentation of vasculature from three-dimensional (3D) magnetic resonance angiography (MRA) images is playing an important role in image-guided neurosurgery, pre-operation planning and clinical analysis. Active Contour based evolution ...
Role of the vessel morphology on the lenticulostriate arteries hemodynamics during atrial fibrillation: A CFD-based multivariate regression analysis
Highlights- Hemodynamic alterations due to atrial fibrillation (AF) increase the risk of dementia.
- Lenticulostriate arteries (LSAs) are susceptible to vascular dementia development.
- We combined MRI-based computational fluid dynamics and ...
Abstract Background and objectiveAtrial fibrillation (AF) is the most common cardiac arrhythmia, inducing accelerated and irregular beating. Beside well-known disabling symptoms - such as palpitations, reduced exercise tolerance, and chest discomfort - ...
Automatic 3D Aorta Segmentation in CT Images
ICBEB 2018: Proceedings of the 2nd International Conference on Biomedical Engineering and BioinformaticsCardiovascular disease is one of the most common high incidence diseases, which leads to the urgent demand of 3D aorta shape reconstruction with CT images for help doctors making effective and accurate diagnosis. In literature, 3D aorta reconstruction ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
Copyright © 2015.
Publisher
IEEE Press
Publication History
Published: 01 January 2016
Qualifiers
- Research-article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 12 Jan 2025