Abstract
Automatic labeling of cerebrovascular territories would greatly advance our ability to systematically study large datasets and also provide rapid decision support during the assessment of stroke patients, for example. Previous attempts have been challenged by the wide inter-subject variation in vascular topography. We investigate the use of a probabilistic model that learns the configurational characteristics of vascular territories to better annotate the cerebrovasculature. In the George Mason Brain Vasculature database, we identified patients with MRA reconstructions segmented into seven major regions (left and right MCA, PCA, and ACA and Circle of Willis). We then augmented these labels by manually segmenting the MCA territory into an additional eight regions. Among 54 patients that met the inclusion criteria, 39 reconstructions were used as training input to the MCA, ACA, and PCA model among the 61 digital reconstructions of human brain arterial structures available. The model was then validated on an independent cohort of 15 patients. The MCA segmentation algorithm was trained and tested using leave-one-out crossvalidation. The algorithm was found to be \(94 \pm 5.2\,\%\) accurate in annotating the seven major regions and \(88 \pm 9.3\,\%\) accurate in annotating the MCA subterritories.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Dufour, A., Ronse, C., Baruthio, J., Tankyevych, O., Talbot, H., Passat, N.: Morphology-based cerebrovascular atlas. In: ISBI, pp. 1210–1214 (2013)
Ghanavati, S., Lerch, J.P., Sled, J.G.: Automatic anatomical labeling of the complete cerebral vasculature in mouse models. Neuroimage 95, 117–128 (2014)
Ghanavati, S., Lerch, J.P., Sled, J.G.: Improved method for automatic cerebrovascular labelling using stochastic tunnelling. In: International Workshop on Pattern Recognition in Neuroimaging, pp. 1–4 (2014)
Ihler, A.T., Fisher, J.W., Willsky, A.S.: Message errors in belief propagation. In NIPS, no. 17, pp. 609–616. MIT Press (2005)
Mut, F., Wright, S., Ascoli, G.A., Cebral, J.R.: Morphometric, geographic, and territorial characterization of brain arterial trees. Int. J. Numer. Method Biomed. Eng. 30(7), 755–766 (2014)
Oda, M., Hoang, B.H., Kitasaka, T., Misawa, K., Fujiwara, M., Mori, K.: Automated anatomical labeling method for abdominal arteries extracted from 3D abdominal CT images (2012)
Osborn, A.: Osborn’s Brain: Imaging, Pathology, and Anatomy. Amirsys Pub., Salt Lake City (2013)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann Publishers Inc., San Francisco (1988)
Peng, H., Ruan, Z., Long, F., Simpson, J.H., Myers, E.W.: V3D enables real-time 3D visualization and quantitative analysis of large-scale biological image data sets. Nat. Biotechnol. 28(4), 348–353 (2010)
Scalzo, F., Piater, J.H.: Statistical learning of visual feature hierarchies. In: CVPR, p. 44 (2005)
Scalzo, F., Piater, J.H.: Unsupervised learning of visual feature hierarchies. In: Perner, P., Imiya, A. (eds.) MLDM 2005. LNCS (LNAI), vol. 3587, pp. 243–252. Springer, Heidelberg (2005)
Scalzo, F., Piater, J.H.: Adaptive patch features for object class recognition with learned hierarchical models. In: CVPR, pp. 1–8 (2007)
Shahzad, R., Dzyubachyk, O., Staring, M., Kullberg, J., Johansson, L., Ahlstrom, H., Lelieveldt, B.P., van der Geest, R.J.: Automated extraction and labelling of the arterial tree from whole-body MRA data. Med. Image Anal. 24(1), 28–40 (2015)
Stefancik, R., Sonka, M.: Highly automated segmentation of arterial and venous trees from three-dimensional magnetic resonance angiography (MRA). Int. J. Cardiovasc. Imaging 17(1), 37–47 (2001)
Uchiyama, Y., Yamauchi, M., Ando, H., Yokoyama, R., Hara, T., Fujita, H., Iwama, T., Hoshi, H.: Automated classification of cerebral arteries in MRA images and its application to maximum intensity projection. IEEE Eng. Med. Biol. Soc. 1, 4865–4868 (2006)
Wang, J., Cohen, M.F.: An iterative optimization approach for unified image segmentation and matting. In: ICCV, vol. 2, pp. 936–943 (2005)
Wright, S.N., Kochunov, P., Mut, F., Bergamino, M., Brown, K.M., Mazziotta, J.C., Toga, A.W., Cebral, J.R., Ascoli, G.A.: Digital reconstruction and morphometric analysis of human brain arterial vasculature from magnetic resonance angiography. Neuroimage 82, 170–181 (2013)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Quachtran, B., Sheth, S., Saver, J.L., Liebeskind, D.S., Scalzo, F. (2015). Probabilistic Labeling of Cerebral Vasculature on MR Angiography. In: Bebis, G., et al. Advances in Visual Computing. ISVC 2015. Lecture Notes in Computer Science(), vol 9474. Springer, Cham. https://doi.org/10.1007/978-3-319-27857-5_49
Download citation
DOI: https://doi.org/10.1007/978-3-319-27857-5_49
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-27856-8
Online ISBN: 978-3-319-27857-5
eBook Packages: Computer ScienceComputer Science (R0)