Abstract
The visual detection of aneurysms in 3D angiographic datasets is very time-consuming and error-prone. Depending on the individual experience, up to 40% of all aneurysms are missed in the diagnostic routine. The aim of this work is to present a computer-aided method for the automatic detection of aneurysm candidates in 3D MRA datasets. In this approach, the cerebrovascular system is automatically segmented in a first step and used for identification of vessel endpoints, which are used as an initial aneurysm candidate sample. In a following step, a number of morphological and structural parameters are calculated for each candidate. Finally, a support vector machine (SVM) is applied for reducing the number of aneurysm candidates based on the extracted parameters. The proposed method was evaluated based on 20 Time-of-Flight MRA datasets of patients with an aneurysm using linear as well as radial basis function kernels for SVM training. Leave-one-out cross validation revealed that the linear kernel SVM leads to better results, achieving a sensitivity of 100% and a concurrent false-positive rate of 3.86. In conclusion, the proposed method may help to improve and speed-up the aneurysm screening in clinical practice.
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
Preview
Unable to display preview. Download preview PDF.
References
Donnan, G.A., Fisher, M., Macleod, M., Davis, S.M.: Stroke. The Lancet 371, 1612–1623 (2008)
Thrift, A.G., Dewey, H.M., Macdonell, R.A., et al.: Incidence of the Major Stroke Subtypes - Initial Findings From the North East Melbourne Stroke Incidence Study (NEMESIS). Stroke 32(8), 1732–1738 (2001)
Okahara, M., Kiyosue, H., Yamashita, M., et al.: Diagnostic accuracy of magnetic resonance angiography for cerebral aneurysms in correlation with 3D-digital subtraction angiographic images: a study of 133 aneurysms. Stroke 33(7), 1803–1808 (2002)
Sato, Y., Nakajimaothers, S., Shiraga, N., et al.: Three-dimensional multi-scale line filter for segmentation and visualization of curvelinear structures in medical images. Med. Image Anal. 2(2), 143–168 (1998)
Forkert, N.D., Säring, D., Illies, T., et al.: Direction-Dependent Level Set Segmentation of Cerebrovascular Structures. In: Dawant, B.M., Haynor, D.R. (eds.) Image Processing, SPIE Medical Imaging 2011, vol. 7962, pp. 3S1–3S (2011)
Lee, T., Kashyap, R.L., Chu, C.: Building skeleton models via 3-D medial surface/axis thinning algorithms. CVGIP: Graph. Models Image Process. 56(6), 462–478 (1994)
Antiga, L.: Generalizing vesselness with respect to dimensionality and shape. The Insight Journal (2007)
Förstner, W., Gülch, E.: A fast operator for detection and precise location of distinct points, corners and centres of circular features. In: ISPRS Intercommission Workshop Interlaken, pp. 281–305 (1987)
Joachims, T.: Making large-scale support vector machine learning practical. In: Schölkopf, B., Burges, C., Smola, A. (eds.) Advances in Kernel Methods, pp. 169–184. MIT Press, Cambridge (1999)
Lauric, A.: Automated Detection and Classification of Intracranial Aneurysms based on 3D Surface Analysis. PhD Thesis, Tufts University (2010)
Hentschke, C.M., Beuing, O., Nickl, R., Tonnies, K.D.: Automatic cerebral aneurysm detection in multimodal angiographic images. In: Nuclear Science Symposium and Medical Imaging Conference, pp. 3116–3120 (2011)
Yang, X., Blezek, D.J., Cheng, L.T.: Computer-aided detection of intracranial aneurysms in MR angiography. J. Digit. Imaging 24(1), 86–95 (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Suniaga, S., Werner, R., Kemmling, A., Groth, M., Fiehler, J., Forkert, N.D. (2012). Computer-Aided Detection of Aneurysms in 3D Time-of-Flight MRA Datasets. In: Wang, F., Shen, D., Yan, P., Suzuki, K. (eds) Machine Learning in Medical Imaging. MLMI 2012. Lecture Notes in Computer Science, vol 7588. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-35428-1_8
Download citation
DOI: https://doi.org/10.1007/978-3-642-35428-1_8
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-35427-4
Online ISBN: 978-3-642-35428-1
eBook Packages: Computer ScienceComputer Science (R0)