ABSTRACT
Region Growing is frequently used for segmentation purposes especially for objects with homogenous intensity. The problem is how the region growing approach begins, how it proceeds and how it finally ends. In this paper we present a modified region growing approach for the purpose of automatic segmentation of the ascending aorta from Computed Tomography Angiography (CTA) images. The ascending aorta in CTA images has homogenous intensity which makes region growing a good approach for its segmentation. Moreover the approach presented in this paper is fully automatic to suit clinical non-invasive diagnosis purposes. For developing our region growing approach; the geometric, spatial and intensity features of the ascending aorta has been exploited. These features provide the region growing methodology with the automatic seed from which it begins and then continues to segment the whole ascending aorta from the aortic arch down to ostia points. The proposed algorithm is tested and validated on the Computed Tomography Angiography database provided by the Rotterdam Coronary Artery Algorithm Evaluation Framework. The proposed algorithm has three main advantages: 1) it's fully automatic, i.e. no user interaction needed, 2) real-time performance even with large datasets, 3) robust since parameters values are the same for all the tested datasets.
- Rolf Adams and Leanne Bischof. 1994. Seeded region growing. Pattern Analysis and Machine Intelligence, IEEE Transactions on 16, 6: 641--647. Google ScholarDigital Library
- Susanne Bock, Caroline Kühnel, Tobias Boskamp, and Heinz-Otto Peitgen. 2008. Robust vessel segmentation. Medical Imaging, 691539.Google Scholar
- Bessem Bouraoui, Christian Ronse, Joseph Baruthio, Nicolas Passat, and Ph Germain. 2008. Fully automatic 3D segmentation of coronary arteries based on mathematical morphology. Biomedical Imaging: From Nano to Macro, 2008. ISBI 2008. 5th IEEE International Symposium on, 1059--1062.Google Scholar
- CIBC. 2014. ImageVis3D: An interactive visualization software system for large-scale volume data. Retrieved from http://www.imagevis3d.orgGoogle Scholar
- Raimund Erbel and Holger Eggebrecht. 2006. Aortic dimensions and the risk of dissection. Heart 92, 1: 137--142.Google ScholarCross Ref
- Anja Hennemuth, Tobias Boskamp, D Fritz, et al. 2005. One-click coronary tree segmentation in CT angiographic images. International Congress Series, 317--321.Google ScholarCross Ref
- Pieter H Kitslaar, Michel Frenay, Elco Oost, Jouke Dijkstra, Berend Stoel, and Johan H C Reiber. 2008. Connected Component and Morpholgy Based Extraction of Arterial Centerlines of the Heart (CocomoBeach). The MIDAS Journal: MICCAI Workshop--Grand Challenge Coronary Artery Tracking.Google Scholar
- Stefan C Saur, Caroline Kühhnel, Tobias Boskamp, Gábor Székely, and Philippe Cattin. 2008. Automatic ascending aorta detection in CTA datasets. In Bildverarbeitung für die Medizin 2008. Springer, 323--327.Google Scholar
- Michiel Schaap, Coert T Metz, Theo van Walsum, et al. 2009. Standardized evaluation methodology and reference database for evaluating coronary artery centerline extraction algorithms. Medical image analysis 13, 5: 701--714.Google Scholar
- Chunliang Wang and Orjan Smedby. 2008. An automatic seeding method for coronary artery segmentation and skeletonization in CTA. The Insight Journal: 1--8.Google Scholar
- Shengjun Wang, Ling Fu, Yong Yue, Yan Kang, and Jiren Liu. 2009. Fast and Automatic Segmentation of Ascending Aorta in MSCT Volume Data. 2009 2nd International Congress on Image and Signal Processing d: 1--5. http://doi.org/10.1109/CISP.2009.5305569Google Scholar
- Raymond K K Yip, Peter K S Tam, and Dennis N K Leung. 1992. Modification of Hough Transform For Circles And Ellipses Detection Using A 2-Dimensional Array. 25, 9: 1007--1022.Google Scholar
- Yefeng Zheng, Senior Member, Matthias John, et al. 2012. Automatic Aorta Segmentation and Valve Landmark Detection in C-Arm CT for Transcatheter Aortic Valve Implantation. 31, 12: 2307--2321.Google Scholar
- 2014. Structure of the aorta, Digital Image. Retrieved October 20, 2014 from http://o.quizlet.com/Jprs34pMgWdtO6BOmfRVLQ_m.jpgGoogle Scholar
Recommendations
An inverse approach for automatic segmentation of carotid and vertebral arteries in CTA
The aim is to make the experts able to evaluate stenosis degree.Experts can make quantitative and qualitative analyze easily with proposed method.We proposed a novel automatic vessel segmentation with inverse approach.Firstly the bone region was ...
Myocardial segmentation using constrained multi-seeded region growing
ICIAR'10: Proceedings of the 7th international conference on Image Analysis and Recognition - Volume Part IIMulti-slice short-axis acquisitions of the left ventricle are fundamental for estimating the volume and mass of the left ventricle in cardiac MRI scans. Manual segmentation of the myocardium in all time frames per each cross-section is a cumbersome ...
Automatic Segmentation of Coronary Arteries Based on Region Growing and Discrete Wavelet Transformation
CMCSN '12: Proceedings of the 2012 International Conference on Computing, Measurement, Control and Sensor NetworkIn this work, we proposed a new method for segmenting coronary arteries automatically in computed tomography angiography (CTA) data sets which allows the coronary pathologies to be reliably detected. Region growing is firstly applied to give the initial ...
Comments