An Automated Segmentation and Classification Framework for CT-Based Myocardial Perfusion Imaging for Detecting Myocardial Perfusion Defect
Thanks to the recent development of the high-resolution and high-speed multi-sliced CT, CT-based perfusion imaging has become possible. In this paper, we have developed a 320-MDCT-based perfusion imaging framework to detect myocardial ischemia. We designed a rest/stress perfusion imaging protocol, developed an automated LV segmentation algorithm, and adapted a LDA-based classifier to predict myocardial ischemia using the intensity profiles in rest perfusion images. Experiments were done on 6 stress/rest CT perfusion data sets from patients with obstructive coronary artery disease (CAD) and 6 rest CT perfusion data sets from normal subjects. Experimental results have shown that rest perfusion images have the potential of accurately predicting ischemia caused by obstructive CAD.
KeywordsMyocardial Perfusion Myocardial Perfusion Imaging Perfusion Imaging Linear Discriminant Analysis Obstructive Coronary Artery Disease
- 2.George, R., Arbab-Zadeh, A., Miller, J., et al.: Adenosine stress 64- and 256-row detector computed tomography angiography and perfusion imaging: a pilot study evaluating the transmural extent of perfusion abnormalities to predict atherosclerosis causing myocardial ischemia. Circ. Cardiovasc Imaging 2(3), 174–182 (2009)CrossRefGoogle Scholar
- 3.Qian, Z., Vasquez, G., et al.: Validation of quantitative vasodilator stress-rest 320-detector row volumetric ct perfusion imaging against invasive x-ray coronary angiography and fractional flow reserve measurements. In: Annual Scientific Meeting of Society of Cardiovascular Computed Tomography (2010)Google Scholar
- 4.Metaxas, D.: Physics-Based Deformable Models. Kluwer Academic Publishers, Dordrecht (1996)Google Scholar
- 8.Zheng, Y., Georgescu, B., Barbu, A., Scheuering, M., Comaniciu, D.: Four-chamber heart modeling and automatic segmentation for 3D cardiac CT volumes. In: SPIE, Medical Imaging, vol. 6914 (2008)Google Scholar
- 10.Li, C., Huang, R., Ding, Z., Gatenby, C., Metaxas, D., Gore, J.: A variational level set approach to segmentation and bias correction of images with intensity inhomogeneity. In: Metaxas, D., Axel, L., Fichtinger, G., Székely, G. (eds.) MICCAI 2008, Part II. LNCS, vol. 5242, pp. 1083–1091. Springer, Heidelberg (2008)CrossRefGoogle Scholar