Automatic Hepatic Vessel Segmentation Using Graphics Hardware
The accurate segmentation of liver vessels is an important prerequisite for creating oncologic surgery planning tools as well as medical visualization applications. In this paper, a fully automatic approach is presented to quickly enhance and extract the
- PDF / 2,045,556 Bytes
- 10 Pages / 430 x 660 pts Page_size
- 106 Downloads / 245 Views
Fraunhofer Institute for Computer Graphics, Cognitive Computing & Medical Imaging, Fraunhoferstrasse 5, 64283 Darmstadt, Germany [email protected] 2 University of Koblenz-Landau, Institute of Computational Visualistics, Universitaetsstrasse 1, 56070 Koblenz, Germany 3 Siemens Medical Solutions, Computed Tomography: Physics & Applications, Siemensstrasse 1, 91301 Forchheim, Germany
Abstract. The accurate segmentation of liver vessels is an important prerequisite for creating oncologic surgery planning tools as well as medical visualization applications. In this paper, a fully automatic approach is presented to quickly enhance and extract the vascular system of the liver from CT datasets. Our framework consists of three basic modules: vessel enhancement on the graphics processing unit (GPU), automatic vessel segmentation in the enhanced images and an option to verify and refine the obtained results. Tests on 20 clinical datasets of varying contrast quality and acquisition phase were carried out to evaluate the robustness of the automatic segmentation. In addition the presented GPU based method was tested against a CPU implementation to demonstrate the performance gain of using modern graphics hardware. Automatic segmentation using graphics hardware allows reliable and fast extraction of the hepatic vascular system and therefore has the potential to save time for oncologic surgery planning. Keywords: Segmentation, Automation, Computed Tomography, Graphics Hardware, Hepatic Vessels.
1
Introduction
Shape and location of the intrahepatic vessels are of significant importance to liver surgery. Modern minimal invasive operation methods like laser surgery as well as established surgical intervention techniques require the detection of vessels with a diameter down to 2 mm to decide whether an operation can be realised or not. In order to develop oncologic operation planning tools it is necessary to segment the vessel systems of the liver in a pre-computing step. Therefore, contrast agents are injected in the bloodstream to raise the opacity of those structures and make them appear bright in the CT scan. However, the distribution of the agent and hence the quality of the contrast between the vessels and the liver-tissue depends on the point of time the scan is started. This leads to heavily varying T. Dohi, I. Sakuma, and H. Liao (Eds.): MIAR 2008, LNCS 5128, pp. 403–412, 2008. c Springer-Verlag Berlin Heidelberg 2008
404
M. Erdt, M. Raspe, and M. Suehling
results regarding the amount of contrast in the image. Usually filter based methods are used to enhance the quality of CT images since they can be applied as soon as the image comes out of the machine and require no user interaction. In [1] gaussian/median filters are used to intensify the liver vessels. However, those filters are insufficient to enhance low contrasted CT images since image details and therefore small vessels may get lost. A common approach is to model the vessels locally as tube like objects and applying hessian based eigenanalysis to find those str
Data Loading...
