Graph Partitioning based Automatic Segmentation Approach for CT Scan Liver Images

Citation:
Elmasry, W. H., H. M. Moftah, N. El-Bendary, and A. E. Hassanien, "Graph Partitioning based Automatic Segmentation Approach for CT Scan Liver Images", IEEE Federated Conference on Computer Science and Information Systems, pp. 205–208, Wroclaw - Poland , 9-13 Sept, 2012.

Date Presented:

9-13 Sept

Abstract:

Manual segmentation of liver computerized tomography (CT) images is very time consuming, so it is desired to develop a computer-based approach for the analysis of liver
CT images that can precisely segment the liver without any human intervention. This paper presents normalized cuts graph partitioning approach for liver segmentation from CT images. To evaluate the performance of the presented approach, we present tests on different liver CT images. Experimental results obtained show that the overall accuracy offered by the employed normalized cuts technique is high compared to the well known K-means segmentation approach.

Manual segmentation of liver computerized tomography (CT) images is very time consuming, so it is desired to develop a computer-based approach for the analysis of liver
CT images that can precisely segment the liver without any human intervention. This paper presents normalized cuts graph partitioning approach for liver segmentation from CT images. To evaluate the performance of the presented approach, we
present tests on different liver CT images. Experimental results obtained show that the overall accuracy offered by the employed normalized cuts technique is high compared to the well known K-means segmentation approach.

Tourism