Automatic Abdominal Organ Segmentation from CT images

Abstract

In the recent years a great deal of research work has been devoted to the development of semi-automatic and automatic techniques for the analysis of abdominal CT images. Some of the current interests are the automatic diagnosis of liver, spleen, and kidney pathologies and the 3D volume rendering of the abdominal organs. The first and fundamental step in all these studies is the automatic organs segmentation, that is still an open problem. In this paper we propose our fully automatic system that employs a hierarchical gray level based framework to segment heart, bones (i.e. ribs and spine), liver and its blood vessels, kidneys, and spleen. The overall system has been evaluated on the data of 100 patients, obtaining a good assessment both by visual inspection by three experts, and by comparing the computed results to the boundaries manually traced by experts.

Semiautomated spleen volumetry with diffusion‐weighted MR imaging

“…Recently, various computer‐aided methods for automatic or semiautomatic spleen volumetry have been proposed (13–19). In medical imaging, the segmentation accuracy depends a lot on the intensity contrast between the segmented and nearby organs when using image processing techniques (21, 22).…”

“…In medical imaging, the segmentation accuracy depends a lot on the intensity contrast between the segmented and nearby organs when using image processing techniques (21, 22). However, on CT images, organs near the spleen have similar densities with the spleen, and automatic segmentation often failed due to the incorrect inclusion of parts of nearby organs (13–18). Farraher et al (19) proposed the semiautomatic spleen segmentation on MR imaging.…”

“…Recently, semiautomatic or automatic methods of spleen volumetry with CT images have been proposed (13–18). In these methods, thresholding (13), machine learning (14), 2D atlas segmentation (15), 3D probabilistic atlas segmentation (16, 17), and registration of multiphase contrast CT images (18) were used on CT images.…”

“…Recently, semiautomatic or automatic methods of spleen volumetry with CT images have been proposed (13–18). In these methods, thresholding (13), machine learning (14), 2D atlas segmentation (15), 3D probabilistic atlas segmentation (16, 17), and registration of multiphase contrast CT images (18) were used on CT images. However, these computer‐aided volumetry lacked measurement accuracy because of the similar attenuation of nearby organs and severe patient‐to‐patient variations in the degree of contrast enhancement (13–18).…”

“…In these methods, thresholding (13), machine learning (14), 2D atlas segmentation (15), 3D probabilistic atlas segmentation (16, 17), and registration of multiphase contrast CT images (18) were used on CT images. However, these computer‐aided volumetry lacked measurement accuracy because of the similar attenuation of nearby organs and severe patient‐to‐patient variations in the degree of contrast enhancement (13–18). A semiautomatic method to measure the spleen volume has been proposed with MR images using a mixed fast spin‐echo pulse sequence (19).…”