Abstract
Liver segmentation is an essential procedure in computer-assisted surgery, radiotherapy, and volume measurement. It is still a challenging task to extract liver tissue from 3D CT images owing to nearby organs with similar intensities. In this paper, an automatic approach integrating multi-dimensional features into graph cut refinement is developed and validated. Multi-atlas segmentation is utilized to estimate the coarse shape of liver on the target image. The unsigned distance field based on initial shape is then calculated throughout the whole image, which aims at automatic graph construction during refinement procedure. Finally, multi-dimensional features and shape constraints are embedded into graph cut framework. The optimal liver region can be precisely detected with a minimal cost. The proposed technique is evaluated on 40 CT scans, obtained from two public databases Sliver07 and 3Dircadb1. The dataset Sliver07 is considered as the training set for parameter learning. On the dataset 3Dircadb1, the average of volume overlap is up to 94%. The experiment results indicate that the proposed method has ability to reach the desired boundary of liver and has potential value for clinical application.
Highlights
The extraction of liver tissue is very important for hepatic disease diagnosis, function assessment, and computer-assisted surgery[1]
It is obvious that registration quality using the free-form deformation (FFD) model is higher than that of using the affine model, which indicates that the former one could well represent soft tissue deformation
We have developed a novel approach for automatic liver segmentation, which integrates the initial shape and multi-dimensional graph cut
Summary
The extraction of liver tissue is very important for hepatic disease diagnosis, function assessment, and computer-assisted surgery[1]. Among the various medical imaging techniques, computed tomography (CT) is often used for these purposes due to higher signal-to-noise ratio and better spatial resolution It is tedious and time-consuming to get liver regions by manual delineation from several thousand slices. To preserve liver shape from the adjacent organs with similar intensities, statistical shape model (SSM)[4] is often incorporated into these approaches. Erdt et al combined learned local shape priors with constraints for liver CT segmentation, in order to restrict adaptation to regions with large deformations[6]. An automatic algorithm including initial process of a probabilistic atlas with the posteriori classification and following extraction based on level set was developed for liver segmentation[13]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
