Abstract
Segmenting a liver and its peripherals from abdominal computed tomography is a crucial step toward computer aided diagnosis and therapeutic intervention. Despite the recent advances in computing methods, faithfully segmenting the liver has remained a challenging task, due to indefinite boundary, intensity inhomogeneity, and anatomical variations across subjects. In this paper, a semi-automatic segmentation method based on multivariable normal distribution of liver tissues and graph-cut sub-division is presented. Although it is not fully automated, the method minimally involves human interactions. Specifically, it consists of three main stages. Firstly, a subject specific probabilistic model was built from an interior patch, surrounding a seed point specified by the user. Secondly, an iterative assignment of pixel labels was applied to gradually update the probabilistic map of the tissues based on spatio-contextual information. Finally, the graph-cut model was optimized to extract the 3D liver from the image. During post-processing, overly segmented nodal regions due to fuzzy tissue separation were removed, maintaining its correct anatomy by using robust bottleneck detection with adjacent contour constraint. The proposed system was implemented and validated on the MICCAI SLIVER07 dataset. The experimental results were benchmarked against the state-of-the-art methods, based on major clinically relevant metrics. Both visual and numerical assessments reported herein indicated that the proposed system could improve the accuracy and reliability of asymptomatic liver segmentation.
Highlights
In the absence of such information, semi-automatic segmentation required a user as a domain expert, to provide initial seed points, contours, surfaces, etc., in training a classifier[18], during subsequent processes[17,19,20,21,22], to make final adjustment[4,23,24,25,26,27,28,29]
18 asymptomatic livers from 20 labelled instances were segmented. Their Volumetric Overlap Error (VOE), Relative Volume Difference (RVD), Average Symmetric Surface Distance (ASD), RMSSD, Maximum Symmetric Surf−ace Distance (MSD), and respective and overall scores are reported in Table 4
Except errors, caused by ambiguous boundary between liver and other abdominal structures, which could only be elevated by means of statistically trained or deeply learnt models, the major cause of lower accuracies was due to inferior vena cava (IVC)
Summary
It is worth noted from the above rigorous investigations that, fully-automatic approach generally relied on statistically trained appearance models or on insights into liver morphology[10,11,12,13,14,15,16]. In the absence of such information, semi-automatic segmentation required a user as a domain expert, to provide initial seed points, contours, surfaces, etc., in training a classifier[18], during subsequent processes[17,19,20,21,22], to make final adjustment[4,23,24,25,26,27,28,29]. Due to inter-and intra-observer variabilities associated with these methods, extent to which user interaction was involved is one of the key determinants in benchmarking. A summary of state-of-the art methods is presented in Table 1a and b
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: 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.