Title
Segmentation using Sparse Shape Composition and minimally supervised method in liver surgery planning system.
Abstract
Liver surgery planning system plays an important role in achieving the optimized surgery plan in Living Donor Liver Transplantation (LDLT). Segmentation of liver is a very challenging component in liver surgery planning systems. Patient-specific shape prior is of great significance in improving the robustness of liver segmentation. However, complex liver shape variations among different patients are difficult to model, which affects the accurate segmentation in liver surgery planning. To address this problem, we incorporated the Sparse Shape Composition (SSC) in the computer assisted liver surgery planning system. The basic modules of the system consist of: (1) Segmentation module. The Sparse Shape Composition (SSC) model is employed to get a patient-specific liver shape prior and then the shape prior is combined with a minimally supervised method to segment the liver parenchyma, hepatic vessels and tumors simultaneously. (2) Approximation of liver segments. It divides the liver into several functionally independent segments. (3) Visualization module. The result of clinical experiment shows this system has a good performance in providing accurate and robust liver surgery planning.
Year
DOI
Venue
2013
10.1109/EMBC.2013.6610938
EMBC
Keywords
Field
DocType
computerised tomography,visualization module,liver parenchyma,liver segmentation,image segmentation,ssc,computer assisted liver surgery planning system,sparse shape composition,liver,tumors,tumours,hepatic vessels,patient-specific liver shape,living donor liver transplantation,surgery,medical image processing,minimally supervised method,planning,shape
Computer vision,Computer science,Segmentation,Surgery planning,Robustness (computer science),Image segmentation,Artificial intelligence,Functionally independent,Liver transplantation
Conference
Volume
Issue
ISSN
2013
null
1557-170X
Citations 
PageRank 
References 
0
0.34
10
Authors
4
Name
Order
Citations
PageRank
Guotai Wang180.84
Shaoting Zhang211.03
Feng Li300.34
Lixu Gu423035.28