Please use this identifier to cite or link to this item:
Title: A new unified level set method for semi-automatic liver tumor segmentation on contrast-enhanced CT images
Authors: Li, B.N.
Chui, C.K. 
Chang, S.
Ong, S.H. 
Keywords: Contrast-enhanced computed tomography
Level set methods
Liver tumor segmentation
Medical image computing
Issue Date: Aug-2012
Source: Li, B.N., Chui, C.K., Chang, S., Ong, S.H. (2012-08). A new unified level set method for semi-automatic liver tumor segmentation on contrast-enhanced CT images. Expert Systems with Applications 39 (10) : 9661-9668. ScholarBank@NUS Repository.
Abstract: Objective: Computerized liver tumor segmentation on computed tomography (CT) images is a challenging problem. Level set methods have been proposed for CT liver and tumor segmentation. However, the common models using image gradient or region competition have inherent drawbacks, and are not very robust for liver tumor segmentation. Methods: We propose a new unified level set model to integrate image gradient, region competition and prior information for CT liver tumor segmentation. The probabilistic distribution of liver tumors is estimated by unsupervised fuzzy clustering, and is utilized to enhance the object indication function, define the directional balloon force and regulate region competition. This unified model has been evaluated on 25 two-dimensional (2D) CT scans and 4 three-dimensional (3D) CT scans with 10 tumors. Results: For the 2D dataset, the area overlapping error (AOE) is 12.75 ± 5.76%, the relative area difference (RAD) is -4.28 ± 9.58%, the average contour distance (ACD) is 1.66 ± 1.09 mm, and the maximum contour distance (MCD) is 4.29 ± 2.75 mm. For the 3D dataset, the volume overlapping error (VOE) is 26.31 ± 5.79%, the relative volume difference (RVD) is -10.64 ± 7.55%, the average surface distance (ASD) is 1.06 ± 0.38 mm, and the maximum surface distance (MSD) is 8.66 ± 3.17 mm. All results are competitive with that of the state-of-the-art methods. Conclusion: The new unified level set model is an effective solution for liver tumor segmentation on contrast-enhanced CT images. © 2012 Elsevier Ltd. All rights reserved.
Source Title: Expert Systems with Applications
ISSN: 09574174
DOI: 10.1016/j.eswa.2012.02.095
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.


checked on Mar 6, 2018


checked on Jan 24, 2018

Page view(s)

checked on Mar 11, 2018

Google ScholarTM



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.