<p>An Enhanced Approach for Segmentation of Liver from Computed Tomography Images</p>
Online Publishing @ NISCAIR
View Archive InfoField | Value | |
Authentication Code |
dc |
|
Title Statement |
<p>An Enhanced Approach for Segmentation of Liver from Computed Tomography Images</p> |
|
Added Entry - Uncontrolled Name |
Rajamanickam, Prabakaran ; Department of Computer Science and Engineering, CEG Campus, Anna University, Chennai, India Darmanayagam, Shiloah Elizabeth; Department of Computer Science and Engineering, CEG Campus, Anna University, Chennai, India Sarangapany, Thamaraiselvam ; Department of Computer Science and Engineering, CEG Campus, Anna University, Chennai, India Raj, Sunil Retmin Raj Cyril; Department of Information Technology, MIT Campus, Anna University, Chennai, India |
|
Uncontrolled Index Term |
Evaluation parameters, Hybrid approach, Image segmentation, Level set, Liver segmentation, PSO |
|
Summary, etc. |
<p>An accurate segmentation of liver from Computed Tomography (CT) scans is essential for liver tumor research as it offers valuable information for clinical diagnosis and treatment. However, it is challenging to achieve an accurate segmentation of the liver because of the blurred edges, low contrast and similar intensity of the organs in the CT scan. In this paper, an automated model which will segment the liver from CT images using a hybrid algorithm has been used. The segmentation of liver from CT scan is done with the help of Particle Swarm Optimization (PSO) followed by level set algorithm. The ultimate aim of using this hybrid algorithm is to improve the accuracy of liver segmentation. Computer aided classification of liver CT into healthy and tumorous images aids in diagnosis of liver diseases. It can help a great deal in diagnosis of liver disorders. In order to achieve better classification results, it is of high importance to segment the liver accurately without an error of over or under segmentation. The results obtained indicate that the approach used in this work is faster and has 98.62% accuracy, 99.2% specificity, 97.1% sensitivity, 97.8% F-measure, 96.6% Matthews Coefficient Constant (MCC), 99.08% precision, 97.8% dice coefficient and 95.7% jaccard coefficient in segmenting the liver.</p> |
|
Publication, Distribution, Etc. |
Journal of Scientific & Industrial Research 2022-03-14 19:52:11 |
|
Electronic Location and Access |
application/pdf http://op.niscair.res.in/index.php/JSIR/article/view/48685 |
|
Data Source Entry |
Journal of Scientific & Industrial Research; ##issue.vol## 81, ##issue.no## 03 (2022): Journal of Scientific and Industrial Research |
|
Language Note |
en |
|