Quantification of Epicardial and Thoracic Adipose Tissue using WOA Optimized CNN
N. Sangeetha A. Kathirvel1, P. Indira Priya2, R. Latha3
1N. Sangeetha A. Kathirvel, Department of Computer Science and Engineering, MNM JAIN Engineering college, Chennai (Tamilnadu), India.
2P. Indira Priya, Professor and HOD, Department of Computer Science and Engineering, MNM JAIN Engineering college, Chennai (Tamilnadu), India.
3R. Latha, Professor, Department of Computer Science and Engineering, MNM JAIN Engineering college, Chennai (Tamilnadu), India.
Manuscript received on 20 August 2019 | Revised Manuscript received on 27 August 2019 | Manuscript Published on 31 August 2019 | PP: 720-724 | Volume-8 Issue-9S2 August 2019 | Retrieval Number: I11500789S219/19©BEIESP DOI: 10.35940/ijitee.I1150.0789S219
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open-access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Fat depots are associated with the heart diseases. Epicardial fat and thoracic fat plays the major role in the development of cardiovascular disease. The increased thickness of the epicardial and thoracic fat leads to several diseases such as metabolic syndrome, coronary atherosclerosis, etc. It is necessary to quantify the epicardial adipose tissue and thoracic adipose tissue. There are different imaging and assessing techniques for epicardial and thoracic adipose tissue quantification. These tissues can be quantified automatically or manually from the CT and MRI cardiac scans. The quantification of the epicardial fat and thoracic fat requires segmentation of these fats by various segmentation methods and then they are quantified. This project proposes the fully automatic segmentation and quantification of the epicardial and thoracic adipose tissues from the cardiac CT scan images using the krill herd optimization algorithm and fuzzy c-means segmentation algorithm. The whale optimization algorithm performs the feature selection process. The fuzzy c-means algorithm is used for the segmentation process by means of clustering which segments the epicardial fat and paracardial adipose tissue(EAT &PAT) from the input image. The segmented epicardial and paracardial fat region are then used for the quantification process which provides the epicardial and thoracic fat volume. The thoracic fat is the combination of the epicardial and paracardial fat. This proposed system is implemented by using the MATLAB code. The proposed system is simple, fully automatic and produces accurate results.
Keywords: Fuzzy K-means Algorithm, Epicardial Adipose Tissue (EAT), Paracardial Adipose Tissue (PAT),
Scope of the Article: Fuzzy Logics