Texture analysis of the media-layer of the left and right common carotid artery
AuthorLoizou, Christos P.
Griffin, Maura B.
Kyriacou, Efthyvoulos C.
Nicolaïdes, Andrew N.
Pattichis, Constantinos S.
PublisherIEEE Computer Society
Source2014 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2014
2014 IEEE-EMBS International Conference on Biomedical and Health Informatics, BHI 2014
Google Scholar check
MetadataShow full item record
The intima-media thickness (IMT) of the common carotid artery (CCA) is a well-known indicator of cardiovascular disease (CVD). The objective of this study was to investigate the application of texture analysis of the medial layer (ML) of the CCA, and how texture features vary between the left and right carotid sides, as well as how these are affected by CVD. The study was performed on 200 longitudinal-section ultrasound images from 150 normal subjects, and 50 symptomatic subjects suffering with CVD. The ML was segmented automatically by a snakes segmentation system and 61 different texture features were extracted. This study showed that only the gray level difference statistics (GLDS) correlation measure of the ML component could be used to differentiate between normal subjects, and subjects suffering with CVD for either the left or the right CCA sides. We furthermore found that a number of texture features were significantly different between the left and the right CCA sides. We have found no other studies in the literature where these findings could be compared to. These findings should be further validated on a larger number of subjects as well as combined with additional risk factors. © 2014 IEEE.