By Topic

Atherosclerotic plaque characterization using geometrical features from virtual histology intravascular ultrasound images

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

8 Author(s)
Athanasiou, L.S. ; Dept of Mater. Sci. & Eng., Univ. of Ioannina, Ioannina, Greece ; Karvelis, P.S. ; Tsakanikas, V.D. ; Stefanou, K.A.
more authors

Intravascular ultrasound imaging (IVUS) is a diagnostic imaging technique which provides two-dimensional (2-D) tomographic views of the coronary lumen and outer vessel wall. Virtual Histology (VH) provides a color-coded plaque characterization which employs the radiofrequency (RF) data from the catheter. The aim of this study is to extract a set of features from IVUS images and to use them in the detection of various plaque components. Intensity features, texture based features and two novel geometrical features are employed in a Random Forests classification algorithm. The first geometrical feature describes the relative position of each pixel from the media-adventitia border and the second the relative position from the media-adventitia and the lumen border. The plaque components are classified into four plaque types: Dense Calcium, Fibrotic Tissue, Fibro-Fatty Tissue and Necrotic Core. We use 300 IVUS frames acquired from Virtual Histology exams from 10 patients to evaluate our methodology. The two geometrical features improved the atherosclerotic plaque classification in terms of overall accuracy, sensitivity and specificity. Using the geometrical features an overall classification accuracy 84.45% is reported.

Published in:

Information Technology and Applications in Biomedicine (ITAB), 2010 10th IEEE International Conference on

Date of Conference:

3-5 Nov. 2010