Analysis and classification of carotid artery stenosis by duplex ultrasound images

• Grant number: 12/20465-5
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: January 01, 2013
• End date: December 31, 2013
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Anderson de Rezende Rocha
• Grantee: Daniel Vatanabe Pazinato
• Host Institution: Instituto de Computação (IC). Universidade Estadual de Campinas (UNICAMP). Campinas , SP, Brazil

Abstract

Research involving the analysis of medical images has shown great interest in discovering the composition of an atheromatous plaque in the carotid artery by ultrasound images. By correlating plaque components with the clinical aspects of the patient, it is possible to observe whether a plaque is stable, therefore, verifying if there is a risk of the patient developing any further complication, or unstable, where the most advisable action is to make surgery to remove the plaque. This criterion would be more accurate than the one currently used, which is based only on the narrowing of the plaque. In this context, it is very important to develop more studies on this subject, proving that the methods used to classify such plaque are indeed reliable. In this project, we propose to use image processing and machine learning techniques to analyze and classify the atheromatous plaques. The initial approach will be to segment the region of interest and then locate the different tissues of the plaque in order to classify the type of plaque. Finally, it is worth mentioning that this undergraduate research will integrate the research project: Recognition and Pattern Classification by means of Feature Engineering, *-Fusion, Open-Set Recognition and Meta-Recognition Techniques in partnership with Samsung Inc., responsible for the acquisition of various computer equipment and creating the necessary conditions for the development of this research and other correlated studies.(AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

PAZINATO, DANIEL V.; STEIN, BERNARDO V.; DE ALMEIDA, WALDIR R.; WERNECK, RAFAEL DE O.; MENDES JUNIOR, PEDRO R.; PENATTI, OTAVIO A. B.; TORRES, RICARDO DA S.; MENEZES, FABIO H.; ROCHA, ANDERSON. Pixel-Level Tissue Classification for Ultrasound Images. IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS, v. 20, n. 1, p. 256-267, JAN 2016. (12/20465-5)