Enhancement of bifurcation points in blood vessel images

• Grant number: 19/20917-2
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: March 01, 2020
• End date: February 28, 2021
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computing Methodologies and Techniques
• Principal Investigator: Cesar Henrique Comin
• Grantee: Isaac Willian Mariotto Marques
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

Detecting blood vessels in images is an important task for the diagnosis of cardiovascular diseases. The majority of blood vessel detection methods apply as a first step tubular enhancement algorithms. Such algorithms tend to ignore bifurcation points of blood vessels, resulting in loss of information about the vascular structure contained in the image. Additionally, the few methodologies defined in the literature aimed at bifurcation point enhancement were proposed specifically for the retinal fundus image. This project aims at comparing three bifurcation enhancement methods, previously defined in the literature when applied to microscopy images containing blood vessels of the mouse cortex. Additionally, a new method for enhancing blood vessel bifurcations will be proposed. The new method will be compared with the previously defined methods. The influence of these methods on the segmentation and characterization of vascular structures will be quantified. (AU)