BW - Eye Ophthalmologic decision support system based on clinical workflow and data mining techniques-image registration algorithm

TL;DR

This paper presents the development of an image registration algorithm for ophthalmologic images, utilizing bifurcation point detection and data matching techniques to aid decision support in ophthalmology.

Contribution

It introduces two novel approaches for matching retinal images based on bifurcation features and mutual information, advancing image registration methods in ophthalmology.

Findings

Implemented in MATLAB, the algorithm detects vascular bifurcation points.

Two approaches for feature correspondence were proposed and analyzed.

The work provides a foundation for future development of ophthalmologic image registration algorithms.

Abstract

Blueworks - Medical Expert Diagnosis is developing an application, BWEye, to be used as an ophthalmology consultation decision support system. The implementation of this application involves several different tasks and one of them is the implementation of an ophthalmology images registration algorithm. The work reported in this document is related with the implementation of an algorithm to register images of angiography, colour retinography and redfree retinography. The implementations described were developed in the software MATLAB. The implemented algorithm is based in the detection of the bifurcation points (y-features) of the vascular structures of the retina that usually are visible in the referred type of images. There are proposed two approaches to establish an initial set of features correspondences. The first approach is based in the maximization of the mutual information of the bifurcation regions of the features of images. The second approach is based in the characterization of each bifurcation point and in the minimization of the Euclidean distance between the descriptions of the features of the images in the descriptors space. The final set of the matching features for a pair of images is defined through the application of the RANSAC algorithm. Although, it was not achieved the implementation of a full functional algorithm, there were made several analysis that can be important to future improvement of the current implementation.