Abstract
Retinal image registration is a key step in treating hypertension, diabetes and various retinal global diseases. In current methods of retinal image registration, they generally suffer from a lack of reliable features, missing true correspondences and geometric distortion. To address above problem, we propose a robust non-rigid retinal image registration method using multi-image features and dual constraints (i.e. the global and local geometric structure constraints). Our method contains the following main contributions. (i) A finite mixture model based on multi-feature is constructed for handling different types of image features. (ii) A combination of three features is substituted into the mixture model to improve the complementarities of different features. (iii) Dual constraints are proposed for ensuring the stability of the global and local structures of feature sets in the process of spatial transformation and updating. The performance of our method is evaluated by four main types of retinal images, which shows our method outperforms five state-of-the-art methods in most scenarios, especially when the retinal image has a large angle change.
Highlights
Diabetes, hypertension, cerebral vascular sclerosis and coronary atherosclerosis are global diseases, which are the major cause of death and disability in the elderly
Retinal image registration is yet an urgent problem to be solved. According to their algorithm differences, existing registration methods of retinal images are roughly divided into two categories: area-based and feature-based methods [3]–[5], and we focus on feature-based methods in this paper
In order to guarantee the universality of our method, we use features that are extracted from the edge maps, which are common in the retinal images
Summary
Hypertension, cerebral vascular sclerosis and coronary atherosclerosis are global diseases, which are the major cause of death and disability in the elderly. In 2015, an estimated 1.6 million deaths were directly caused by diabetes. There are 12-million diabetics throughout the world will double by 2025 [1] and diabetes will be the seventh leading cause of death in 2030 [2]. Tissue level changes of these disease damages are in the microcirculation and microvessels level, what’s more, retinal microvessel is the only deeper capillaries that can be observed directly. Observing retinal microvessel changes can correlate to the changes in such diseases closely. Glaucoma, agerelated macular degeneration and other retinal diseases can obtain better therapeutic regimens by retinal images
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call