Abstract
In this paper, we give a review on automatic image processing tools to recognize diseases causing specific distortions in the human retina. After a brief summary of the biology of the retina, we give an overview of the types of lesions that may appear as biomarkers of both eye and non-eye diseases. We present several state-of-the-art procedures to extract the anatomic components and lesions in color fundus photographs and decision support methods to help clinical diagnosis. We list publicly available databases and appropriate measurement techniques to compare quantitatively the performance of these approaches. Furthermore, we discuss on how the performance of image processing-based systems can be improved by fusing the output of individual detector algorithms. Retinal image analysis using mobile phones is also addressed as an expected future trend in this field.
Highlights
The retina [1] has a very specific diagnostic role regarding human health
Though in this work we focus on fundus photography, from other image acquisition techniques we can highlight optical coherence tomography with the corresponding image analytic methods [135, 136]
Proper benchmarking analyses are often omitted in the presentation of the algorithms, and the rapid development of computer hardware and the various hardware platforms make a quantitative comparison of the execution times challenging
Summary
The retina (fundus) [1] has a very specific diagnostic role regarding human health. The eye is a window into the body responsible for sensing information in the visible light domain, it is suitable to make clinical diagnoses in a non-invasive manner. The retina is a spherical anatomic structure on the inner side of the back of the eye as shown in Fig. 1 (a) It can be subdivided into ten layers supporting the extraction of visual information by photoreceptor cells: the rods and the cones. From diagnostic point of view, retinal image analysis is a natural approach to deal with eye diseases. It is getting more and more important nowadays, since the types and quantities of different lesions can be associated with several non-eye diseases, as well. The fovea, macula, optic disc, optic cup, and blood vessels are the most essential anatomic landmarks to extract (see Fig. 1 (b)).
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have