Retinal blood vessel classification method and device

Abstract

The invention relates to a retinal blood vessel classification method and a retinal blood vessel classification device. The retinal blood vessel classification method combines a local binary algorithm with an independent component analysis technique for integrated use in the aspect of fundus blood vessel feature extraction, since the local binary algorithm and the independent component analysis technique performs structural description of blood vessel features from different angles, the method inherites the advantages of each single technology, supplements the blood vessels to certain extent, and filters the influence of more noise; and the retinal blood vessel classification method finally improves the precision of fundus blood vessel arteriovenous classification, reduces the proportion of blood vessels without classification marks, and provides a solid data basis for the follow-up diagnosis of diseases related to fundus blood vessels.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a method and device for classifying retinal blood vessels. Background technique [0002] For a long time, cardiovascular and cerebrovascular diseases have been the main cause of death and disability of the elderly population in the world, among which hypertension, arteriosclerosis, and central retinal artery occlusion are the most common. The formation and pathogenesis of these diseases will show gradual morphological changes in the microvessels. Through the analysis of the microvascular morphological structure, not only can the degree of disease occurrence be judged and then diagnosed, but also the early symptoms can be predicted. Clinically is of great significance. Since the fundus retinal vascular network is the only small artery and small venous vascular network that can be directly observed in the human body, the characteristics of common diseases such as hyperten...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a method and device for classifying retinal blood vessels. Through local binary model algorithm combined with independent component analysis, the structural characteristics of blood vessels are integrated, and the characteristics of arteriovenous vessels are reflected from multiple levels, which solves the problem of arteriovenous classification in the prior art. In this case, the accuracy rate is low or only the main blood vessels can be classified, but the fine branches cannot be detected, so that in the arteriovenous classification step, a better classification effect can be obtained, and effective and reliable data premise can be provided for the identification and diagnosis of subsequent disease characteristics.

Images