Automatic segmentation method for a visual disc and a visual cup of a color fundus image

Abstract

The invention discloses an automatic segmentation method for an optic disc optic cup of a color fundus image. The method comprises the following steps: acquiring a known color fundus image and a corresponding fundus image data set; Constructing and obtaining an optic disc segmentation model; segmentating and intercepting The data set, and obtaining a screenshot; Constructing and obtaining an optic disc optic cup segmentation model under the Euclidean coordinates; Performing polar coordinate transformation on the screenshot to obtain a polar coordinate screenshot; Constructing and obtaining anoptic disc optic cup segmentation model under polar coordinates; Segmenting the to-be-analyzed data by using two types of models to obtain an Euclidean coordinate optic disc optic cup segmentation result and a polar coordinate optic disc optic cup segmentation result; And fusing the two types of segmentation results to obtain a final optic disc and optic cup segmentation result of the fundus image. According to the method, automatic optic disk and optic cup segmentation can be more accurately carried out on the color fundus image, and the method is simple, reliable and good in applicability.

Description

technical field [0001] The invention specifically relates to a method for automatically segmenting an optic disc and an optic cup of a color fundus map. Background technique [0002] With the development of economy and technology, people's requirements for physical health are becoming more and more prominent. [0003] Glaucoma is the second leading cause of blindness in the world. It will cause irreversible blindness from the outside to the inside of the patient, and it is already late when the patient realizes it. At present, there is no effective treatment for glaucoma, and the process of blindness can only be delayed through early detection and intervention. Therefore, glaucoma has immeasurable harm to society and people's life. [0004] In clinical practice, the methods used by doctors to determine whether a patient has glaucoma include intraocular pressure detection, visual field detection, and fundus image analysis and diagnosis. In the analysis and diagnosis of co...

AI Technical Summary

Problems solved by technology

[0006] However, most of these algorithms only focus on the analysis of local features, which have high requirements for sample data and poor accuracy.

Secondly, these algorithms focus on a single data set, have high requirements on the environment, and have poor robustness.

Images