Method for measuring diameter of maximum choroid blood vessel based on image segmentation

Abstract

The invention discloses a method for measuring the diameter of the maximum choroid blood vessel based on image segmentation. The method comprises the following steps: firstly performing image pre-processing on a choroid in a SD-OCT retina image, then adopting the method of image segmentation to extract a region of interest and performing related calculation on the region, and finally outputting a measuring result. According to the invention, the method reduces measuring errors by making the obtained diameter of the choroid maximum blood vessel with an improved precision than the diameter obtained by manual measuring. The method, by using the simple and rapid image segmentation technology, increases accuracy and efficiency in measuring the diameter of the choroid blood vessel, and has great significance in facilitating successive choroid diseases analysis and improving doctor's working efficiency.

Description

technical field [0001] The invention relates to a measurement method, in particular to a method for measuring the maximum choroidal vessel diameter based on image segmentation. Background technique [0002] The choroid layer is composed of a large number of blood vessels, which provide nutrition for the retinal layer and is closely related to retinal diseases. Abnormal changes such as choroidal vasodilation, congestion, and high permeability can cause choroid-related fundus diseases. The morphology of the choroid plays an irreplaceable role in auxiliary diagnosis in clinical practice. concern of ophthalmology clinicians. In recent years, due to the incomplete and unclear performance of choroidal vessels in frequency-domain optical coherence tomography (SD-OCT) images, the methods for monitoring choroidal vessels are limited, and the lack of accurate and objective quantitative detection tools is often used clinically. The disadvantage is that the retinal blood vessels are n...

AI Technical Summary

Problems solved by technology

In recent years, due to the incomplete and unclear performance of choroidal vessels in frequency-domain optical coherence tomography (SD-OCT) images, the methods for monitoring choroidal vessels are limited, and the lack of accurate and objective quantitative detection tools is often used clinically. The disadvantage is that the retinal blood vessels are not completely regular and radially distributed with the optic disc as the center, so when scanning the blood vessels within the concentric circle with the optic disc as the center, there will be non-perpendicular measurement of the blood vessel diameter, resulting in errors;

Therefore, the traditional target extraction method is difficult to effectively give the choroidal vessel area

In order to overcome the low accuracy of existing methods for measuring choroidal blood vessels and easily lead to errors, the present invention provides a method with high accuracy and capable of obtaining the largest diameter of choroidal blood vessels

Images