OCT (Optical Coherence Tomography) synthetic fundus image optic disc center positioning method and equipment

Abstract

The invention discloses an OCT (Optical Coherence Tomography) synthetic fundus image optic disc center positioning method and equipment. The OCT synthetic fundus image optic disc center positioning method comprises the following steps of: acquiring fundus image data; processing the fundus image data by utilizing a preset inner and outer square frames; calculating the correlation between a characteristic template and the fundus image by moving the characteristic template of the preset inner and outer square frames to acquire a correlation matrix; and finding the maximum numerical value point in the correlation matrix, so that a central area of the fundus image optic disc can be positioned. Data loss or high noise is not required in the fundus image acquisition, an optic disc area acquired by standard operation of an OCT instrument generally meets the characteristics that the central area of the optic disc is dark and the periphery is bright, and the optic disc area can be rapidly and accurately positioned; and therefore, the algorithm is higher in stability and higher in calculation speed and can be used for rapidly positioning and analyzing a lots of fundus images.

Description

technical field [0001] The invention belongs to the technical field of positioning, and in particular relates to a method and equipment for positioning the center of an optic disc of an OCT synthetic fundus image. Background technique [0002] The current optic disc center positioning technology of fundus map mainly includes: 1. Positioning of the optic disc center based on the blood vessels in the fundus map, and positioning of the optic disc center based on the direction of the blood vessels; 2. Positioning of the optic disc area based on hough circle detection and active contour model. [0003] First, both methods are based on edge features of images, such as blood vessels and optic disc edges. However, edge detection is greatly affected by image quality, so at present, these two aspects mainly focus on non-OCT-synthesized fundus maps, such as fundus maps obtained by fundus cameras. Because the image quality of this type of fundus map is clear, blood vessels and optic di...

AI Technical Summary

Problems solved by technology

The overall quality of the optical coherence tomography (OCT) fundus composite image is not as good as that of fundus color photos, and the contrast of blood vessels and optic disc area is weak, especially the edge of the optic disc. At the same time, the scanning time of each OCT area is relatively short Long, the shaking or blinking of the human eye will affect the OCT fundus image synthesized in the later stage

Therefore, these two types of methods cannot be directly applied to synthetic OCT images.

[0004] Secondly, these two methods, whether it is blood vessel thinning or edge detection, require complex algorithm design in the early stage, especially the impact of the image quality of the OCT synthetic fundus image. To produce a more accurate edge segmentation effect, the algorithm will be More complex, there will be a larger amount of calculation

Images