Fundus image macular center positioning method and device, electronic equipment and storage medium

Abstract

The invention provides a fundus image macular center positioning method and device, electronic equipment and a storage medium. The fundus image macular center positioning method comprises the steps that a fundus image to be detected is input into a fundus image detection model; obtaining a detection result of the fundus image detection model, wherein the detection result comprises an optic disc region and a corresponding first detection frame, a macular region and a corresponding second detection frame and confidence; calculating central point coordinates of the optic disk area according to the first detection frame and calculating central point coordinates of the macular area according to the second detection frame; and when the confidence coefficient is smaller than a preset confidence coefficient threshold, identifying whether the fundus image to be detected is a left eye fundus image or a right eye fundus image, and correcting the central point of the macular area by adopting different correction models. The problem of macular area detection failure caused by image quality, lesion shielding and the like in a macular positioning method based on deep learning is solved, and the dependence of macular center positioning and optic disc center positioning in a traditional method is eliminated.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method, device, electronic equipment and storage medium for locating the center of the macula in a fundus image. Background technique [0002] A large number of visual function cells are concentrated in the macula. If the lesion in the macular area is not detected and treated in time, the chance of blindness will be greatly increased. Therefore, accurate macular center positioning is of great significance for the diagnosis of retinopathy. In the prior art, there is a method for locating the center of the macula based on fundus images, which first locates the center of the optic disc, and then locates the center of the macula according to the center of the optic disc; or directly detects the macular region using a target detection model of a deep neural network. [0003] However, the macular center location method based on fundus images completely depends on the...

AI Technical Summary

Problems solved by technology

[0003] However, the macular center positioning method based on fundus images completely depends on the positioning of the optic disc center. Once the optic disc center positioning fails, the macular center cannot be effectively located, and the calculation complexity is high, the timeliness is low, and the robustness is poor.

Although the macular center location method based on deep neural network does not depend on the location of the optic disc center, the macula is easily affected by the lesion area, image quality and atrophy area, so the macular area cannot be successfully detected and cannot be effectively located.

Images