Diabetic retinopathy grading method based on depth map network

Abstract

The invention provides a diabetic retinopathy grading method based on a depth map network. The actual diagnosis process of an ophthalmologist on the diabetic retinopathy can be effectively simulated;information transmission and integration of disease characteristics are carried out on a plurality of images of a single eye of a patient to obtain a more accurate diagnosis result. The method is characterized by comprising the following steps of S1, performing preprocessing at least including image quality detection and left and right eye classification and recognition on a plurality of to-be-detected eye fundus images of two eyes of a patient to obtain preprocessed eye fundus images; s2, constructing logic diagram data according to the plurality of preprocessed eye fundus images corresponding to the single eye of the patient, wherein the logic diagram data comprises a full-connection diagram taking the plurality of preprocessed eye fundus images as nodes; and S3, inputting the logic diagram data into a pre-trained diabetic retinopathy grading model so as to obtain diabetic retinopathy grade information of the patient.

Description

technical field [0001] The invention belongs to the fields of computer vision and medical treatment, and relates to a method for classifying diabetic retinopathy, in particular to a method for grading diabetic retinopathy based on a depth map network. Background technique [0002] Diabetic retinopathy (DR) is an eye disease associated with diabetes. About 40% to 45% of people with diabetes suffer from the disease to varying degrees. If diabetic retinopathy is detected in time, vision loss can be slowed or avoided. Based on the fundus images taken by patients, the severity of diabetic retinopathy can be divided into five grades according to the disease characteristics such as lesions, which are normal, mild in the non-proliferative stage, moderate in the non-proliferative stage, severe in the non-proliferative stage, and proliferative stage. [0003] Manual detection of diabetic retinopathy is a time-consuming process with high resource demands. Where diabetes rates are hi...

AI Technical Summary

Problems solved by technology

[0005] However, such an automated diagnosis method has certain limitations. Due to external factors such as equipment, a single image may not fully reflect the actual condition of the patient, resulting in a certain degree of misdiagnosis

Images