Deep learning-based diabetic retina image classification method and system

Abstract

The invention discloses a deep learning-based diabetic retina image classification method and system in the technical field of artificial intelligence. The method comprises steps: a fundus image is acquired; the same fundus image is imported to a microvascular tumor-like lesion recognition model, a hemorrhagic lesion recognition model and an exudative lesion recognition model for recognition; andaccording to recognition results, lesion feature information is extracted, a trained SVM classifier is then adopted to classify the extracted lesion feature information, and a classification result isacquired, wherein the microvascular tumor-like lesion recognition model is obtained when a microvascular tumor-like lesion candidate area in the fundus image is extracted and is then inputted to a CNN model for training, and the hemorrhagic lesion recognition model and the exudative lesion recognition model are obtained when a hemorrhagic lesion area and an exudative lesion area in the fundus image are marked and are then inputted to an FCN model for training. The requirements on the description ability of the network model are reduced, the model is easy to train, a lesion focus area is positioned and delineated for different lesions, and clinical screening by a doctor is facilitated.

Description

technical field [0001] The invention relates to the field of artificial intelligence, and is a method and system for classifying diabetic retinal images based on deep learning. Background technique [0002] The number of diabetic patients in my country is huge and is increasing year by year. Diabetic retinopathy is one of the serious complications of diabetes and the main cause of blindness among people aged 20 to 65. It not only causes great harm to the society and the families of patients The harm and burden of diabetes, and the quality of life of diabetic patients is greatly reduced. [0003] Since blindness caused by diabetic retinopathy is preventable, early detection and early intervention are the most effective means to prevent diabetic blindness. However, in the early stage of retinopathy caused by diabetes, patients basically do not feel discomfort. Without screening, it is easy to be neglected and delay treatment, resulting in irreversible damage to vision. [000...

AI Technical Summary

Problems solved by technology

However, the current mature deep learning models all adopt the supervised learning mode, but it is difficult to obtain a large amount of high-quality labeled medical image data, resulting in the medical images used in deep learning training generally lagging behind natural images; especially in diabetic retinopathy , the patient's retinal fundus image is complex, and multiple lesions often coexist. Under the limitation of limited materials, it is difficult to improve the detection efficiency

Images