Judgment method for simultaneously identifying stages and lesion features of diabetic retinopathy

Abstract

The invention discloses a judgment method for simultaneously identifying stages and lesion features of diabetic retinopathy. The judgment method comprises the following steps: acquiring a fundus image; and inputting the fundus image into a deep learning-based multi-task network to simultaneously identify a stage to which the fundus image belongs and lesion features of the fundus image, the multi-task network at least comprising a backbone network, a feature head network and a stage head network, the backbone network receiving the fundus image and outputting a first feature map, the feature head network receiving the first feature map, judging lesion features of the fundus image and obtaining a second feature map through a middle layer of the feature head network, and the staging head network receiving the first feature map and obtaining a third feature map based on a middle layer of the staging head network; and performing feature fusion on the third feature map and the second feature map to judge the stage to which the eye fundus image belongs. Therefore, the causal relationship between the lesion features and the stages can be simulated, and the recognition performance of the stages and the lesion features can be improved at the same time.

Description

technical field [0001] The present disclosure generally relates to a judgment method and a judgment system for simultaneously recognizing the stages and characteristics of diabetic retinopathy. Background technique [0002] Diabetes is a group of metabolic diseases characterized by hyperglycemia. Long-term high blood sugar can lead to various tissue damage or dysfunction, especially damage to the eyes. In severe cases, it may cause fundus hemorrhage and cause blurred vision or complete loss of vision. According to statistics, more than 80% of diabetic patients will develop diabetic retinopathy, and the risk of blindness is 25 times higher than that of normal people. Diabetic retinopathy is an eye disease that can prevent blindness, and retinal lesions are not obvious in the early stage, but if regular fundus examinations can be performed at the early stage of the disease, the risk of blindness caused by diabetic retinopathy can be reduced by more than 90%. Therefore, early...

AI Technical Summary

Problems solved by technology

[0004] However, one of the biggest problems of deep learning-based medical imaging diagnosis technology is that the image features automatically learned by deep learning lack interpretability, so doctors cannot well understand and accept the diagnosis results based on deep learning

Similarly, for the identification of diabetic retinopathy, currently available technologies cannot provide intelligible evidence (such as lesion characteristics related to the stage of diabetic retinopathy) to support the recognition result (that is, the diabetic retina to which the fundus image belongs). staging of lesions), thus hindering the application of the technique

Images