Eye image segmentation method and device based on prior information, equipment and medium

Abstract

The invention discloses an eye image segmentation method and device based on prior information, equipment and a medium, and the method comprises the steps: obtaining a fundus image data set, and calculating prior information according to the fundus image data set; constructing a machine learning model, and training the machine learning model based on the prior information to obtain an image segmentation model; obtaining a to-be-segmented target image, wherein the target image comprises an eye part; and inputting the target image into the image segmentation model to obtain a target image segmentation result output by the image segmentation model. Prior information is introduced to train an image segmentation model. The segmentation result of the to-be-segmented target image has high interpretability and accuracy. In addition, a classification model can be trained based on prior information, and the classification model is used to classify the segmentation result of the to-be-segmented target image so as to obtain the classification result with high interpretability and high accuracy, so that the scheme of the invention has a wider application prospect.

Description

technical field [0001] The present invention relates to the field of image processing, in particular to an eye image segmentation method, device, equipment and medium based on prior information. Background technique [0002] In the prior art, there are mainly two schemes for eye image classification based on machine learning. The first is based on the deep learning model MRNet for eye image classification, and the second is based on the Recurrent Attention Convolutional Neural Network (Recurrent Attention Convolutional Neural Network). ) for eye image classification. [0003] As shown in Figure 1(a), it shows a schematic diagram of the structure of the deep learning model MRNet. MRNet is based on the convolutional neural network AlexNetAlexnet structure, with a corresponding two-dimensional image of a three-dimensional knee image as input, and different convolutional layers. The output can finally give the probability that the 3D knee image points to a certain target object...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the technical problem in the prior art that eye image classification does not use prior knowledge, resulting in poor interpretation of image segmentation and classification results, embodiments of the present invention provide eye image segmentation methods, devices, devices and methods based on prior information. medium

Images