MCASPP neural network fundus image optic cup and optic disk segmentation model based on Attention mechanism

Abstract

The embodiment of the invention relates to an MCASPP neural network fundus image optic cup and optic disc segmentation model based on an Attention mechanism. The model comprises a model body, the system comprises a feature extraction module, an attention mapping module, a multi-scale cavity convolution module and an output module. Extracting a first image feature in the input image through a feature extraction module; the attention mapping module is used for extracting a second image feature of the input image; and obtaining a first feature according to the advanced feature, the low-level feature and the second image feature in the first image feature, through the multi-scale cavity convolution module, the advanced features are subjected to multiple convolution to obtain the second features, and the output module obtains the prediction probability graph according to the first features and the second features, so that the feature extraction precision of the image segmentation network can be improved, and the technical problem of relatively low optic disc precision of optic cups segmented by a full convolution network in related technologies is avoided.

Description

technical field [0001] The invention relates to the field of neural networks, in particular to a multi-scale hole convolution MCASPP neural network fundus image cup and disc segmentation model based on an attention mapping mechanism. Background technique [0002] The analysis of retinal fundus images is very important for ophthalmologists to deal with fundus diseases such as diabetic retinopathy and glaucoma, as well as other diseases related to fundus performance, such as hypertension and coronary heart disease. If not diagnosed and treated in time, there is a risk of blindness or worse. Optic cup and optic disc are one of the most basic organizational structures in retinal fundus images, and changes in the shape of the optic cup and optic disc are an important basis for clinical diagnosis of glaucoma. And in the practice of clinical diagnosis, there is a serious shortage of doctors for glaucoma, making diagnosis difficult. Therefore, automatic retinal fundus image cup-di...

AI Technical Summary

Problems solved by technology

[0006] In the traditional unsupervised method mentioned above, the neural network model usually involves many additional conditions that need to be met, and has high requirements on the quality of the image itself, and the accuracy of the segmented optic cup and disc is also low.

For the fully convolutional neural network mentioned in the neural network segmentation method, a lot of useful information is lost by extracting features layer by layer, resulting in the parameters finally learned by the model cannot fully describe the characteristics of the cup and plate.

[0007] For the above problems, no effective solution has been proposed

Images