Method for segmenting choroidal atrophy in fundus medical image

Abstract

The invention discloses a method for segmenting choroidal atrophy in a fundus medical image, and the method comprises the steps: firstly constructing a cascaded multi-scale information interaction fusion network based on a U-Net network, and setting a cascaded multi-scale information interaction fusion module between a coding network and a decoding network during the construction of the cascaded multi-scale information interaction fusion network; and inputting a fundus medical image to be processed into the cascaded multi-scale information interaction fusion network for choroidal atrophy segmentation. The extraction capability of the segmentation network for different shape features is improved, and the segmentation efficiency of choroidal atrophy in the medical image is improved.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for segmenting choroidal atrophy in fundus medical images. Background technique [0002] Medical imaging refers to the technology and processing process of obtaining internal tissue and organ images of the human body or a certain part of the human body in a non-invasive manner for the purpose of medical treatment or medical research. According to different implementation steps, medical imaging includes medical imaging technology and medical processing technology. With the help of medical imaging technology, medical personnel can have a clearer understanding of the specific tissue and organ conditions of the human body and then provide more accurate and reasonable diagnosis and treatment plans. Medical image segmentation is a key technology in modern medical image processing, and it is the basis for follow-up operations such as 3D reconstruction and quant...

AI Technical Summary

Problems solved by technology

However, the segmentation of choroidal atrophy in fundus images is a difficult task due to the following reasons: the shape and area of ​​choroidal atrophy are diverse, and the occurrence area, shape and area of ​​choroidal atrophy in different degrees of pathological myopia vary greatly Myopia is often associated with optic disc and choroidal atrophy similar to high myopia, and as the degree of pathological myopia deepens, diffuse chorioretinal atrophy, plaque-like chorioretinal atrophy, and macular atrophy will occur, with differences in the area, shape, and area of ​​occurrence Great changes

[0005] However, existing medical image segmentation methods, such as PSP-Net, CE-Net, and CPF-Net, mostly use expansion convolution or pyramid pooling modules, and the segmentation network uses expansion convolution, although large-resolution feature maps can be obtained. , but it also increases the memory usage and calculation amount, while the pyramid pooling module uses parallel multi-scale pooling. Finally, the features of each branch are upsampled and merged with the original feature map to obtain multi-scale features. However, due to the pyramid pooling The pooling module adopts a square pooling template, which is difficult to improve the segmentation performance of slender objects

Therefore, the existing medical image segmentation methods have problems such as insufficient ability to extract different shape features and low segmentation efficiency, and cannot meet the segmentation requirements of choroidal atrophy in fundus medical images.

Images