Eye fundus image optic cup and optic disc segmentation method under unified framework

Abstract

The invention discloses an eye fundus image optic cup and optic disk segmentation method under a unified framework, and the method comprises the steps: obtaining an eye fundus image before segmentation, and carrying out the image preprocessing operation, such as cutting and rotating; generating a corresponding mask image according to an optic cup and optic disk area marked on the fundus color photo by an ophthalmologist; constructing a deep network for segmenting an optic cup and an optic disk; iteratively training the deep segmentation network by using the mask image and the fundus image, and optimizing network parameters; and segmenting the optic cup and the optic disc, and obtaining the segmentation results of the optic cup and the optic disc by using the trained segmentation network model. The invention provides a deep neural network for optic cup and optic disc segmentation. The deep neural network comprises a multi-scale feature extractor, a multi-scale feature transition and an attention pyramid structure. According to the method, the optic cup and the optic disc can be effectively segmented, the segmentation precision is high, and meanwhile, a new thought is provided for segmentation of fundus images and segmentation of other medical images.

Description

technical field [0001] The invention belongs to the technical field of image segmentation, and in particular relates to a fundus image optic cup and optic disc segmentation method under a unified framework. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] Medical image segmentation is a basic task in medical image processing and a hotspot in medical image processing at present. Accurate segmentation results are of great significance in clinical diagnosis and disease treatment. Medical image segmentation is to extract the lesions or organs and tissues in the image from the background. [0004] Glaucoma is one of the three leading causes of blindness in the world, and its damage to the vision of patients is irreversible. Therefore, early screening is essential for the prevention and treatment of glaucoma. Currently, fundus color images and...

AI Technical Summary

Problems solved by technology

First of all, there are a large number of vascular structures in the optic disc area in the fundus image, which is likely to cause interference during the segmentation process and affect the segmentation accuracy of the optic cup and optic disc.

The second difficulty is that the boundary between the optic disc and the optic cup is very blurred in the fundus image, which is not conducive to the positioning of the optic cup and optic disc, and may easily lead to inaccurate segmentation results.

However, most of the optic disc and optic cup segmentation methods based on deep learning ignore the preservation of edge features and do not combine edge information with the optic cup and optic disc regions.

In addition, some methods based on deep learning only segment the optic disc, or segment the optic disc and the optic cup separately, ignoring the connection between the optic disc and the optic cup

Images