A Neural Network Model for Blood Vessel Segmentation in Fundus Images

Abstract

The invention relates to a neural network model for blood vessel segmentation in fundus images. The highest layer of blood vessel feature processing layer is connected to the lowest layer of blood vessel feature optimization layer through a backward short connection; each blood vessel feature optimization layer is connected to a higher layer through a forward short connection. The vascular feature optimization layer of the layer is connected; each vascular feature optimization layer is used to obtain the upsampled image of the connected vascular feature processing layer; the lowest layer of the vascular feature optimization layer is also used to obtain the features of the lowest layer of the vascular feature extraction layer image; each vascular feature optimization layer is also used to sequentially perform vascular feature extraction and nonlinear processing on each acquired image to obtain the nonlinear image corresponding to each image, and connect the acquired Each image is sent to a higher layer of vessel feature optimization layer. The invention transmits the high-level information to the low-level through the backward short connection, and transmits the low-level information to the high-level through the forward short connection, fully integrates the features of all levels, and makes the blood vessel segmentation more accurate.

Description

technical field [0001] The embodiment of the present invention relates to the field of computer technology, in particular to a neural network model for blood vessel segmentation in fundus images. Background technique [0002] Retinal fundus image analysis helps ophthalmologists to deal with the diagnosis, screening and treatment of cardiovascular and ophthalmic diseases, such as macular degeneration, diabetic retinopathy, glaucoma, hypertension, etc. These diseases can lead to blindness if left untreated. Vessel segmentation is a fundamental step in retinal image analysis and helps localize diabetic retinopathy and foveal regions. However, in clinical practice, manual labeling of blood vessels in retinal images is time-consuming and requires a lot of experience. Therefore, automatic retinal vessel segmentation is necessary to reduce labeling time. [0003] The automatic segmentation schemes of retinal image vessels in recent decades can be divided into two categories: uns...

AI Technical Summary

Problems solved by technology

In the supervised scheme, the neural network model needs to extract image features layer by layer, and a lot of useful information is lost, resulting in the parameters learned by the neural network model not being able to fully describe the characteristics of blood vessels.

Images