Eye fundus image blood vessel segmentation method

Abstract

The embodiment of the invention relates to an eye fundus image blood vessel segmentation method. Each blood vessel feature processing layer sends an up-sampling image self-obtained to a connected blood vessel feature optimization layer; a blood vessel feature optimization layer at the lowest layer also acquires a feature image of a blood vessel feature extraction layer at the lowest layer; the blood vessel feature processing layer at the highest layer sends the up-sampling image self-obtained to the blood vessel feature optimization layer at the lowest layer by virtue of a backward short connection; each blood vessel feature optimization layer sequentially performs blood vessel feature extraction and non-linear processing on each acquired image and obtains a non-linear image correspondingto each image; and each blood vessel feature optimization layer sends each acquired image to the blood vessel feature optimization layer one layer higher by virtue of a forward short connection. The embodiment of the invention sends high layer information to lower layers by virtue of the backward short connection and sends low layer information to higher layers by virtue of the forward short connection and fully fuses features of all the levels, so that blood vessel segmentation is more accurate.

Description

technical field [0001] Embodiments of the present invention relate to the field of computer technology, and in particular to a method for segmenting blood vessels 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: unsupervised schem...

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