Blood vessel, artery and vein identification method for fundus photography

Abstract

The invention discloses a blood vessel, artery and vein identification method for fundus photography. Each position in the fundus photography is automatically positioned and measured to achieve an effect on pre-screening diseases, pictures with lesion suspicions can be automatically screened so as to accurately and effectively carry out mark identification on blood vessel contours and blood vesselarteries and veins, then, the diameter ratio of arteries and veins can be calculated to assist in diagnosing diseases, including retina blood vessels and the like, and the workloads of doctors are reduced. In addition, the result of the method does not depend on the experience of doctors and is more objective, doctors can be effectively assisted in diagnosing diseases, and a purpose of remote consultation is realized.

Description

technical field [0001] The invention relates to a method for identifying blood vessels and arteries and veins in fundus color photographs. Background technique [0002] In order to identify and draw the boundaries of blood vessels and arteries and veins in fundus color photos quickly and in large quantities, so as to accurately and effectively identify the outline of blood vessels and mark identification with blood vessels, arteries and veins, and then calculate the diameter ratio of veins and arteries to assist in the diagnosis of the retina diseases such as blood vessels. In clinical practice, due to the limited manpower of ophthalmologists in remote mountainous areas, grass-roots hospitals, and fundus-related film readers, such as mechanically reviewing a large number of fundus color photos one by one, the work content is heavy, single and repetitive, and the efficiency is not high. , wasting a lot of valuable human resources. The existing fundus color photo automatic r...

AI Technical Summary

Problems solved by technology

In clinical practice, due to the limited manpower of ophthalmologists in remote mountainous areas, grass-roots hospitals, and fundus-related film readers, such as mechanically reviewing a large number of fundus color photos one by one, the work content is heavy, single and repetitive, and the efficiency is not high. , wasting a lot of valuable human resources

The existing fundus color photo automatic recognition system also involves the automatic recognition and partition method of the fundus image, but it does not carry out the precise positioning of the fundus structure position, lesion identification

In addition, most of the existing methods use standard pictures on the Internet for reference comparison and identification. However, the color fundus pictures in clinical practice are not standard pictures, and even include many pictures with problems with focus and brightness. At present, many systems directly use the pictures Recognition, regardless of the quality of the picture, because the standard library on the Internet is a good quality picture, and the number is very small

Images