Vein and artery recognition method based on neural network

Abstract

The invention provides a vein and artery recognition method based on a neural network. The vein and artery recognition method comprises the steps of inputting a to-be-recognized ultrasonic image intoa neural network model to be processed; obtaining position information of veins and arteries from a to-be-recognized ultrasonic image through the neural network model; distinguishing the marked vein and artery according to the acquired position information, and generating an ultrasonic image containing the vein mark and the artery mark. According to the invention, the method is used for automatically identifying the artery and the vein in the ultrasonic image to be identified, is safe and efficient, can help doctors to improve the diagnosis accuracy, better assists the doctors in identifying the artery and the vein, and further assists the doctors in venipuncture.

Description

technical field [0001] The invention relates to the technical field of medical ultrasound, in particular to a neural network-based vein and artery recognition method and system. Background technique [0002] In clinical medicine, many endovascular operations require catheter placement and puncture on veins, such as in the right jugular vein, such as central venous catheter placement, hemodynamic measurements, myocardial biopsy, and cardiac ablation. During jugular venipuncture, doctors rely on vision, touch, and experience to manually judge the location of blood vessels, such as detecting the pressure in the blood vessels and observing the color of blood to identify the nature of the blood vessels. These methods for judging the jugular vein based on blood vessel pressure and blood color have poor reliability. If the puncture needle enters the jugular vein, follow-up operations such as dilation and catheterization will continue; if the puncture needle is located in the caroti...

AI Technical Summary

Problems solved by technology

However, at present, the identification of arteries and veins in ultrasound images is still almost done manually, especially the identification of carotid arteries and jugular veins, which requires the operator to have professional knowledge of ultrasound images, which also causes the uncertainty of the identification results, which cannot be minimized. The risk of minimalist surgery; at the same time, it also limits the promotion and popularization of ultrasound-guided jugular vein puncture

Images