Venous blood sampling needle inserting point automatic extraction method based on vision

Abstract

The invention belongs to the technical field of machine vision and medical instruments and discloses a venous blood sampling needle inserting point automatic extraction method based on vision. The method comprises the following steps of carrying out whole skeleton extraction on venous bifurcations in a binary image, thereby obtaining an image containing a venous bifurcation center line, further obtaining intersection points of the venous bifurcations, and moreover, recording the coordinates of the intersection points of the venous bifurcations; carrying out partial skeleton extraction on the venous bifurcations in the binary image, thereby obtaining a partially refined image; processing the partially refined image according to the obtained coordinates of the intersection points of the venous bifurcations, carrying out statistics on the number of valid points of each intersection point in a preset length range of the midpoint of the intersection point column by column from the venous proximal part corresponding to the orientation of the intersection point, and further obtaining a length count value corresponding to each intersection point, wherein the interaction point corresponding to the venous bifurcation with the maximum length count value is the venous blood sampling needle inserting point. According to the method, the needle inserting point is extracted automatically and the precision and efficiency are improved.

Description

technical field [0001] The invention belongs to the related technical fields of machine vision and medical instruments, and more specifically relates to a vision-based automatic extraction method for venous blood collection needle points. Background technique [0002] Medical staff will frequently collect blood samples during physical examination and diagnosis of patients or during daily inspections. At present, most blood collection occasions use traditional blood collection methods, which require manual operations. This artificial blood collection method is inefficient and often cannot meet the blood collection requirements during peak hours, and because the blood collection operation is difficult and the risk factor is high, it requires high skills for medical staff, and some patients even have thicker fat and darker skin. And other reasons lead to blood vessels can not be clearly presented, and then lead to puncture failure, bring a lot of inconvenience to medical staff ...

AI Technical Summary

Problems solved by technology

[0002] Medical personnel will frequently collect blood samples during physical examination and diagnosis of patients or during daily inspections. At present, most blood collection occasions use traditional blood collection methods, which require manual operation.

This artificial blood collection method is inefficient and often cannot meet the blood collection requirements during peak hours, and because the blood collection operation is difficult and the risk factor is high, it requires high skills for medical staff, and some patients even have thicker fat and darker skin. Blood vessels cannot be clearly displayed due to other reasons, which leads to puncture failure and brings a lot of inconvenience to medical staff and patients

[0003] Aiming at the difficulty, high risk, and low efficiency of manual blood collection, relevant technical personnel in the field have done some research. For example, the VeinSight series of vascular imaging instruments invented by Bolian Zhongke (Wuhan) Technology Co., Ltd. can identify the superficial venous vessels of the human body. , and project the identified blood vessels onto the surface of the skin, which is convenient for medical staff to find veins; another example is patent 201320403264.2, which proposes a method of using near-infrared light with a mixed wavelength of 940nm and 850nm to irradiate veins to improve the image effect; however, the above method They are all used in auxiliary equipment for manual blood collection to improve the success rate and efficiency of manual blood collection. None of them involve automatic blood collection and the extraction of needle points in automatic blood collection. The needle points cannot be automatically extracted, and the extraction accuracy is low. , and the extraction efficiency is also low

Images