A blood vessel recognition and positioning method based on near infrared spectroscopy

Abstract

The present invention discloses a blood vessel identification and positioning method based on near infrared spectrum, comprising the following steps: S1, using a near infrared imaging camera to take an imaging picture to obtain an infrared imaging picture; S2, selecting a plurality of straight vein segments in the infrared imaging picture, and sorting the widths of the plurality of vein segments, and selecting the vein segments with the top five sorting as the vein segments to be collected; S3, using a near infrared imaging camera to take a plurality of photos, and extracting the photos of the vein segments to be collected; S4, in chronological order, taking the first photo as the reference photo, comparing the subsequent photos of the vein segments to be collected with the reference photo, recording the coincidence rates respectively, and calculating the average coincidence rate according to the respectively recorded coincidence rates; S5, setting the middle position of the vein segment to be collected with the highest average coincidence rate as the blood sampling point, and recording the coordinates of the point as the blood sampling point coordinates. Compared with the prior art, the present invention can realize accurate identification of blood vessels.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic blood sampling, and in particular to a blood vessel recognition and positioning method based on near infrared spectroscopy. Background Art

[0002] Usually, when it is necessary to collect blood samples from patients or donate blood, medical staff are required to draw blood manually. For example, in hospitals, blood collection stations and other places, there are a large number of subjects whose blood is drawn, and medical staff are required to work for a long time. This long-term repetitive blood collection operation makes medical staff in a state of high concentration for a long time, which is easy to cause fatigue and lead to unexpected medical errors. In order to save manpower and reduce medical errors, a blood collection robot specially used to replace medical staff to draw blood for patients has emerged. As long as the arm of the subject whose blood is drawn is in place, the blood collection robot can automatically complete the blood collection action, and the medical staff only needs to replace the test tube for collecting blood. The blood collection robot must identify the blood vessels before drawing blood, and the identification method in the prior art is not accurate enough. In view of this, the inventor of the present application has obtained a blood vessel identification and positioning method based on near-infrared spectroscopy after in-depth research. Summary of the invention

[0003] The purpose of the present invention is to provide a blood vessel recognition and positioning method based on near-infrared spectroscopy, which can realize accurate recognition of blood vessels.

[0004] The above technical objectives of the present invention are achieved through the following technical solutions:

[0005] A blood vessel identification and positioning method based on near-infrared spectroscopy comprises the following steps: S1, taking an imaging picture with a near-infrared imaging camera to obtain an infrared imaging picture; S2, selecting a plurality of straight vein segments in the infrared imaging picture, sorting the widths of the plurality of vein segments, and selecting the vein segments with the top five in the sorting as the vein segments to be collected; S3, taking a plurality of photos with a near-infrared imaging camera, and extracting the photos of the vein segments to be collected; S4, in chronological order, taking the first photo as a reference photo, comparing the subsequent photos of the vein segments to be collected with the reference photo, recording the coincidence rates respectively, and calculating the average coincidence rate according to the respectively recorded coincidence rates; S5, setting the middle position of the vein segment to be collected with the highest average coincidence rate as a blood sampling point, and recording the coordinates of the point as the blood sampling point coordinates.

[0006] In a preferred embodiment, step S3 further includes receiving a heartbeat frequency, and setting the heartbeat frequency as a shooting frequency of the near-infrared imaging camera.

[0007] In a preferred embodiment, in step S3, the number of photos taken by the near-infrared imaging camera is 3-5.

[0008] In a preferred embodiment, step S5 specifically includes: setting the middle position of the vein segment to be collected with the highest average overlap rate as the blood collection point, outputting an enlarged photo of the point, and receiving a pinhole identification and judgment information instruction, the pinhole identification and judgment information instruction includes "there is a pinhole" and "there is no pinhole". If "there is a pinhole" is received, the point is excluded and this step is restarted. If "there is no pinhole" is received, the point is determined to be the blood collection point, and the coordinates of the point are recorded as the blood collection point coordinates.

[0009] In a preferred embodiment, the method further includes: S6, using a near-infrared imaging camera to respectively take imaging pictures of the blood sampling point under two wavelength settings, and calculating the fat thickness of the blood sampling point based on the changes in light intensity at the blood vessels marked in the two imaging pictures.

[0010] Compared with the prior art, the present invention provides a blood vessel identification and positioning method based on near-infrared spectroscopy, through which an accurate identification process can be achieved and the most appropriate blood collection point coordinates can be obtained. Specifically, five straight vein segments that are more suitable for needle insertion are selected through the first screening, and they are defined as the vein segments to be collected. Then, the blood flow stability of these five vein segments to be collected is compared, and the middle part of the vein segment to be collected with the most stable blood flow is selected as the blood collection point, which can ensure the stability of blood collection work. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 The present invention relates to a flow chart of a blood vessel recognition and positioning method based on near infrared spectroscopy.

[0012] Figure 2 This is a first perspective structural schematic diagram of a blood sampling robot used in a blood vessel recognition and positioning method based on near-infrared spectroscopy according to the present invention.

[0013] Figure 3 This is a second viewing angle structural schematic diagram of a blood sampling robot used in a blood vessel recognition and positioning method based on near-infrared spectroscopy according to the present invention.

[0014] Figure 4 yes Figure 3 Schematic diagram of the enlarged structure of part A.

[0015] In the picture

[0016] Main unit 1; near-infrared imaging camera 2; first segment 3; second segment 4; needle transport mechanism 5; touch sensing device 6; distance sensor 7; handheld confirmer 8; driving cylinder 9; applicator head 10; needle 11. DETAILED DESCRIPTION

[0017] The present invention is further described in detail below in conjunction with the accompanying drawings.

[0018] This specific embodiment is merely an explanation of the present invention and is not a limitation of the present invention. After reading this specification, those skilled in the art may make non-creative modifications to the present embodiment as needed. However, as long as they are within the scope of the claims of the present invention, they are protected by the patent law.

[0019] like Figures 2 to 4 As shown, a blood sampling robot used in a blood vessel identification and positioning method based on near-infrared spectroscopy in this embodiment includes a host 1, a near-infrared imaging camera 2 and a mechanical arm, the mechanical arm includes a first segment 3, a second segment 4 and a needle transport mechanism 5, the first segment 3 is connected to the host 1, and forms a first degree of freedom with the host 1, the first segment 3 is connected to the second segment 4, forming a second degree of freedom, the second segment 4 is connected to the needle transport mechanism 5, forming a third degree of freedom, and the needle transport mechanism 5 is used for the execution of the blood sampling process. The above structures are all settings in the prior art, and those skilled in the art can clearly understand the settings of the structure. On this basis, in order to realize the control method of this embodiment, a forehead touch sensing device 6 is set on the host 1, and a sensor plate is set on the forehead touch sensing device 6. When the forehead touches the sensor plate, electrical information is generated. Such a sensor plate is a mature technology in the prior art.

[0020] Meanwhile, a distance sensor 7 may also be provided on the host 1 .

[0021] Furthermore, a handheld confirmer 8 may be provided on the host 1. The handheld confirmer 8 includes a shell and an electrical signal generating device built into the shell. The electrical signal generating device is provided with a button. When the button is pressed, an electrical signal is generated and sent to the host 1.

[0022] The blood sampling robot can also include a smearing component, which includes a driving cylinder 9 and a smearing head 10. A smearing liquid, such as iodine, is adhered to the smearing head 10. The smearing head 10 is connected to the driving cylinder 9 and is driven to move by the driving cylinder 9. The movement path of the smearing head 10 is located at the needle entry point of the needle 11 of the needle transporting mechanism 5. The driving cylinder is installed on the needle transporting mechanism 5.

[0023] like Figure 1As shown, a blood vessel recognition and positioning method based on near-infrared spectroscopy includes the following steps: S1, using a near-infrared imaging camera to take an imaging picture to obtain an infrared imaging picture; S2, selecting multiple straight vein segments in the infrared imaging picture, and sorting the widths of the multiple vein segments, and selecting the top five vein segments as the vein segments to be collected; S3, using a near-infrared imaging camera to take multiple photos, and extracting the photos of the vein segments to be collected; S4, in chronological order, taking the first photo as the reference photo, comparing the subsequent photos of the vein segments to be collected with the reference photo, recording the overlap rates respectively, and calculating the average overlap rate based on the respectively recorded overlap rates; S5, setting the middle position of the vein segment to be collected with the highest average overlap rate as the blood collection point, and recording the coordinates of the point as the blood collection point coordinates.

[0024] The embodiment of the present invention is a method for blood vessel identification and positioning based on near-infrared spectroscopy, which can realize accurate identification process and obtain the most appropriate blood collection point coordinates. Specifically, firstly, through the first screening, five straight vein segments that are more suitable for needle insertion are selected and defined as the vein segments to be collected. Then, the blood flow stability of these five vein segments to be collected is compared, and the middle part of the vein segment to be collected with the most stable blood flow is selected as the blood collection point, which can ensure the stability of blood collection work.

[0025] The stability of blood flow is judged by the coincidence rate of photos in each vein segment. In order to clearly explain this process, the five vein segments to be collected are defined as segment one, segment two, segment three, segment four and segment five, and segment one is taken as an example. First, photos of segment one at different times are obtained, and then the earliest photo is used as the reference photo, and multiple photos at later times are compared with the reference photo to obtain the respective coincidence rates. The coincidence rate here refers to the coincidence rate of vein images. After obtaining the respective coincidence rates, the respective coincidence rates are averaged to obtain the average survival rate, which is the average coincidence rate of segment one. According to this method, the average coincidence rates of segments two, three, four and five can be calculated respectively. By comparing the average coincidence rates, the comparison results of blood flow stability can be obtained. The reason is that the more stable the blood flow is, the smaller the imaging difference at different times should be, so we can get the results of blood flow stability by comparing the coincidence rates.

[0026] Furthermore, in order to ensure that the vein state is consistent when photographing at different time periods, step S3 further includes receiving the heart rate and setting the heart rate as the shooting frequency of the near-infrared imaging camera. In this way, the vein state is consistent each time a photo is taken, and some photos are not taken when the heart is contracted and some photos are taken when the heart is relaxed, thereby ensuring the consistency of the vein state when the photos are taken, so that the results have better reliability.

[0027] Specifically, in step S3, the number of photos taken by the near-infrared imaging camera is 3-5.

[0028] The step S5 specifically includes: setting the middle position of the vein segment to be collected with the highest average coincidence rate as the blood collection point, outputting an enlarged photo of the point, and receiving a pinhole identification and judgment information instruction, the pinhole identification and judgment information instruction includes "there is a pinhole" and "there is no pinhole". If "there is a pinhole" is received, the point is excluded and this step is restarted. If "there is no pinhole" is received, the point is determined to be the blood collection point, and the coordinates of the point are recorded as the blood collection point coordinates. The issuance of the pinhole identification and judgment instruction is realized through the doctor's operation. After the doctor sees the enlarged picture through the display screen set on the blood collection robot, he determines whether there is a pinhole in the picture. If there is a pinhole, an instruction with a pinhole is issued to avoid continuing the blood collection work. If there is no pinhole, an instruction without a pinhole is issued to allow the blood collection work to continue. Through such a program setting, it is possible to effectively eliminate the phenomenon of repeated blood collection from the same pinhole during blood collection, and effectively avoid the pain burden of the patient.

[0029] The blood vessel identification and positioning method based on near infrared spectroscopy in this embodiment also includes: S6, using a near infrared imaging camera to take imaging pictures of the blood sampling point under two wavelength settings, and calculating the fat thickness of the blood sampling point according to the light intensity changes at the blood vessels marked in the two imaging pictures. In this way, it is convenient to determine the needle insertion angle later.

[0030] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method, article or terminal device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or terminal device. In the absence of further restrictions, the elements defined by the sentence "include..." or "comprise..." do not exclude the existence of other elements in the process, method, article or terminal device including the elements. In addition, in this article, "greater than", "less than", "exceed" and the like are understood to exclude the number itself; "above", "below", "within" and the like are understood to include the number itself.

[0031] The above description of the embodiments is to facilitate the understanding and use of the present invention by those skilled in the art. It is obvious that those skilled in the art can easily make various modifications to the embodiments and apply the general principles described herein to other embodiments without creative work. Therefore, the present invention is not limited to the above embodiments. Improvements and modifications made by those skilled in the art based on the disclosure of the present invention without departing from the scope of the present invention should be within the protection scope of the present invention.

Claims

1. A blood vessel recognition and positioning method based on near infrared spectroscopy, characterized in that: The method comprises the following steps: S1, taking an imaging picture with a near-infrared imaging camera to obtain an infrared imaging picture; S2, selecting a plurality of straight vein segments in the infrared imaging picture, and sorting the widths of the plurality of vein segments, and selecting the first five vein segments as the vein segments to be collected; S3, taking a plurality of photos with a near-infrared imaging camera, and extracting photos of the vein segments to be collected; S4, in chronological order, taking the first photo as the reference photo, comparing subsequent photos of the vein segments to be collected with the reference photo, recording the coincidence rates respectively, and calculating the average coincidence rate according to the respectively recorded coincidence rates; S5, setting the middle position of the vein segment to be collected with the highest average coincidence rate as the blood collection point, and recording the coordinates of the point as the blood collection point coordinates.

2. The method for blood vessel identification and positioning based on near infrared spectroscopy according to claim 1, characterized in that: The step S3 also includes receiving the heartbeat frequency and setting the heartbeat frequency as the shooting frequency of the near-infrared imaging camera.

3. The method for blood vessel identification and positioning based on near infrared spectroscopy according to claim 1, characterized in that: In step S3, the number of photos taken by the near-infrared imaging camera is 3-5.

4. The method for blood vessel identification and positioning based on near infrared spectroscopy according to claim 1, characterized in that: The step S5 specifically includes: setting the middle position of the vein segment to be collected with the highest average coincidence rate as the blood collection point, outputting an enlarged photo of the point, and receiving a pinhole identification and judgment information instruction, the pinhole identification and judgment information instruction includes "there is a pinhole" and "there is no pinhole". If "there is a pinhole" is received, the point is excluded and this step is restarted. If "there is no pinhole" is received, the point is determined to be the blood collection point, and the coordinates of the point are recorded as the blood collection point coordinates.

5. The method for blood vessel identification and positioning based on near infrared spectroscopy according to claim 1, characterized in that: Also includes: S6. Use a near-infrared imaging camera to take imaging pictures of the blood sampling point at two wavelength settings respectively, and calculate the fat thickness of the blood sampling point based on the light intensity changes at the blood vessels marked in the two imaging pictures.

Images