A method and system for identifying elbow vein depth

Abstract

The present invention discloses a method for identifying the depth of elbow veins, comprising the following steps: obtaining a target vein from an ultrasonic image of the elbow; calculating the depth of the target vein based on the target vein; calculating the aspect ratio of the cross section of the target vein based on the target vein, and determining whether it is necessary to re-acquire the ultrasonic image of the elbow. Using this technical solution, the time consumed for a single calculation of the vein is short, and real-time calculation can be achieved, and the obtained vascular depth identification accuracy is higher.

Description

Technical Field

[0001] The present invention belongs to the technical field of vein recognition, and in particular relates to a method and system for recognizing the depth of elbow veins. Background Art

[0002] Elbow vein puncture is one of the basic medical care methods and an important method for clinical venous blood collection and intravenous infusion. Avoiding repeated punctures is an important issue of concern to patients and medical staff. In the traditional manual blood collection process, about 27% of patients do not have clear veins, and 40% of patients have too thin veins, which increases the difficulty of venous blood collection for medical staff. Repeated failure of intravenous injection also greatly increases the possibility of phlebitis, thrombosis and infection. First of all, the situation of different individuals is different. Smaller blood vessel diameter, darker skin color, thicker subcutaneous fat, and severe skin dehydration will have a greater impact on the success rate of puncture. Secondly, whether the patient cooperates with the nurse to complete the entire puncture process will also affect the success rate of puncture.

[0003] At present, most venous punctures are done manually by nurses. The manual puncture process usually involves first tying the patient's arm with a medical hose, then asking the patient to make a fist to make the blood vessel stand out, and then the nurse touches and presses to determine the thickness and position of the blood vessel. This process is a great test of the medical staff's clinical experience and proficiency in needle handling.

[0004] As a common medical device, the ultrasound probe plays an irreplaceable role. It can use ultrasound to measure tissues and organs below 5mm of the skin. Based on the shape of blood vessels in the ultrasound image of the blood sampler, the location and depth of puncture, the doctor can make a quick decision.

[0005] Detecting the subcutaneous location of the veins before puncture and obtaining information such as the depth of the veins has been proven to be an important and reliable means of improving the success rate of puncture. Summary of the invention

[0006] The purpose of the present invention is to provide an elbow vein identification method to solve the problem of failure of medical staff or robots to insert needles during venous blood sampling due to difficulty in determining the specific subcutaneous location of the elbow veins.

[0007] To achieve the above object, the present invention provides a method for identifying the depth of elbow veins, comprising the following steps:

[0008] Obtain the target vein from ultrasound images of the elbow;

[0009] Calculating the depth of the target venous blood vessel based on the target venous blood vessel;

[0010] The aspect ratio of the cross section of the target venous blood vessel is calculated based on the target venous blood vessel, and it is determined whether it is necessary to reacquire the ultrasonic image of the elbow.

[0011] Optionally, acquiring the target vein from the ultrasonic image of the elbow includes: determining whether the ultrasonic image of the elbow satisfies set conditions, and if not, reacquiring the ultrasonic image; the set conditions include: determining whether a threshold of the acquired ultrasonic image is greater than or equal to a preset threshold.

[0012] Optionally, acquiring the target vein from the ultrasound image of the elbow comprises:

[0013] Selecting a vein region based on the ultrasound image;

[0014] The selected ultrasound image is preprocessed to remove image noise; the ultrasound image after image noise removal is segmented, the blood vessel area is marked, and the target vein is obtained.

[0015] Optionally, the vein region is rectangular and has a depth range of 0 mm-12 mm.

[0016] Optionally, after the ultrasonic image after image noise is removed is segmented, it is also necessary to perform morphological processing of opening and closing operations on the segmented image.

[0017] Optionally, the blood vessel region is marked by using a connected region marking method, wherein the connected region with the most pixels is marked as a blood vessel.

[0018] Optionally, calculating the depth of the target venous blood vessel includes: calculating the pixel center coordinates of the connected area of ​​the target venous blood vessel using a geometric moment to obtain the vertical coordinate of the pixel center, and then converting it into an actual blood vessel depth according to a ratio.

[0019] Optionally, calculating the aspect ratio of the cross section of the target venous blood vessel includes: acquiring pixel coordinates of endpoints of the target venous blood vessel region, and calculating the aspect ratio of the cross section of the target venous blood vessel according to the pixel coordinates.

[0020] Optionally, it is determined whether the aspect ratio exceeds a preset aspect ratio threshold, and if so, the ultrasonic image of the elbow is reacquired.

[0021] Optionally, the preprocessing includes removing image noise by using Gaussian filtering.

[0022] The technical effect of the present invention is that: using this technical solution, the time consumed for a single calculation of venous blood vessels is short, and real-time calculation can be achieved, and the obtained blood vessel depth recognition accuracy is higher. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0024] Figure 1 It is a schematic diagram of a flow chart in an embodiment of the present invention. DETAILED DESCRIPTION

[0025] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0026] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0027] Embodiment 1

[0028] like Figure 1 As shown, this embodiment provides a method for identifying the depth of elbow veins, comprising the following steps:

[0029] Acquire a target vein from an ultrasound image of the elbow; for example, acquire an image of a superficial vein of the elbow using an ultrasound probe;

[0030] Calculating the depth of the target venous blood vessel based on the target venous blood vessel;

[0031] The aspect ratio of the cross section of the target venous blood vessel is calculated based on the target venous blood vessel to determine whether it is necessary to reacquire the ultrasonic image of the elbow. In this embodiment, the aspect ratio of the cross section is calculated to determine the proximity of the ultrasonic probe to the elbow.

[0032] Optionally, the ultrasound probe may be a 14 MHz high-frequency linear array B-type ultrasound probe, and the ultrasound image is a real-time B-type ultrasound picture stream with a picture stream frame rate of 10 fps.

[0033] A further optimization scheme for acquiring the target vein from the ultrasonic image of the elbow includes: determining whether the ultrasonic image of the elbow satisfies a set condition; if not, reacquiring the ultrasonic image; the set condition includes: determining whether a threshold of the acquired ultrasonic image is greater than or equal to a preset threshold.

[0034] In this embodiment, the average gray value of the image is calculated. If the average gray value of the image is lower than a preset threshold, it indicates that the probe is not in close contact with the skin. The probe is allowed to contact the skin again, and the ultrasound image is acquired again. The preset gray threshold is determined by the gain value of the image, and the range is generally 30-35.

[0035] Further optimization of the scheme to obtain the target vein from the ultrasound image of the elbow includes:

[0036] Selecting a vein region based on the ultrasound image;

[0037] The selected ultrasound image is preprocessed; the ultrasound image after image noise removal is segmented, the blood vessel area is marked, and the target vein is obtained.

[0038] Optionally, a threshold segmentation method is used to segment the ultrasonic image after removing image noise. The specific calculation formula is as follows:

[0039]

[0040] Among them, dst(i, j) is the grayscale value of the pixel at the coordinates (i, j) after image segmentation; src(i, j) is the grayscale value of the pixel at the coordinates (i, j) in the ultrasound image before segmentation; MaxVal is the maximum grayscale value; thresh is the threshold set by yourself.

[0041] According to a further optimization scheme, the vein region is rectangular with a depth range of 0 mm-12 mm and a width of 12 mm.

[0042] To further optimize the solution, after the ultrasonic image is segmented after removing the image noise, it is also necessary to perform morphological processing of opening and closing operations on the segmented image. The opening operation in morphological processing is used to remove impurity points. The closing operation is opposite to the opening operation. It is usually used to bridge the slender grooves and eliminate small holes. The specific calculation formulas of the opening and closing operations are as follows:

[0043]

[0044]

[0045] Among them, f is a binary image and b is a structural element.

[0046] To further optimize the scheme, the connected region labeling method is used to mark the vascular region, in which the connected region with the most pixels is labeled as a vessel.

[0047] Optionally, a seed filling method in the connected region labeling method is used to mark the blood vessels. The seed filling algorithm assumes that at least one pixel inside the connected region is known, and then tries to find all other pixels in the region and fill them.

[0048] A further optimization scheme for calculating the depth of the target vein includes: using geometric moments to calculate the pixel center coordinates of the connected area of ​​the target vein, obtaining the vertical coordinate of the pixel center, and then converting it into the actual blood vessel depth according to a certain ratio, i.e., the number of pixels per millimeter.

[0049] The image geometric moment calculation formula is as follows:

[0050]

[0051] Among them, m ij represents the (i+j)th order moment, and P(x, y) is the grayscale value at the pixel coordinate (x, y). Here x = y = 1. Let the pixel center coordinates of the graph be (X, Y), X = m10 / m00, Y = m01 / m00.

[0052] According to a further optimization scheme, calculating the aspect ratio of the cross section of the target venous vessel includes: obtaining pixel coordinates of four endpoints of the target venous vessel region, and calculating the aspect ratio of the cross section of the target venous vessel according to the pixel coordinates.

[0053] A further optimization scheme is used to determine whether the aspect ratio exceeds a preset aspect ratio threshold value, which is 2.5. If it exceeds the threshold value, the ultrasonic image of the elbow is reacquired.

[0054] According to a further optimization scheme, the preprocessing includes removing image noise by using Gaussian filtering method.

[0055] Optionally, the preprocessing further includes: the method of increasing the resolution includes interpolating the image using a bilinear interpolation method.

[0056] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed in the present application should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0057] In the present invention, unless otherwise clearly specified and limited, a first feature being "above" or "below" a second feature may mean that the first and second features are in direct contact, or the first and second features are in indirect contact through an intermediate medium. Moreover, a first feature being "above", "above" or "above" a second feature may mean that the first feature is directly above or obliquely above the second feature, or simply means that the first feature is higher in level than the second feature. A first feature being "below", "below" or "below" a second feature may mean that the first feature is directly below or obliquely below the second feature, or simply means that the first feature is lower in level than the second feature.

[0058] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0059] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

[0060] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0061] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0062] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0063] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

Claims

1. A method for identifying elbow vein depth, characterized in that: The following steps are involved: Obtain the target vein from ultrasound images of the elbow; Calculating the depth of the target venous blood vessel based on the target venous blood vessel; Calculating the aspect ratio of the cross section of the target venous blood vessel based on the target venous blood vessel, and determining whether it is necessary to reacquire an ultrasonic image of the elbow; Acquiring a target vein from an ultrasonic image of an elbow includes: determining whether the ultrasonic image of the elbow meets a set condition, and if not, reacquiring the ultrasonic image; the set condition includes: determining whether a threshold of the acquired ultrasonic image is greater than or equal to a preset threshold; Targeted veins to be acquired from ultrasound images of the elbow include: Selecting a vein region based on the ultrasound image; Preprocessing the selected ultrasound image to remove image noise; segmenting the ultrasound image after removing image noise, marking the blood vessel area, and obtaining the target vein; After the ultrasonic image is segmented after the image noise is removed, the segmented image needs to be morphologically processed by opening and closing operations; The connected region marking method is used to mark the blood vessel area, in which the connected region with the most pixels is marked as a blood vessel; Calculating the depth of the target venous blood vessel comprises: using geometric moments to calculate the pixel center coordinates of the connected area of ​​the target venous blood vessel, obtaining the ordinate of the pixel center, and then converting it into the actual blood vessel depth according to the ratio; The geometric moment calculation formula is as follows: Among them, m ij represents the (i+j)th order moment, and P(x, y) is the grayscale value at the pixel coordinates (x, y).

2. The method according to claim 1, characterized in that The vein area is rectangular and has a depth range of 0 mm-12 mm.

3. The method according to claim 1, characterized in that Calculating the aspect ratio of the cross section of the target venous blood vessel includes: acquiring pixel coordinates of endpoints of the target venous blood vessel region, and calculating the aspect ratio of the cross section of the target venous blood vessel according to the pixel coordinates.

4. The method according to claim 3, characterized in that It is determined whether the aspect ratio exceeds a preset aspect ratio threshold, and if so, the ultrasonic image of the elbow is reacquired.

5. The method according to claim 1, characterized in that The preprocessing includes removing image noise, and the method adopted is Gaussian filtering.

Images