Operation method of an automatic needle insertion device combining a blood flow optimization model and a neural network

Abstract

To provide an automatic needle insertion method combining a blood flow optimization model and a neural network.SOLUTION: First, a position of a blood vessel and blood flow velocity distribution of a region waiting for needle insertion are calculated by blood flow information measured by automatic ultrasonic scanning using a Doppler ultrasonic principle. Then, a blood flow relative velocity optimization model and a neural network having a selection function are established, and optimum needle insertion point and needle insertion angle are determined on the basis of a result of physical measurement. Last, a needle insertion route is designed by simulating a needle insertion method of specialized staff using a neural network having a learning function. This method can be used for needle insertion for a subcutaneous blood vessel of a body part such as limbs, and can provide technical assistance for a self-help emergency situation in an environment where specialized staff is not enough while overcoming the difficulty of needle insertion by a human when blood vessel visibility by naked eyes is low.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to the fields of artificial intelligence and medicine, and more specifically to an automatic needle insertion method that combines a blood flow optimization model and a neural network. [Background technology]

[0002] Needle insertion into veins is a ubiquitous part of modern medicine, from small procedures such as venous blood sampling during health checkups to large procedures such as blood transfusions during emergency treatment. However, accurately locating veins or arteries and determining their direction of travel is often difficult for medical staff. For example, some people's veins are thin, tightly encased in subcutaneous fat and muscle layers, or have thick fur, making them difficult to see with the human eye. On the other hand, animals' veins are often covered in fur, making it difficult for the human eye to determine the direction of veins and arteries. Emergency care is often delayed due to the inability to accurately locate veins suitable for needle insertion. Poor needle insertion techniques can result in multiple unnecessary injections for patients or animals, resulting in pain, bleeding, and varying degrees of infection, as well as medical accidents and serious conflicts between patients' families and doctors.

[0003] Ultrasound can be used to detect superficial and deep tissues invisible to the human eye, and is particularly suitable for accurately detecting and locating blood vessels in the human and animal bodies. In nature, vampire bats use their ultrasonic capabilities to accurately determine the distribution of blood vessels invisible to the human eye in the bodies of animals and livestock, thereby achieving blood feeding. In artificially developed medical devices, color Doppler ultrasound imaging devices can provide two-dimensional or three-dimensional image information, such as the direction and velocity of blood flow within a given cross-section.

[0004] However, currently, there is no automated needle insertion method based on Doppler ultrasound principles and blood flow optimization models that does not require imaging. Summary of the Invention

[0005] JPEG0007750565000001.jpg124163

[0006] Furthermore, the above step 1 includes automatic ultrasound scanning with multiple sets of frequencies and adjustable angles, and calculating the blood vessel position and blood flow velocity based on ultrasound Doppler.Usually, ultrasound examinations in medical practice are performed manually, but to obtain the variable values ​​required for the above blood flow relative velocity optimization model and achieve the purpose of automatic needle insertion, ultrasound scanning with automatically adjustable emission angle and frequency is performed on the body part waiting for needle insertion, and automatic measurement is performed using the Doppler principle.

[0007] Ultrasound scanning can be either mobile or stationary, with mobile ultrasound scanning requiring the ultrasound probe to automatically rotate at variable angles within a local area and perform mobile translational scanning along a movable support, while stationary ultrasound scanning employs an electronically controlled phased array mode.

[0008] Based on the collected ultrasound information, irrelevant information is filtered out, and the necessary information, including the local spatial distribution and blood flow direction of the major subcutaneous blood vessels at the needle insertion site, is demodulated and calculated using the Doppler ultrasound principle.The method for measuring and marking the blood flow spatial angle using the ultrasonic Doppler principle is as follows:

[0009] The red blood cells move along the X axis, i.e., the direction of blood flow, at a velocity v, and W is the reference axis, which may be perpendicular to the direction of gravity. The Z axis, X axis, and W axis are in the same plane, of which the Z axis is perpendicular to the X axis, and the angle between the Z axis and W is φ. Ultrasound with a radiation frequency of f0 from the ultrasonic probe travels at a sound speed c in the body medium. S The scattered signal propagates to the detection target at f and returns to the receiving probe. The received frequency is f rThe ultrasound incident plane is the plane P1 on which the incident sound beam axis and the Z axis are located, and the axis perpendicular to the Z axis in P1 is Y. The included angle between the ultrasound incident plane and the blood flow direction is α, i.e., the included angle between the X axis and the Y axis is α. The included angle between the incident sound beam axis and the XY plane is β, i.e., the included angle between the incident sound beam axis and the Y axis is β. The scattering plane on which the scattered sound beam axis of the red blood cell(s) along the receiver direction and the Z axis is located is P2. The axis perpendicular to the Z axis in P2 is Y'. The included angle between the Y' axis and the blood flow direction is α', and the included angle between the scattered sound beam axis and the Y' axis is β'. The intersection angle between the incident sound beam axis and the W axis is γ, and the intersection angle between the scattered sound beam axis and the W axis is γ'. The values ​​of γ and γ' can be measured directly.

[0010] JPEG0007750565000002.jpg118170After the scanning angle is changed, based on the collected and filtered extracted effective ultrasound feedback band, a set of Doppler shifts is obtained by directional demodulation, and the blood vessel position and blood flow velocity parameters are calculated using the frequency shift change equation set, the corresponding delay change, and Equation (3) to obtain the relative flow velocity and relative angle parameters (μ, α, β, φ), and further obtain the distribution and running direction of the local blood vessels in the required needle insertion area relative to the reference coordinate.When the ultrasound transmitter and receiver are located in the same probe, i.e., at the same spatial position, the frequency shift change equation set is as follows: In equations (8a)-(9), the ± sign ensures that the calculation quantity on the right side is consistent with the sign of cosβ or cosα on the left side. Under conditions where Δα and Δβ can be accurately controlled, the relative angle parameters are calculated, and the local relative flow velocity is obtained from the frequency shift change equation. Furthermore, the included angle φ between the Z axis and the reference axis w is calculated and recorded using equation (3). Also, even if the parameter α is maintained, the value of B can be obtained by calculating the delay due to the pitch change. JPEG0007750565000004.jpg28170

[0011] JPEG0007750565000005.jpg106163

[0012] JPEG0007750565000006.jpg81170JPEG0007750565000007.jpg68170

[0013] JPEG0007750565000008.jpg22170

[0014] JPEG0007750565000009.jpg63164

[0015] JPEG0007750565000010.jpg54170

[0016] Furthermore, in the above step 3, the preferred needle insertion plan and actual clinical expression scores obtained from the physical measurement and the relative blood flow velocity optimization model are used to train a neural network with a selection function, which is then integrated into a single learning chip. The neural network with a selection function includes multiple intermediate layers, and the parameters (μ1, α1, β1, φ1), ... (μ5, α5, β5, φ5) corresponding to the relative blood flow velocity and coordinates of the candidate injection points and the serial numbers (1, 2, 3, 4, 5) are used as input data for the input layer, and evaluation feedback is performed on the needle insertion coordinates and needle insertion angle physically calculated by experienced medical professionals. Where μ is the ultrasonic sound speed c in human or animal tissue medium. s is the ratio of the blood flow velocity to the incident sound beam. α, β, and φ determine the included angle between the incident sound beam and the blood flow direction. The evaluation feedback content of the learning group includes the preferred injection position previously marked on the experimental sample by the medical professional using other medical equipment, the blood vessel direction at the time of actual needle insertion, and a serial number ranking given based on priority. The preferred injection position and blood vessel direction noted in the experiment are scanned and calculated by the system and fed back to the neural network with the above-mentioned selection function in data form. After multiple use evaluations, the trained neural network with the selection function can output the optimal needle insertion coordinates and needle insertion angle in the parameter form (p, α0, β0, φ0, d) based on the input data.

[0017] JPEG0007750565000011.jpg23170

[0018] JPEG0007750565000012.jpg26170

[0019] The beneficial effects of the present invention are as follows: (1) By combining a blood flow optimization model with the learning and discrimination functions of a neural network, the present invention automatically selects the optimal needle insertion position on a blood vessel and designs a needle insertion path that mimics the needle insertion technique of professional staff, thereby overcoming the difficulty of finding blood vessels with the naked eye under special circumstances and improving the survival rate of self-help emergency care in environments where professional staff are in short supply. (2) The present invention is useful in avoiding or reducing the pain and suffering caused by repeated needle insertion failures in humans and animals. (3) The present invention is based on the ultrasonic Doppler principle, but only requires the calculation and optimization of spatial coordinates within a local area using relevant data on blood flow velocity, eliminating the need for three-dimensional ultrasonic imaging. This eliminates the enormous amount of calculation and development equipment required for three-dimensional ultrasonic imaging, and provides the basis for a novel technical method for realizing an automatic needle insertion device that is small in volume, light in weight, and easy to carry. [Brief explanation of the drawings]

[0020] [Figure 1] FIG. 1 is a schematic diagram of the overall flow of an automatic needle insertion method that combines a blood flow optimization model and a neural network. [Figure 2] FIG. 2 is a schematic diagram showing the relationship between angular parameters in the Doppler shift calculation formula. DETAILED DESCRIPTION OF THE INVENTION

[0021] The present invention will now be described in more detail with reference to the accompanying drawings and examples, in which: The specific embodiments described herein are intended to be illustrative of the invention and are not intended to be limiting thereof. As shown in Figure 1, the automatic needle insertion method combining the blood flow optimization model and neural network includes three main parts in the overall implementation process: obtaining ultrasonic blood flow information, constructing a blood flow relative velocity optimization model and determining the neural network, and automatic needle insertion. The specific steps are as follows:

[0022] Step 1: Acquisition of ultrasonic blood flow information, which utilizes the Doppler ultrasonic principle to calculate the blood vessel position and blood flow velocity distribution in the injection area based on the blood flow feedback signal measured by automatic ultrasound scanning.

[0023] To obtain the necessary variable values ​​for the blood flow relative velocity optimization model and achieve the goal of automatic needle insertion, an ultrasound scan is performed at the target needle insertion site, with the emission angle and frequency automatically adjusted, and the Doppler principle is used for automatic measurement. Ultrasound scanning can be performed in either a mobile or stationary mode. Taking arm vein insertion as an example, a mobile mode refers to the ultrasound probe being able to automatically translate along the arm axis within the parallel cut plane of the skin within a certain distance around the injection site, and also be able to rotate axially within a certain angle range. Therefore, a holder of an appropriate length must be provided to accommodate the probe's small range of movement. A stationary probe can achieve focusing using a phased array or electronically controlled phase difference, and is more suitable for body parts with limited moving space. Additionally, the ultrasound emitter must be automatically adjusted within a certain range (7.5 MHz or higher) and emit multiple sets of ultrasound waves at different frequencies. Because the needle insertion site is generally located shallowly under the skin, a relatively high ultrasound frequency stage can be used, improving sampling accuracy. Ultrasound scanning should be performed when the heart rate is stable, thereby ensuring a relatively stable cardiac cycle and avoiding or reducing blood flow disturbances.

[0024] Considering the need to protect the privacy of the human body being inserted, sampling must be completed within a limited space. The entire needle insertion device is fixed to the body part using a fixation device and remains stationary relative to the area requiring needle insertion, thereby ensuring the necessary accuracy for ultrasound detection and needle insertion. Selecting a good sampling volume is extremely important and challenging for obtaining accurate blood flow information. For example, increasing the number of phased arrays increases the density of the sampling grid, thereby improving accuracy. However, how to accurately select the sampling volume is beyond the scope of the above method of the present invention. The following calculations all assume that the sampling volume at each location can be determined automatically and satisfactorily within an extremely short time, and that sufficiently accurate measurement results can be obtained.

[0025] According to the installation position of the needle insertion device, a reference coordinate is selected, and the blood vessel position, blood flow velocity, and other variables are automatically measured using the Doppler ultrasound principle. Below, we will describe a method for measuring and marking the spatial angle of blood flow direction using the Doppler ultrasound principle.

[0026] As shown in Figure 2, red blood cells move at a speed v along the X-axis (blood flow direction). W is the reference axis, and the vertical axis is the direction of gravity. The Z-axis, X-axis and W-axis are on the same plane, the Z-axis is perpendicular to the X-axis, and the intersection angle between the Z-axis and W is φ. The emission frequency of the ultrasonic probe is f0. Ultrasound travels at a sound speed of c in the medium inside the body. s propagates to the target and returns the scattered signal to the receiving probe at frequency f rThe ultrasound is received at the receiver. The ultrasound incidence plane is the plane P1 where the incident sound beam axis and the Z axis lie, and the axis perpendicular to the Z axis in P1 is Y. The included angle between the ultrasound incidence plane and the blood flow direction is α, i.e., the included angle between the X axis and the Y axis is α. The included angle between the incident sound beam axis and the XY plane is β, i.e., the included angle between the incident sound beam axis and the Y axis is β. The scattering plane where the scattered sound beam axis of the red blood cell(s) along the receiver direction and the Z axis is located is P2. The axis perpendicular to the Z axis in P2 is Y', the included angle between the Y' axis and the blood flow direction is α', and the included angle between the scattered sound beam axis and the Y' axis is β'. The intersecting angle between the incident sound beam axis and the W axis is γ, and the intersecting angle between the scattered sound beam axis and the W axis is γ', where γ and γ' can be measured directly. The angle between the incident sound beam axis and the blood flow direction should not be too large; that is, the initial values ​​of α, β, α', and β' are to be determined, but they should not exceed 60 degrees to avoid inaccurate measurement results. Ultrasonic receiving frequency f r The relation between (t+Δt) and the incident frequency f0(t) is as follows: JPEG0007750565000013.jpg94170JPEG0007750565000014.jpg135170JPEG0007750565000015.jpg101170In equation (10), 1 is the distance between the probe and the target detection point, t is the time when the ultrasonic wave is transmitted, and t k indicates the signal reception time when β becomes β+k△β and α remains the same. If Δα and Δβ can be precisely controlled, the relative angle parameters can be determined, and the local relative flow velocity can be obtained from the frequency shift variation equation. j and △β k One alternative method to accurately control the value of is to transmit a set of ultrasonic pulses with a fixed relative angle (which can be easily controlled accurately using a phased array) to each location where blood flow velocity is to be detected. In setting the frequency shift change equation set, the selected frequency shift intensity is higher than a certain threshold, i.e., a large amount of low-intensity frequency shift information corresponds to non-blood flow-related information and can be excluded in advance and not considered.

[0027] Step 2: Establish a blood flow relative velocity optimization model and calculate the relative velocity from the physical measurements and the blood flow relative velocity optimization model. Calculate multiple preferable needle insertion plans, which are combinations of preferable blood vessel positions and blood flow directions suitable for needle insertion. obtain.

[0028] Locations near the skin surface where the change in the direction of blood flow in μ value is gradual and the blood flow rate is relatively large (corresponding to thick, unbranched veins) are considered to be ideal needle insertion location candidates, and these (five hypotheses) are denoted as p1, p2, ..., p5. Here, p1 is the optimal needle insertion point obtained by physical calculation, and p2 is the next best needle insertion point. We will proceed by analogy in order.

[0029] JPEG0007750565000016.jpg187164

[0030] JPEG0007750565000017.jpg32170

[0031] JPEG0007750565000018.jpg70170JPEG0007750565000019.jpg64170JPEG0007750565000020.jpg34170

[0032] JPEG0007750565000021.jpg27170

[0033] JPEG0007750565000022.jpg57170

[0034] Step 3: The preferred needle insertion plan obtained in Step 2 is combined with a neural network with a selection function to determine the optimal needle insertion point and angle, thereby obtaining the optimal needle insertion plan.

[0035] To improve clinical efficacy, a neural network (Network 1) with a selection function is trained using optimal values ​​obtained from physical measurements and mathematical optimization models, along with actual clinical expression scores, and integrated into a single training chip. A simple example is to create a convolutional neural network with multiple hidden layers, using parameters (μ1, α1, β1, φ1)...(μ5, α5, β5, φ5) corresponding to candidate injection points and serial numbers (1, 2, 3, 4, 5) as input data for the input layer. Experienced specialists evaluate and provide feedback on the physically calculated needle insertion coordinates and needle insertion angle. The training group's evaluation feedback can include the preferred needle insertion position and vascular direction marked on the experimental sample by the specialists using another device, as well as a ranking based on priority, such as (2, 1, 3, 5, 4). The optimal needle insertion position and vascular direction marked during the experiment are then scanned and calculated by the system and fed back to the neural network in the form of data. After multiple evaluations, the neural network trained with the selection function can provide a better output scheme based on the input data, and can determine the optimal blood vessel to use for needle insertion, the needle insertion point p, and the exact direction of blood flow at that point (α0, β0, φ0).

[0036] The above physical calculations, blood flow optimization model calculations, and neural network training can be integrated into a small chip or small computing device (rather than an external standalone PC or mainframe), making the entire needle insertion device more portable. Therefore, the selection of the optimization model and the number of nodes and layers of the neural network should meet practical computing capabilities.

[0037] It should be further noted that the device required by the present invention utilizes the Doppler ultrasound principle, but has the following essential differences compared to color Doppler blood flow imaging systems. The present invention utilizes a blood flow optimization model and Doppler principle to calculate the blood flow velocity distribution, calculate the exact position and angle of the sampling volume relative to the reference coordinate, prepare the needle, and eliminate the need for imaging, resulting in a small volume, small weight, and easy portability.Color Doppler blood flow imaging is intuitive and qualitative, and current color Doppler blood flow imaging systems require the cooperation of a display and a computer to process the collected ultrasound signals through digital ultrasound DSC processing to generate color images, which consumes a large amount of time and involves processing the large amount of data required to generate a three-dimensional image.

[0038] Step 4: Using the optimal needle insertion method, the needle head is controlled to accurately contact the optimal needle insertion point and begin needle insertion. During the needle insertion process, a neural network with learning capabilities is incorporated to learn and simulate professional needle insertion techniques, automatically adjusting the needle insertion angle and speed to obtain the needle insertion path.

[0039] JPEG0007750565000023.jpg32170

[0040] JPEG0007750565000024.jpg33162

[0041] The present invention uses ultrasound to accurately measure local blood flow information, and combines a blood flow velocity optimization model with a neural network to automatically adjust the needle insertion position and angle, and achieves automatic needle insertion by imitating the needle insertion technique of a professional. The automatic needle insertion technology and method of the present invention provides a technical basis for the production of a portable automatic needle insertion device, and subsequently provides convenience for using portable automatic devices to perform injections and blood collection in environments where there is a shortage of medical personnel.

[0042] The above is only a preferred embodiment of the present invention, and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the above embodiments, it is understood by those skilled in the art that modifications to the technical solutions described in the above embodiments or equivalent substitutions of some technical features thereof are still possible. Any modifications, equivalent substitutions, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

[Request 1] Request 2 Request 3 Request 4 Request 5 [Request 6] Request 7

Images