Intelligent collaborative robot system for microneedle introduction

Abstract

The application provides a kind of intelligent collaborative robot system for microneedle introduction, and relates to medical puncture technology field.The application obtains characteristic parameters such as skin cuticle thickness, surface roughness and hue by optical scanning and image processing technology, and predicts initial puncture depth and initial puncture frequency using a deep learning model;During the puncture process, real-time monitoring of skin humidity, impedance, tissue density and hue changes generates depth adjustment index and frequency adjustment index to adjust the initial puncture depth and initial puncture frequency.This method realizes real-time perception of skin state and precise regulation of puncture parameters, significantly improving the safety of microneedle treatment.

Description

Technical Field

[0001] The present invention relates to the field of medical puncture technology, and in particular to an intelligent collaborative robot system for microneedle introduction. Background Art

[0002] Microneedle insertion technology has a wide range of applications in the fields of medical cosmetology and drug delivery, but its effectiveness and safety are highly dependent on the precise control of puncture parameters. In existing technologies, the depth and frequency of microneedle puncture are usually set based on experience, and there is a lack of real-time monitoring and dynamic adjustment of skin conditions. As a result, the puncture process may cause excessive stimulation or insufficient penetration due to individual differences in skin stratum corneum thickness, roughness, humidity, etc. In addition, traditional methods have difficulty accurately identifying changes in hue and tissue density on the skin surface, and are unable to adjust puncture parameters in time to adapt to the characteristics of different skin layers. These problems limit the accuracy and safety of microneedle technology, and there is an urgent need for an intelligent system that can monitor skin conditions in real time and dynamically optimize puncture parameters.

[0003] In the prior art, publication number CN118787850A discloses a microneedle control method, device, electronic device and storage medium, which monitor the skin resistance of the microneedle during the puncture process and determine the motor speed of the microneedle thrust motor based on the skin resistance, wherein the microneedle thrust motor is used to push the microneedle to puncture the skin; the microneedle thrust motor is controlled based on the motor speed to push the microneedle for puncture; the actual depth of the microneedle puncture is monitored, and when the actual depth reaches the target depth, the microneedle thrust motor is stopped, thereby ensuring that the microneedle can reach the target depth.

[0004] The main problems with the above method are: it only relies on skin resistance to adjust the thrust motor, but skin resistance can only reflect local mechanical impedance and cannot fully reflect the true state of the skin, which may cause the puncture to be too deep or too shallow, affecting the safety of microneedle introduction; and the motor speed is only adjusted during the puncture process, without considering the changes in skin state after puncture, and the puncture parameters cannot be dynamically adjusted according to the real-time state.

[0005] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0006] The purpose of the present invention is to provide an intelligent collaborative robot system for microneedle introduction to solve the problems raised in the above background technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] The intelligent collaborative robot system for microneedle insertion includes:

[0009] The skin scanning module is used to scan the target skin area where microneedle puncture is required to obtain the thickness of the skin stratum corneum;

[0010] An image processing module is configured to capture a surface image of the target skin area, convert the image into a grayscale image to generate a first recognition image, convert the image into the HSV color space to generate a second recognition image, extract edge pixels from the first recognition image based on Canny edge detection, generate skin surface roughness based on the number of edge pixels and the area enclosed by the edge pixels, obtain the hue of the pixels in the second recognition image, and generate the hue of the target skin area based on the hue of all pixels, which is recorded as the baseline hue;

[0011] The model building module is used to build a deep learning network, using the known skin stratum corneum thickness and skin surface roughness as input and the microneedle puncture depth and puncture frequency as labels to train the puncture parameter prediction model;

[0012] a parameter generation module, configured to input the stratum corneum thickness and skin surface roughness of the target skin area into a puncture parameter prediction model to generate initial puncture parameters, the initial puncture parameters including an initial puncture depth and an initial puncture frequency;

[0013] A frequency adjustment module is used to measure the surface humidity and skin layer impedance of the target skin area before puncture, recording them as baseline humidity and baseline impedance. After the microneedle is introduced into the skin according to the initial puncture parameters, the module monitors the changes in humidity and skin layer impedance of the target skin area in real time during the monitoring period. Based on the changes in humidity and impedance, a frequency adjustment index is generated to adjust the initial puncture frequency in real time.

[0014] The depth adjustment module is used to measure the tissue density of the target skin area before puncture, record it as the baseline density, monitor the tissue density and skin surface color of the target skin area in real time during the monitoring period, generate a depth adjustment index, and adjust the initial puncture depth in real time.

[0015] Furthermore, the principle for generating skin surface roughness is as follows:

[0016] For each pixel in the first recognition image, convolve the pixel and its neighboring pixels with the horizontal and vertical templates of the Prewitt operator to generate the grayscale difference of the pixel in the horizontal and vertical directions. The formula is:

[0017]

[0018] Among them, P X represents the horizontal template of the Prewitt operator, P YRepresents the vertical template of the Prewitt operator, G x Represents the horizontal difference of the pixel, G y Represents the vertical difference of the pixel point, (x, y) represents the coordinates of the pixel point;

[0019] The gradient amplitude of each pixel is generated based on the grayscale difference in the horizontal and vertical directions. The formula is:

[0020]

[0021] Among them, G(x,y) represents the gradient amplitude of the pixel point with coordinates (x,y), G x Represents the horizontal difference of the pixel, G y Indicates the vertical difference of the pixel;

[0022] A preset edge threshold is set, and when the gradient amplitude of a pixel point is higher than the edge threshold, it is considered an edge pixel point;

[0023] The number of edge pixels and the area of ​​the area enclosed by the outermost edge pixels are obtained based on all edge pixels to generate the skin surface roughness. The formula is:

[0024]

[0025] Among them, R represents the roughness of the skin surface, S represents the area enclosed by the outermost circle of edge pixels, and N represents the number of edge pixels.

[0026] Furthermore, the principle for generating the hue of the target skin area is as follows:

[0027] The principle of converting an image to the HSV color space is:

[0028] For any point in the image, its RGB color space is (R, G, B), and its HSV color space is (H, S, V). First, normalize the R, G, and B values:

[0029]

[0030] Among them, R0 represents the normalized red channel value, G0 represents the normalized green channel value, B0 represents the normalized blue channel value, R represents the red channel value, G represents the green channel value, and B represents the blue channel value;

[0031] The formula for generating H, S, and V based on R0, G0, and B0 is:

[0032] V=max(R0,G0,B0)

[0033]

[0034] Among them, H, S, and V represent hue, saturation, and brightness respectively.

[0035] The formula for generating the hue of the target skin area based on the hue of all pixels is:

[0036]

[0037] Among them, H total Indicates the hue of the target skin area, H i Represents the hue of the i-th pixel, i represents the index of the pixel, n represents the number of pixels, and atan2[] represents the four-quadrant inverse tangent function.

[0038] Furthermore, the principle for generating the frequency adjustment index to adjust the initial puncture frequency in real time is as follows:

[0039] The frequency adjustment index is generated based on the formula:

[0040]

[0041] Among them, k f,t Represents the frequency adjustment index at time t, M t Represents the humidity value at time t, t represents the index of the monitoring time, and t∈[0,T], T represents the length of the monitoring period, M0 represents the reference humidity, M max Represents the humidity safety threshold, Z t represents the skin layer impedance at time t, Z min represents the impedance safety threshold, Z0 represents the reference impedance, w1 and w2 represent the weight coefficients of humidity and impedance respectively, w1+w2=1 and w1>w2;

[0042] The formula for adjusting the puncture frequency is:

[0043] f t =f0×[1+u1×(k f,t -0.5)]

[0044] Among them, f t represents the puncture frequency adjusted at time t, f0 represents the initial puncture frequency, u1 represents the frequency adjustment gain coefficient, u1∈(0,1].

[0045] Furthermore, the principle for generating the depth adjustment index to adjust the initial puncture depth in real time is as follows:

[0046] The formula for generating the depth-adjusted index is:

[0047]

[0048] Among them, kd,t represents the depth adjustment index at time t, ρ t represents the tissue density at time t, ρ0 represents the reference density, and H t represents the skin surface hue at time t, H max Indicates the maximum hue value, H max =360°, w3 and w4 represent the weight coefficients of tissue density and hue respectively, w3+w4=1 and w3>w4;

[0049] The formula for adjusting the puncture depth is:

[0050] d t =d0×(1-u2×k d,t )

[0051] Among them, d t represents the puncture depth adjusted at time t, d0 represents the initial puncture depth, u2 represents the depth adjustment gain coefficient, u2∈(0,0.5].

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] By integrating skin scanning, image processing, and deep learning technologies, this invention achieves precise measurement of skin stratum corneum thickness and skin surface roughness. Based on the skin stratum corneum and skin roughness, it predicts the initial puncture depth and frequency, ensuring that the initial puncture parameters match the physiological characteristics of the target skin area, thereby improving the scientific nature of the initial puncture parameter setting. By real-time monitoring of humidity and impedance changes in the target skin area, the puncture frequency can be adjusted in a timely manner according to the dynamic changes in skin condition. This adaptability significantly improves the effectiveness of treatment, avoids potential problems caused by inappropriate initial parameters, effectively reduces errors during the puncture process, avoids skin damage or unnecessary side effects caused by inappropriate frequency, and enhances the safety of treatment. Furthermore, humidity and impedance changes are closely related to the skin's absorption capacity. Timely adjustment of the puncture frequency can effectively increase drug permeability and enhance the therapeutic effect.

[0054] This invention also dynamically adjusts the puncture depth based on the skin's actual physiological characteristics by measuring tissue density before puncture and monitoring both tissue density and skin surface color in real time during treatment. This precise control effectively avoids improper punctures due to individual differences, improving the safety and effectiveness of treatment. On the one hand, it ensures that the microneedle puncture reaches the ideal depth, allowing the drug to more effectively penetrate the target skin layer, helping to improve its bioavailability. On the other hand, it monitors changes in skin tissue density in real time, allowing for the timely identification of potential risk factors and appropriate adjustments, reducing the incidence of complications and ensuring patient safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 Schematic diagram of system modules according to an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to specific embodiments.

[0057] It should be noted that, unless otherwise defined, the technical or scientific terms used in the present invention should have the usual meanings understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative position relationships. When the absolute position of the object being described changes, the relative position relationship may also change accordingly.

[0058] Example:

[0059] See also Figure 1 , the present invention provides a technical solution:

[0060] An intelligent collaborative robot system for microneedle introduction, specifically comprising:

[0061] The skin scanning module is used to scan the target skin area where microneedle puncture is required to obtain the thickness of the skin stratum corneum;

[0062] In this embodiment, a high-resolution optical sensor and a confocal microscope are used to locate the target skin area where microneedle puncture is required. Near-infrared light is emitted by optical coherence tomography, and a reflected signal is received to generate a cross-sectional image. Since the stratum corneum has a high reflectivity and is distinguished from the living cell layer below, the target skin area is divided into five equal parts in the horizontal and vertical directions to form 25 intersections. The thickness of the stratum corneum is sampled at each intersection, and the average value of the stratum corneum thickness at the 25 intersections is calculated as the thickness of the stratum corneum of the skin.

[0063] An image processing module is configured to capture a surface image of the target skin area, convert the image into a grayscale image to generate a first recognition image, convert the image into the HSV color space to generate a second recognition image, extract edge pixels from the first recognition image based on Canny edge detection, generate skin surface roughness based on the number of edge pixels and the area enclosed by the edge pixels, obtain the hue of the pixels in the second recognition image, and generate the hue of the target skin area based on the hue of all pixels, which is recorded as the baseline hue;

[0064] The principles underlying the generation of skin surface roughness are:

[0065] For each pixel in the first recognition image, convolve the pixel and its neighboring pixels with the horizontal and vertical templates of the Prewitt operator to generate the grayscale difference of the pixel in the horizontal and vertical directions. The formula is:

[0066]

[0067] Among them, P X represents the horizontal template of the Prewitt operator, P Y Represents the vertical template of the Prewitt operator, G x Represents the horizontal difference of the pixel, G y Represents the vertical difference of the pixel point, (x, y) represents the coordinates of the pixel point;

[0068] The gradient amplitude of each pixel is generated based on the grayscale difference in the horizontal and vertical directions. The formula is:

[0069]

[0070] Among them, G(x,y) represents the gradient amplitude of the pixel point with coordinates (x,y), G x Represents the horizontal difference of the pixel, G y Indicates the vertical difference of the pixel;

[0071] A preset edge threshold is set, and when the gradient amplitude of a pixel point is higher than the edge threshold, it is considered an edge pixel point;

[0072] The gradient amplitude combines the grayscale changes in the horizontal and vertical directions and is used to measure the edge strength at the pixel point. The larger the gradient amplitude, the more likely it is an edge pixel point. The edge threshold is used to distinguish edge and non-edge pixels.

[0073] The number of edge pixels and the area of ​​the area enclosed by the outermost edge pixels are obtained based on all edge pixels to generate the skin surface roughness. The formula is:

[0074]

[0075] Among them, R represents the roughness of the skin surface, S represents the area enclosed by the outermost circle of edge pixels, and N represents the number of edge pixels.

[0076] Skin surface roughness represents the number of pixels within the area enclosed by pixels. The outermost edge pixels reflect the actual edge of the target skin area. Within the actual edge enclosed area, if there are pixels with gradient amplitudes greater than the edge threshold, they are also identified as edge pixels. The reason for the generation of such edge pixels is that the target skin area is relatively rough. During image detection, due to the unevenness of the area, there will be more pixels with higher gradient amplitudes, which in turn affects the overall number of edge pixels. The more edge pixels there are, the more uneven the target skin area is and the higher the skin surface roughness is. Conversely, if the number of edge pixels is smaller, it means that except for the outermost edge pixels, there are fewer pixels with high gradient amplitudes inside, and the corresponding skin surface roughness is lower. The skin surface roughness is inversely proportional to the area enclosed by the outermost edge pixels and directly proportional to the number of edge pixels.

[0077] In this embodiment, the principle for generating the hue of the target skin area is:

[0078] The principle of converting an image to the HSV color space is:

[0079] For any point in the image, its RGB color space is (R, G, B), and its HSV color space is (H, S, V). First, normalize the R, G, and B values:

[0080]

[0081] Among them, R0 represents the normalized red channel value, G0 represents the normalized green channel value, B0 represents the normalized blue channel value, R represents the red channel value, G represents the green channel value, and B represents the blue channel value;

[0082] The formula for generating H, S, and V based on R0, G0, and B0 is:

[0083] V=max(R0,G0,B0)

[0084]

[0085]

[0086] Among them, H, S, and V represent hue, saturation, and brightness respectively.

[0087] The formula for generating the hue of the target skin area based on the hue of all pixels is:

[0088]

[0089] Among them, H total Indicates the hue of the target skin area, H i Represents the hue of the i-th pixel, i represents the index of the pixel, n represents the number of pixels, and atan2[] represents the four-quadrant inverse tangent function.

[0090] Hue is an angle value, ranging from [0°, 360°], and 0° and 360° are equivalent. Therefore, the arithmetic mean cannot be used directly when calculating the average hue. The hue is converted into a vector in the rectangular coordinate system through the four-quadrant inverse tangent function. For the hue H of the i-th pixel point i , and its corresponding horizontal and vertical components are cos(H i )、sin(H i ), convert each hue into a vector and sum it up, the result is and Then calculate the point using the four-quadrant inverse tangent function The angle with the positive direction of the horizontal axis is the average hue, that is, the hue of the target skin area, which is also the benchmark hue before puncture.

[0091] The model building module is used to build a deep learning network, using the known skin stratum corneum thickness and skin surface roughness as input and the microneedle puncture depth and puncture frequency as labels to train the puncture parameter prediction model;

[0092] In this embodiment, the structure of the deep learning network is:

[0093] Output layer: contains 2 neurons, which are used to input the thickness of the skin stratum corneum and the roughness of the skin surface;

[0094] The first hidden layer: contains 64 neurons and is activated using the ReLU function;

[0095] The second hidden layer contains 32 neurons and is activated using the ReLU function.

[0096] Output layer: contains 2 neurons, which are used to output puncture depth and puncture frequency.

[0097] a parameter generation module, configured to input the stratum corneum thickness and skin surface roughness of the target skin area into a puncture parameter prediction model to generate initial puncture parameters, the initial puncture parameters including an initial puncture depth and an initial puncture frequency;

[0098] In this embodiment, the initial puncture parameters are generated based on the thickness of the skin stratum corneum and the roughness of the skin surface. When the microneedle is introduced, the skin stratum corneum is first penetrated. The thickness of the stratum corneum and the roughness of the skin surface mainly reflect the characteristics of the stratum corneum. Therefore, the initial puncture parameters required to penetrate the stratum corneum are determined based on the characteristics of the stratum corneum. The initial puncture parameters are then adjusted according to the changes in skin parameters during the actual introduction process.

[0099] A frequency adjustment module is used to measure the surface humidity and skin layer impedance of the target skin area before puncture, recording them as baseline humidity and baseline impedance. After the microneedle is introduced into the skin according to the initial puncture parameters, the module monitors the changes in humidity and skin layer impedance of the target skin area in real time during the monitoring period. Based on the changes in humidity and impedance, a frequency adjustment index is generated to adjust the initial puncture frequency in real time.

[0100] In this embodiment, the principle for generating a frequency adjustment index to adjust the initial puncture frequency in real time is as follows:

[0101] The frequency adjustment index is generated based on the formula:

[0102]

[0103] Among them, k f,t Represents the frequency adjustment index at time t, M t Represents the humidity value at time t, t represents the index of the monitoring time, and t∈[0,T], T represents the length of the monitoring period, M0 represents the reference humidity, M max Represents the humidity safety threshold, Z t represents the skin layer impedance at time t, Z min represents the impedance safety threshold, Z0 represents the reference impedance, w1 and w2 represent the weight coefficients of humidity and impedance respectively, w1+w2=1 and w1>w2;

[0104] The frequency adjustment index reflects the adjustment ratio of the puncture frequency under the influence of surface humidity and skin layer impedance. The surface humidity reflects the amount of tissue fluid that penetrates during the microneedle puncture introduction process. The higher the humidity, the more tissue fluid that penetrates. When the surface humidity is close to the safety threshold, the puncture frequency needs to be reduced to avoid excessive stimulation. Humidity is inversely proportional to the puncture frequency and therefore inversely proportional to the frequency adjustment index. When the humidity is lower than the baseline humidity, the skin surface is too dry, and the friction during microneedle puncture increases, which may make it difficult for the microneedle to penetrate. At this time, the puncture frequency should be increased to ensure that the microneedle effectively penetrates the stratum corneum.

[0105] Normalize the skin layer impedance to a safe range. When the impedance is lower than the safety threshold Z minWhen the impedance is low, it will cause abnormal microneedle introduction, which may be because the microneedle has penetrated the dermis and the skin is over-stimulated. The frequency needs to be reduced to ensure safety. When the impedance is high, it means that the microneedle has difficulty in continuing to penetrate, and the puncture frequency needs to be increased to ensure smooth penetration. Humidity can directly reflect whether tissue fluid has penetrated, so the weight coefficient of humidity is higher, taking w1=0.7 and w2=0.3.

[0106] The formula for adjusting the puncture frequency is:

[0107] f t =f0×[1+u1×(k f,t -0.5)]

[0108] Among them, f t represents the puncture frequency adjusted at time t, f0 represents the initial puncture frequency, u1 represents the frequency adjustment gain coefficient, u1∈(0,1].

[0109] f t It reflects the puncture frequency adjusted based on the initial puncture frequency at time t, and the puncture frequency adjusted at time t actually acts at time t+1; 0.5 is taken as the balance point, indicating that the penetration state at this time does not damage the skin, nor is it difficult to penetrate. When k f,t When k > 0.5, the puncture frequency needs to be increased to enhance the penetration effect. f,t When u1 is less than 0.5, the puncture frequency needs to be reduced to reduce damage to the skin. The adjustment amplitude is controlled by the gain coefficient. The larger the gain coefficient u1 is, the more sensitive the adjustment is, but oscillation may occur. The smaller the gain coefficient u1 is, the smoother the adjustment is, but response delay may occur. In actual situations, a larger gain coefficient is used for skin with a thicker stratum corneum, such as 0.5 to 1, and a smaller gain coefficient is used for skin with a thinner stratum corneum, such as 0.2 to 0.5.

[0110] The depth adjustment module is used to measure the tissue density of the target skin area before puncture, record it as the baseline density, monitor the tissue density and skin surface color of the target skin area in real time during the monitoring period, generate a depth adjustment index, and adjust the initial puncture depth in real time.

[0111] In this embodiment, the principle for generating the depth adjustment index to adjust the initial puncture depth in real time is as follows:

[0112] The formula for generating the depth-adjusted index is:

[0113]

[0114] Among them, k d,t represents the depth adjustment index at time t, ρ t represents the tissue density at time t, ρ0 represents the reference density, and H trepresents the skin surface hue at time t, H max Indicates the maximum hue value, H max =360°, w3 and w4 represent the weight coefficients of tissue density and hue respectively, w3+w4=1 and w3>w4;

[0115] The depth adjustment index reflects the adjustment ratio of the puncture depth under the influence of tissue density and skin surface color. Represents the relative rate of change of tissue density, when ρ t When ρ > 0, it indicates that the tissue density increases, which means that the microneedle enters a denser skin layer, such as the dermis. At this time, the puncture depth needs to be reduced to avoid excessive damage. t When ρ<0, it indicates that the tissue density is reduced, which means that the microneedles are in the loose stratum corneum or epidermis, and the penetration depth needs to be increased to ensure effective penetration. It reflects whether the hue after the change is close to red. The closer the value is to 1, the closer the hue after the change is to red. If it is closer to red than the reference hue, it may be caused by bleeding on the skin, and the puncture depth needs to be reduced. If the hue is close to the reference hue, then If the value is close to 0, it means that the skin condition is normal; the depth adjustment index is inversely proportional to the tissue density and inversely proportional to the hue after the change and the deviation of the red hue. The tissue density directly reflects the physical state of the skin during microneedle puncture, and the hue indirectly reflects the skin condition based on whether there is bleeding. Therefore, the tissue density has a higher weight, and w3=0.6 and w4=0.4 are taken.

[0116] The formula for adjusting the puncture depth is:

[0117] d t =d0×(1-u2×k d,t )

[0118] Among them, d t represents the puncture depth adjusted at time t, d0 represents the initial puncture depth, u2 represents the depth adjustment gain coefficient, and u1∈(0,0.5].

[0119] d t It reflects the adjusted puncture depth based on the reference puncture depth. d,t When k > 0, it means that the skin tissue density increases or the color is close to red, and the puncture depth needs to be reduced. d,t When it is less than 0, it means that the skin tissue density is relatively stable and the hue is close to the reference hue, so the puncture depth can be increased. The gain coefficient u2 reflects the sensitivity of the depth adjustment. For thick stratum corneum, a larger gain coefficient is used to quickly penetrate dense tissue. For thin stratum corneum, a smaller gain coefficient is used to avoid excessive penetration into the dermis.

[0120] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0121] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0122] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, and may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment as needed.

[0123] The above is only a specific implementation method of the present application, but the scope of protection of the present application is not limited thereto. Any technician familiar with this technical field can easily think of changes or replacements within the technical scope disclosed in this application, which should be covered by the scope of protection of the present application.

Claims

1. An intelligent collaborative robot system for microneedle introduction, characterized in that: Specifically include: The skin scanning module is used to scan the target skin area where microneedle puncture is required to obtain the thickness of the skin stratum corneum; An image processing module is configured to capture a surface image of the target skin area, convert the image into a grayscale image to generate a first recognition image, convert the image into the HSV color space to generate a second recognition image, extract edge pixels from the first recognition image based on Canny edge detection, generate skin surface roughness based on the number of edge pixels and the area enclosed by the edge pixels, obtain the hue of the pixels in the second recognition image, and generate the hue of the target skin area based on the hue of all pixels, which is recorded as the baseline hue; The model building module is used to build a deep learning network, using the known skin stratum corneum thickness and skin surface roughness as input and the microneedle puncture depth and puncture frequency as labels to train the puncture parameter prediction model; a parameter generation module, configured to input the stratum corneum thickness and skin surface roughness of the target skin area into a puncture parameter prediction model to generate initial puncture parameters, the initial puncture parameters including an initial puncture depth and an initial puncture frequency; A frequency adjustment module is used to measure the surface humidity and skin layer impedance of the target skin area before puncture, recording them as baseline humidity and baseline impedance. After the microneedle is introduced into the skin according to the initial puncture parameters, the module monitors the changes in humidity and skin layer impedance of the target skin area in real time during the monitoring period. Based on the changes in humidity and impedance, a frequency adjustment index is generated to adjust the initial puncture frequency in real time. The depth adjustment module is used to measure the tissue density of the target skin area before puncture, record it as the baseline density, monitor the tissue density and skin surface color of the target skin area in real time during the monitoring period, generate a depth adjustment index, and adjust the initial puncture depth in real time; The formula for generating the hue of the target skin area based on the hue of all pixels is: Among them, H total Indicates the hue of the target skin area, H i Indicates the hue of the i-th pixel, i represents the index of the pixel, n represents the number of pixels, and atan2[] represents the four-quadrant inverse tangent function; The principle behind generating the depth adjustment index to adjust the initial puncture depth in real time is: The formula for generating the depth-adjusted index is: Among them, k d,t represents the depth adjustment index at time t, ρ t represents the tissue density at time t, ρ0 represents the reference density, and H t represents the skin surface hue at time t, H max Indicates the maximum hue value, H max =360°, w3 and w4 represent the weight coefficients of tissue density and hue respectively, w3+w4=1 and w3>w4; The formula for adjusting the puncture depth is: d t =d0×(1-u2×k d,t ); Among them, d t represents the puncture depth adjusted at time t, d0 represents the initial puncture depth, u2 represents the depth adjustment gain coefficient, u2∈(0,0.5]; The principle behind generating the depth adjustment index to adjust the initial puncture depth in real time is: The formula for generating the depth-adjusted index is: Among them, k d,t represents the depth adjustment index at time t, ρ t represents the tissue density at time t, ρ0 represents the reference density, and H t represents the skin surface hue at time t, H max Indicates the maximum hue value, H max =360°, w3 and w4 represent the weight coefficients of tissue density and hue respectively, w3+w4=1 and w3>w4; The formula for adjusting the puncture depth is: d t =d0×(1-u2×k d,t ); Among them, d t represents the puncture depth adjusted at time t, d0 represents the initial puncture depth, u2 represents the depth adjustment gain coefficient, u2∈(0,0.5].

2. The intelligent collaborative robot system for microneedle introduction according to claim 1, characterized in that: The principle for generating skin surface roughness in the image processing module is: For each pixel in the first recognition image, convolve the pixel and its neighboring pixels with the horizontal and vertical templates of the Prewitt operator to generate the grayscale difference of the pixel in the horizontal and vertical directions. The formula is: Among them, P X represents the horizontal template of the Prewitt operator, P Y Represents the vertical template of the Prewitt operator, G x Represents the horizontal difference of the pixel, G y Represents the vertical difference of the pixel point, (x, y) represents the coordinates of the pixel point; The gradient amplitude of each pixel is generated based on the grayscale difference in the horizontal and vertical directions. The formula is: Among them, G(x,y) represents the gradient amplitude of the pixel point with coordinates (x,y), G x Represents the horizontal difference of the pixel, G y Indicates the vertical difference of the pixel; A preset edge threshold is set, and when the gradient amplitude of a pixel point is higher than the edge threshold, it is considered an edge pixel point; The number of edge pixels and the area of ​​the area enclosed by the outermost edge pixels are obtained based on all edge pixels to generate the skin surface roughness. The formula is: Among them, R represents the roughness of the skin surface, S represents the area enclosed by the outermost circle of edge pixels, and N represents the number of edge pixels.

3. The intelligent collaborative robot system for microneedle introduction according to claim 1, characterized in that: The principle by which the hue of the target skin area is generated in the image processing module is: The principle of converting an image to the HSV color space is: For any point in the image, its RGB color space is (R, G, B), and its HSV color space is (H, S, V). First, normalize the R, G, and B values: Among them, R0 represents the normalized red channel value, G0 represents the normalized green channel value, B0 represents the normalized blue channel value, R represents the red channel value, G represents the green channel value, and B represents the blue channel value; The formula for generating H, S, and V based on R0, G0, and B0 is: V = max(R0, G0, B0); Among them, H, S, and V represent hue, saturation, and brightness respectively.

4. The intelligent collaborative robot system for microneedle introduction according to claim 1, characterized in that: The principle by which the frequency adjustment module generates a frequency adjustment index to adjust the initial puncture frequency in real time is: The frequency adjustment index is generated based on the formula: Among them, k f,t Represents the frequency adjustment index at time t, M t Represents the humidity value at time t, t represents the index of the monitoring time, and t∈[0,T], T represents the length of the monitoring period, M0 represents the reference humidity, M max Represents the humidity safety threshold, Z t represents the skin layer impedance at time t, Z min represents the impedance safety threshold, Z0 represents the reference impedance, w1 and w2 represent the weight coefficients of humidity and impedance respectively, w1+w2=1 and w1>w2; The formula for adjusting the puncture frequency is: f t =f0×[1+u1×(k f,t -0.5)]; Among them, f t represents the puncture frequency adjusted at time t, f0 represents the initial puncture frequency, u1 represents the frequency adjustment gain coefficient, u1∈(0,1].

Images