Puerpera postpartum state intelligent planning radio frequency assisted rehabilitation method

Abstract

The invention relates to the technical field of postpartum rehabilitation, in particular to a postpartum state intelligent planning radio frequency assisted rehabilitation method based on a puerpera, which comprises the following steps: acquiring postpartum scar image data of the puerpera, processing the image data, and calculating the area, perimeter and pigmentation degree of the scar according to the processed image data. Calculating the hardness and elasticity data of the scar; integrating the scar state data and the physiological data to establish puerpera health record data, and calculating the correlation between scar hardness and age and weight through a Pearson coefficient; the scar severity index is divided into three grades, and accordingly, the energy output of the radio frequency is accurately regulated and controlled. The high-definition camera and the palpation sensor are utilized, an advanced image analysis algorithm and mechanical property measurement are combined, multi-dimensional data of scars can be accurately obtained, and rehabilitation requirements and difficulty levels can be accurately evaluated.

Description

Technical Field

[0001] The present invention relates to the technical field of postpartum rehabilitation, and in particular to a radio frequency assisted rehabilitation method based on intelligent planning of the postpartum state of a parturient. Background Art

[0002] With the continuous advancement of modern medical technology and the improvement of people's living standards, more and more women have begun to pay attention to the importance of postpartum rehabilitation. As an emerging medical technology, radio frequency technology has been widely used in the medical field in recent years. Radio frequency technology acts on human tissues through high-frequency electromagnetic waves to produce thermal and non-thermal effects, thereby achieving the purpose of treating diseases. In the field of postpartum rehabilitation, radio frequency technology can be used to promote blood circulation, relieve muscle tension, relieve pain and other symptoms, and has a significant effect on improving the physical condition of mothers. Postpartum rehabilitation not only involves the physical recovery of mothers, but also includes mental health and social adaptability. The presence of scars may have an adverse effect on the mental health of mothers. Traditional postpartum scar rehabilitation methods mainly include physical therapy, drug therapy, etc., but these methods often have problems such as insignificant effects, large side effects, and long rehabilitation cycles. Summary of the invention

[0003] In view of the technical problems existing in the prior art, the present invention provides a radio frequency assisted rehabilitation method for intelligent planning based on the postpartum state of the parturient.

[0004] The technical solution of the present invention to solve the above technical problems is as follows: a method for intelligently planning radio frequency-assisted rehabilitation based on the postpartum state of a parturient, comprising the following steps:

[0005] S101, collecting postpartum scar image data of the parturient, processing the image data, and calculating the area, perimeter, pigmentation degree, hardness and elasticity data of the scar based on the processed image data;

[0006] S102, integrating scar status data and physiological data to establish maternal health record data, and calculating the correlation between scar hardness and age and weight through the Pearson coefficient;

[0007] S103. Scars are divided into three levels according to their severity index, and the energy output of radio frequency is precisely controlled accordingly.

[0008] In a preferred embodiment, in S101, a high-definition camera is used to collect images of postpartum scars, and the collected images are processed using an image analysis algorithm to obtain scar status data, including scar area, perimeter and pigmentation parameters. The hardness and elasticity of the scar are measured in combination with a palpation sensor, and the basic physiological information of the parturient is obtained through an electronic questionnaire, including height, weight and age information. A unique identification code is established for each parturient, and all data are stored in the health record database of the parturient. The scar area is separated from the background by a threshold segmentation algorithm. The original pixel value of a certain pixel in the image is set to I(x, y), and a threshold T is selected to binarize the image pixel value. After threshold segmentation and binarization, the specific calculation formula of the new pixel value B(x, y) is as follows:

[0009]

[0010] The pixel value greater than T is the scar area, and the pixel value less than T is the normal skin area. Based on the binarized image data, the number of pixels in the scar area is calculated. All the pixels in the binarized image are traversed to count the number of pixels in the scar area n p , the specific calculation formula is as follows:

[0011]

[0012] For each pixel (x, y) in the image, when its binary pixel value B(x, y) is a scar area, add 1 when counting. After traversing the entire image, the cumulative sum is the number of pixels n contained in the scar area. p , perform scale calibration on the collected image data. When collecting images, collect a square calibration plate at the same time, measure the pixel side length of the square calibration plate in the image, and set the side length used when collecting images as L c The square calibration plate is 1 cm in diameter, and the pixel side length of the calibration plate in the image is measured as n. c Pixels, since the area of ​​a square is equal to the square of its side length, the actual area of ​​the calibration plate is Its pixel area in the image The specific calculation formula of the ratio coefficient k between the actual area and the pixel area is as follows:

[0013]

[0014] According to the number of pixels in the scar area n p And the proportional coefficient k, the specific calculation formula for calculating the actual area of ​​the scar is as follows:

[0015]

[0016] Among them, S represents the actual scar area, which provides a data basis for the subsequent postpartum scar status assessment based on the final actual scar area;

[0017] In the binarized image, the edge detection algorithm is used to extract the edge contour of the scar area. By calculating the image gradient, the pixel points with amplitude values ​​greater than the threshold are found as edge points, and then these edge points are connected to form a continuous contour curve to calculate the perimeter of the scar. The specific steps are as follows:

[0018] S1. Smooth the image by Gaussian filtering. Suppose the original binary image is I(x, y), then the kernel function G(x, y, σ) of Gaussian filtering is defined as:

[0019]

[0020] Among them, x and y represent the horizontal and vertical coordinates of the image, σ represents the standard deviation of the Gaussian kernel, which determines the degree of smoothing, and e represents the base of the natural logarithm function, which is used to control the decay speed and shape of the function. The filtered image I smooth (x,y) is obtained by convolution with Gaussian kernel function:

[0021]

[0022] Among them, I smooth (x, y) represents the pixel value of the image at the coordinate (x, y) after Gaussian filtering, k represents the parameter related to the size of the Gaussian kernel, so that the convolution kernel can cover the surrounding pixel area centered on the current pixel, i and j represent the coordinate offset, i represents the offset relative to the current pixel on the horizontal coordinate of the image, and j represents the offset relative to the current pixel on the vertical coordinate of the image;

[0023] S2, calculate the filtered image I through the sobel operator smooth (x,y) in the horizontal direction G x (x,y) and the vertical direction G y The gradient of (x, y) is obtained by convolution operation, and the gradient values ​​in the horizontal and vertical directions are obtained. The horizontal gradient G x The specific calculation formula for (x,y) is as follows:

[0024]

[0025] Among them, S x (i, j) represents the gradient value after convolution by the Sobel operator in the horizontal direction, and the vertical gradient G y The specific calculation formula for (x,y) is as follows:

[0026]

[0027] Among them, S y (i, j) represents the gradient value after convolution by the Sobel operator in the vertical direction. The specific calculation formula for calculating the gradient amplitude and gradient direction of each pixel is as follows:

[0028]

[0029] Among them, G(x,y) represents the gradient amplitude of each pixel, which is used to represent the intensity of the grayscale change of the image at the pixel, and θ(x,y) represents the gradient direction of each pixel;

[0030] S3. Along the gradient direction θ(x, y), compare the gradient amplitude G(x, y) of each pixel with the gradient amplitude of its adjacent pixel in the gradient direction. If the gradient amplitude of the pixel is not the local maximum, mark it as a non-edge point. In this way, the edge is refined and redundant edge responses are removed.

[0031] S4, set high threshold T h and high threshold T l , for gradient magnitude G(x,y) greater than T h The pixel point is determined as an edge point. For the pixel point with a gradient amplitude less than T l , it is determined that it is not an edge point, and for the pixel point with a gradient amplitude between T h and T l If the pixel points between are connected to the determined edge points, they are marked as edge points;

[0032] S5, the ratio coefficient k between the actual area and the pixel area calculated by the calibration plate, which establishes the association between the image pixel and the actual physical size. Assume that in the image coordinate system, the actual length corresponding to each pixel in the horizontal and vertical coordinate directions is l x and l y For the square calibration plate, we can get

[0033] S6. The obtained scar contour pixel coordinates are set to be (x0, y0), (x1, y1), ..., (x m-1 ,y m-1 ), there are a total of m pixels forming a closed contour curve, and the last pixel is considered to be adjacent to the first pixel to form a closed perimeter calculation path;

[0034] S7, for two adjacent contour pixels (x i ,y i ) and (x i+1 ,y i+1 ), first calculate their pixel distance in the horizontal and vertical directions:

[0035] Pixel distance in the horizontal direction: Δx i =x i+1 -x i ;

[0036] Pixel distance in the ordinate direction: Δy i =y i+1 -y i

[0037] Among them, i represents the serial number of the contour pixel point, Δx i Represents two adjacent pixels x i and x i+1 Pixel distance in the horizontal direction, Δy i Represents two adjacent pixel points y i and i+1 The pixel distance in the ordinate direction is converted into the actual physical distance according to the actual length l corresponding to each pixel. x and l y , calculate the actual distance d between two adjacent points i :

[0038]

[0039] Among them, l x Indicates the actual physical length of each pixel in the horizontal direction, l y Indicates the actual physical length of each pixel in the ordinate direction;

[0040] S8. The actual perimeter of the scar is the cumulative sum of the actual distances between all adjacent pixels. The specific calculation formula is as follows:

[0041]

[0042] Where C represents the actual circumference of the scar;

[0043] The scar pigmentation degree is calculated by converting the collected color image into the LAB color space, where the L channel represents brightness, the A channel represents the color components from red to green, and the B channel represents the color components from yellow to blue. Multiple sampling points are selected in the scar area and the surrounding normal skin area, and the average value of each sampling point in the A and B channels is calculated. and in, Indicates scar area, Represents the normal skin area, calculates the pigmentation index P, and uses the Euclidean distance formula:

[0044]

[0045] A large value of P indicates a severe degree of pigmentation;

[0046] The hardness and elasticity of the scar are evaluated by placing the palpation sensor at the center of the scar surface. The hardness is evaluated by calculating the initial slope of the pressure-deformation curve. When the pressure is small, a segment of the curve is selected and the slope k of the segment is calculated. h , then scar hardness H = k h The elasticity is evaluated by calculating the hysteresis loop area of ​​the pressure-deformation curve during loading and unloading. max , slowly unload the pressure to 0, obtain the complete loading-unloading curve, and calculate the hysteresis loop area A enclosed by the curve e , then the specific calculation formula of scar elasticity E is as follows:

[0047]

[0048] Where, ΔL max Indicates the maximum deformation during loading.

[0049] In a preferred embodiment, in S102, the scar status data and physiological data are integrated to establish a maternal personal health record database. The correlation between the scar status and the physiological parameters is analyzed by big data analysis technology to obtain scar status data including scar area S, circumference C, elasticity H and pigmentation degree P, as well as physiological data including maternal age A, weight W and height Hgt. The Pearson coefficient is used to calculate the correlation analysis between scar hardness and maternal age and weight. Assume that the scar hardness data sequence is H=[h1,h2,...,h n ], the maternal age data sequence is A = [a1, a2, ..., a n ], the weight sequence is W = [w1,w2,...,w n ], where n represents the number of data points, and the Pearson coefficient r of scar hardness and age HA The specific calculation formula is as follows:

[0050]

[0051] in, represents the average value of scar hardness data, represents the average of the average age data, h i represents the scar hardness data of the i-th sample, a i represents the age data of the i-th sample, the Pearson correlation coefficient r between scar hardness and weight HW The specific calculation formula is as follows:

[0052]

[0053] in, Indicates the average value of weight data, w i represents the weight data of the i-th sample. The absolute value of the correlation coefficient is used to determine the strength of the correlation. 1 indicates a strong positive correlation, -1 indicates a strong negative correlation, and 0 indicates a weak correlation. A scar severity index evaluation system is established, which comprehensively considers scar area, elasticity, and pigmentation degree factors, and adopts a weighted summation method. The specific calculation formula is as follows:

[0054] SSI=αS+βH+γ(1 / P)

[0055] Among them, α, β, and γ represent weight coefficients. The scar severity index is used to evaluate the severity of the scar of the parturient, and a rehabilitation plan is formulated based on the severity.

[0056] In a preferred embodiment, in S103, scar severity is divided into three levels based on the scar severity index, and the specific determination formula is as follows:

[0057]

[0058] Among them, G=1 represents mild, G=2 represents moderate, and G=3 represents severe. Based on the scar severity index, the output intensity, pulse frequency and treatment time of the radio frequency energy are precisely controlled. During the treatment, the working status of the radio frequency equipment is monitored in real time to ensure the safe and stable operation of the equipment. At the same time, the body reactions of the mother during the treatment, including skin temperature and pain perception, are monitored. Once any abnormality is found, the treatment is stopped immediately and corresponding measures are taken.

[0059] The beneficial effects of the present invention are as follows: the present invention utilizes high-definition cameras and palpation sensors, combined with advanced image analysis algorithms and mechanical property measurements, to accurately obtain multi-dimensional scar data, and then integrates it with the comprehensive physiological data of the parturient. Through in-depth analysis using big data and machine learning algorithms, it can accurately assess rehabilitation needs and difficulty levels, and develop highly personalized rehabilitation plans that cater to individual differences in everything from radiofrequency treatment to training, diet, and psychological support, significantly improving rehabilitation effects and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0061] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0062] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0063] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0064] like Figure 1 This embodiment provides: a method for intelligently planning radio frequency-assisted rehabilitation based on the postpartum state of a parturient, the specific steps of which are as follows:

[0065] S101, collecting postpartum scar image data of the parturient, processing the image data, and calculating the area, perimeter, pigmentation degree, hardness and elasticity data of the scar based on the processed image data;

[0066] Furthermore, the postpartum scar is imaged by a high-definition camera, and the image analysis algorithm is used to process the image to obtain scar status data, including scar area, perimeter and pigmentation parameters. The hardness and elasticity of the scar are measured by palpation sensors. The basic physiological information of the parturient, including height, weight and age, is obtained through an electronic questionnaire. A unique identification code is established for each parturient, and all data is stored in the parturient's health record database. The scar area is separated from the background by a threshold segmentation algorithm. The original pixel value of a certain pixel in the image is set to I(x, y), and a threshold T is selected to binarize the image pixel value. After threshold segmentation and binarization, the specific calculation formula of the new pixel value B(x, y) is as follows:

[0067]

[0068] The pixel value greater than T is the scar area, and the pixel value less than T is the normal skin area. Based on the binarized image data, the number of pixels in the scar area is calculated. All the pixels in the binarized image are traversed to count the number of pixels in the scar area n p , the specific calculation formula is as follows:

[0069]

[0070] For each pixel (x, y) in the image, when its binary pixel value B(x, y) is a scar area, add 1 when counting. After traversing the entire image, the cumulative sum is the number of pixels n contained in the scar area. p , perform scale calibration on the collected image data. When collecting images, collect a square calibration plate at the same time, measure the pixel side length of the square calibration plate in the image, and set the side length used when collecting images as L c The square calibration plate is 1 cm in diameter, and the pixel side length of the calibration plate in the image is measured as n. c Pixels, since the area of ​​a square is equal to the square of its side length, the actual area of ​​the calibration plate is Its pixel area in the image The specific calculation formula of the ratio coefficient k between the actual area and the pixel area is as follows:

[0071]

[0072] According to the number of pixels in the scar area n p And the proportional coefficient k, the specific calculation formula for calculating the actual area of ​​the scar is as follows:

[0073]

[0074] Among them, S represents the actual scar area, which provides a data basis for the subsequent postpartum scar status assessment based on the final actual scar area;

[0075] In the binarized image, the edge detection algorithm is used to extract the edge contour of the scar area. By calculating the image gradient, the pixel points with amplitude values ​​greater than the threshold are found as edge points, and then these edge points are connected to form a continuous contour curve to calculate the perimeter of the scar. The specific steps are as follows:

[0076] S1. Smooth the image by Gaussian filtering. Suppose the original binary image is I(x, y), then the kernel function G(x, y, σ) of Gaussian filtering is defined as:

[0077]

[0078] Among them, x and y represent the horizontal and vertical coordinates of the image, σ represents the standard deviation of the Gaussian kernel, which determines the degree of smoothing, and e represents the base of the natural logarithm function, which is used to control the decay speed and shape of the function. The filtered image I smooth (x,y) is obtained by convolution with Gaussian kernel function:

[0079]

[0080] Among them, I smooth (x, y) represents the pixel value of the image at the coordinate (x, y) after Gaussian filtering, k represents the parameter related to the size of the Gaussian kernel, so that the convolution kernel can cover the surrounding pixel area centered on the current pixel, i and j represent the coordinate offset, i represents the offset relative to the current pixel on the horizontal coordinate of the image, and j represents the offset relative to the current pixel on the vertical coordinate of the image;

[0081] S2, calculate the filtered image I through the sobel operator smooth (x,y) in the horizontal direction G x (x,y) and the vertical direction G y The gradient of (x, y) is obtained by convolution operation, and the gradient values ​​in the horizontal and vertical directions are obtained. The horizontal gradient G x The specific calculation formula for (x,y) is as follows:

[0082]

[0083] Among them, S x (i, j) represents the gradient value after convolution by the Sobel operator in the horizontal direction, and the vertical gradient G y The specific calculation formula for (x,y) is as follows:

[0084]

[0085] Among them, S y (i, j) represents the gradient value after convolution by the Sobel operator in the vertical direction. The specific calculation formula for calculating the gradient amplitude and gradient direction of each pixel is as follows:

[0086]

[0087] Among them, G(x,y) represents the gradient amplitude of each pixel, which is used to represent the intensity of the grayscale change of the image at the pixel, and θ(x,y) represents the gradient direction of each pixel;

[0088] S3. Along the gradient direction θ(x, y), compare the gradient amplitude G(x, y) of each pixel with the gradient amplitude of its adjacent pixel in the gradient direction. If the gradient amplitude of the pixel is not the local maximum, mark it as a non-edge point. In this way, the edge is refined and redundant edge responses are removed.

[0089] S4, set high threshold T h and high threshold T l , for gradient magnitude G(x,y) greater than T h The pixel point is determined as an edge point. For the pixel point with a gradient amplitude less than T l , it is determined that it is not an edge point, and for the pixel point with a gradient amplitude between T h and T l If the pixel points between are connected to the determined edge points, they are marked as edge points;

[0090] S5, the ratio coefficient k between the actual area and the pixel area calculated by the calibration plate, which establishes the association between the image pixel and the actual physical size. Assume that in the image coordinate system, the actual length corresponding to each pixel in the horizontal and vertical coordinate directions is l x and l y For the square calibration plate, we can get

[0091] S6. The obtained scar contour pixel coordinates are set to be (x0, y0), (x1, y1), ..., (x m-1 ,y m-1 ), there are a total of m pixels forming a closed contour curve, and the last pixel is considered to be adjacent to the first pixel to form a closed perimeter calculation path;

[0092] S7, for two adjacent contour pixels (x i ,y i ) and (x i+1 ,y i+1 ), first calculate their pixel distance in the horizontal and vertical directions:

[0093] Pixel distance in the horizontal direction: Δx i =x i+1 -x i ;

[0094] Pixel distance in the ordinate direction: Δy i =y i+1 -y i

[0095] Among them, i represents the serial number of the contour pixel point, Δx i Represents two adjacent pixels x i and x i+1 Pixel distance in the horizontal direction, Δy i Represents two adjacent pixel points y i and i+1 The pixel distance in the ordinate direction is converted into the actual physical distance according to the actual length l corresponding to each pixel. x and l y , calculate the actual distance d between two adjacent points i :

[0096]

[0097] Among them, l x Indicates the actual physical length of each pixel in the horizontal direction, l y Indicates the actual physical length of each pixel in the ordinate direction;

[0098] S8. The actual perimeter of the scar is the cumulative sum of the actual distances between all adjacent pixels. The specific calculation formula is as follows:

[0099]

[0100] Where C represents the actual circumference of the scar;

[0101] The scar pigmentation degree is calculated by converting the collected color image into the LAB color space, where the L channel represents brightness, the A channel represents the color components from red to green, and the B channel represents the color components from yellow to blue. Multiple sampling points are selected in the scar area and the surrounding normal skin area, and the average value of each sampling point in the A and B channels is calculated. and in, Indicates scar area, Represents the normal skin area, calculates the pigmentation index P, and uses the Euclidean distance formula:

[0102]

[0103] A large value of P indicates a severe degree of pigmentation;

[0104] The hardness and elasticity of the scar are evaluated by placing the palpation sensor at the center of the scar surface. The hardness is evaluated by calculating the initial slope of the pressure-deformation curve. When the pressure is small, a segment of the curve is selected and the slope k of the segment is calculated. h , then scar hardness H = k h The elasticity is evaluated by calculating the hysteresis loop area of ​​the pressure-deformation curve during loading and unloading. max , slowly unload the pressure to 0, obtain the complete loading-unloading curve, and calculate the hysteresis loop area A enclosed by the curve e , then the specific calculation formula of scar elasticity E is as follows:

[0105]

[0106] Among them, ΔL max Indicates the maximum deformation during loading.

[0107] S102, integrating scar status data and physiological data to establish maternal health record data, and calculating the correlation between scar hardness and age and weight through the Pearson coefficient;

[0108] Furthermore, the scar status data and physiological data are integrated to establish a maternal personal health record database. The correlation between scar status and physiological parameters is analyzed through big data analysis technology. Scar status data including scar area S, circumference C, elasticity H and pigmentation degree P, as well as physiological data including maternal age A, weight W and height Hgt are obtained. The Pearson coefficient is used to calculate the correlation analysis between scar hardness and maternal age and weight. Suppose the scar hardness data sequence is H = [h1,h2,...,h n ], the maternal age data sequence is A = [a1, a2, ..., a n ], the weight sequence is W = [w1,w2,...,w n ], where n represents the number of data points, and the Pearson coefficient r of scar hardness and age HA The specific calculation formula is as follows:

[0109]

[0110] in, represents the average value of scar hardness data, represents the average of the average age data, h i represents the scar hardness data of the i-th sample, a i represents the age data of the i-th sample, the Pearson correlation coefficient r between scar hardness and weightHW The specific calculation formula is as follows:

[0111]

[0112] in, Indicates the average value of weight data, w i represents the weight data of the i-th sample. The absolute value of the correlation coefficient is used to determine the strength of the correlation. 1 indicates a strong positive correlation, -1 indicates a strong negative correlation, and 0 indicates a weak correlation. A scar severity index evaluation system is established, which comprehensively considers scar area, elasticity, and pigmentation degree factors, and adopts a weighted summation method. The specific calculation formula is as follows:

[0113] SSI=αS+βH+γ(1 / P)

[0114] Among them, α, β, and γ represent weight coefficients. The scar severity index is used to evaluate the severity of the scar of the parturient, and a rehabilitation plan is formulated based on the severity.

[0115] S103, scars are divided into three levels according to the severity index, and the energy output of radio frequency is precisely controlled accordingly;

[0116] Furthermore, based on the scar severity index, the scar severity is divided into three levels, and the specific determination formula is as follows:

[0117]

[0118] Among them, G=1 represents mild, G=2 represents moderate, and G=3 represents severe. Based on the scar severity index, the output intensity, pulse frequency and treatment time of the radio frequency energy are precisely controlled. During the treatment, the working status of the radio frequency equipment is monitored in real time to ensure the safe and stable operation of the equipment. At the same time, the body reactions of the mother during the treatment, including skin temperature and pain perception, are monitored. Once any abnormality is found, the treatment is stopped immediately and corresponding measures are taken.

[0119] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0120] 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.

[0121] 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 computer, or other programmable data processing device to generate 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.

[0122] 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.

[0123] 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.

[0124] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0125] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A radiofrequency-assisted rehabilitation method based on intelligent planning of the postpartum state of a parturient, characterized in that: The following steps are involved: S101, collecting postpartum scar image data of the parturient, processing the image data, and calculating the area, perimeter, pigmentation degree, hardness and elasticity data of the scar based on the processed image data; S102, integrating scar status data and physiological data to establish maternal health record data, and calculating the correlation between scar hardness and age and weight through the Pearson coefficient; S103. Scars are divided into three levels according to their severity index, and the energy output of radio frequency is precisely controlled accordingly.

2. According to claim 1, a radio frequency assisted rehabilitation method based on intelligent planning of the postpartum state of the parturient is characterized in that: In S101, a high-definition camera is used to collect images of postpartum scars, and the collected images are processed using an image analysis algorithm to obtain scar status data, including scar area, perimeter and pigmentation parameters. The hardness and elasticity of the scar are measured in combination with a palpation sensor, and basic physiological information of the parturient is obtained through an electronic questionnaire, including height, weight and age information. A unique identification code is established for each parturient, and all data is stored in the health record database of the parturient. The scar area is separated from the background using a threshold segmentation algorithm. The original pixel value of a certain pixel in the image is set to I(x, y), and a threshold T is selected to binarize the image pixel value. After threshold segmentation and binarization, the specific calculation formula of the new pixel value B(x, y) is as follows: The pixel value greater than T is the scar area, and the pixel value less than T is the normal skin area. Based on the binarized image data, the number of pixels in the scar area is calculated. All the pixels in the binarized image are traversed to count the number of pixels in the scar area n p , the specific calculation formula is as follows: For each pixel (x, y) in the image, when its binary pixel value B(x, y) is a scar area, add 1 when counting. After traversing the entire image, the cumulative sum is the number of pixels n contained in the scar area. p , perform scale calibration on the collected image data. When collecting images, collect a square calibration plate at the same time, measure the pixel side length of the square calibration plate in the image, and set the side length used when collecting images as L c The square calibration plate is 1 cm in diameter, and the pixel side length of the calibration plate in the image is measured as n. c Pixels, since the area of ​​a square is equal to the square of its side length, the actual area of ​​the calibration plate is Its pixel area in the image The specific calculation formula of the ratio coefficient k between the actual area and the pixel area is as follows: According to the number of pixels in the scar area n p And the proportional coefficient k, the specific calculation formula for calculating the actual area of ​​the scar is as follows: Among them, S represents the actual scar area. The final actual scar area provides a data basis for the subsequent postpartum scar status assessment.

3. The method of intelligently planning radiofrequency-assisted rehabilitation based on the postpartum state of a parturient according to claim 2, characterized in that: The scar perimeter is calculated by using an edge detection algorithm to extract the edge contour of the scar area in the binarized image, calculating the image gradient, finding pixels with amplitude values ​​greater than a threshold as edge points, and then connecting these edge points to form a continuous contour curve to calculate the scar perimeter. The specific steps are as follows: S1. Smooth the image by Gaussian filtering. Suppose the original binary image is I(x, y), then the kernel function G(x, y, σ) of Gaussian filtering is defined as: Among them, x and y represent the horizontal and vertical coordinates of the image, σ represents the standard deviation of the Gaussian kernel, which determines the degree of smoothing, and e represents the base of the natural logarithm function, which is used to control the decay speed and shape of the function. The filtered image I smooth (x,y) is obtained by convolution with Gaussian kernel function: Among them, I smooth (x, y) represents the pixel value of the image at the coordinate (x, y) after Gaussian filtering, k represents the parameter related to the size of the Gaussian kernel, so that the convolution kernel can cover the surrounding pixel area centered on the current pixel, i and j represent the coordinate offset, i represents the offset relative to the current pixel on the horizontal coordinate of the image, and j represents the offset relative to the current pixel on the vertical coordinate of the image; S2, calculate the filtered image I through the sobel operator smooth (x,y) in the horizontal direction G x (x,y) and the vertical direction G y The gradient of (x, y) is obtained by convolution operation, and the gradient values ​​in the horizontal and vertical directions are obtained. The horizontal gradient G x The specific calculation formula for (x,y) is as follows: Among them, S x (i, j) represents the gradient value after convolution by the Sobel operator in the horizontal direction, and the vertical gradient G y The specific calculation formula for (x,y) is as follows: Among them, S y (i, j) represents the gradient value after convolution by the Sobel operator in the vertical direction. The specific calculation formula for calculating the gradient amplitude and gradient direction of each pixel is as follows: Among them, G(x,y) represents the gradient amplitude of each pixel, which is used to represent the intensity of the grayscale change of the image at the pixel, and θ(x,y) represents the gradient direction of each pixel; S3. Along the gradient direction θ(x, y), compare the gradient amplitude G(x, y) of each pixel with the gradient amplitude of its adjacent pixel in the gradient direction. If the gradient amplitude of the pixel is not the local maximum, mark it as a non-edge point. In this way, the edge is refined and redundant edge responses are removed. S4, set high threshold T h and high threshold T l , for gradient magnitude G(x,y) greater than T h The pixel point is determined as an edge point. For the pixel point with a gradient amplitude less than T l , it is determined that it is not an edge point, and for the pixel point with a gradient amplitude between T h and T l If the pixel points between are connected to the determined edge points, they are marked as edge points; S5, the ratio coefficient k between the actual area and the pixel area calculated by the calibration plate, which establishes the association between the image pixel and the actual physical size. Assume that in the image coordinate system, the actual length corresponding to each pixel in the horizontal and vertical coordinate directions is l x and l y , for the square calibration plate, we can get S6. The obtained scar contour pixel coordinates are set to be (x0, y0), (x1, y1), ..., (x m-1 ,y m-1 ), there are a total of m pixels forming a closed contour curve, and the last pixel is considered to be adjacent to the first pixel to form a closed perimeter calculation path; S7, for two adjacent contour pixels (x i ,y i ) and (x i+1 ,y i+1 ), first calculate their pixel distance in the horizontal and vertical directions: Pixel distance in the horizontal direction: Δx i =x i+1 -x i ; Pixel distance in the ordinate direction: Δy i =y i+1 -y i Among them, i represents the serial number of the contour pixel point, Δx i Represents two adjacent pixels x i and x i+1 Pixel distance in the horizontal direction, Δy i Represents two adjacent pixel points y i and i+1 The pixel distance in the ordinate direction is converted into the actual physical distance according to the actual length l corresponding to each pixel. x and l y , calculate the actual distance d between two adjacent points i : Among them, l x Indicates the actual physical length of each pixel in the horizontal direction, l y Indicates the actual physical length of each pixel in the ordinate direction; S8. The actual perimeter of the scar is the cumulative sum of the actual distances between all adjacent pixels. The specific calculation formula is as follows: Where C represents the actual circumference of the scar.

4. The method of intelligently planning radio frequency-assisted rehabilitation based on the postpartum state of a parturient according to claim 2, characterized in that: The pigmentation degree is calculated by converting the collected color image into the LAB color space, where the L channel represents brightness, the A channel represents the color components from red to green, and the B channel represents the color components from yellow to blue. Multiple sampling points are selected in the scar area and the surrounding normal skin area, and the average value of each sampling point in the A and B channels is calculated. and in, Indicates scar area, Represents the normal skin area, calculates the pigmentation index P, and uses the Euclidean distance formula: A large P value indicates a severe degree of pigmentation.

5. The method of intelligently planning radiofrequency-assisted rehabilitation based on the postpartum state of a parturient according to claim 2, characterized in that: The hardness and elasticity of the scar are calculated by placing the palpation sensor at the center of the scar surface. The hardness is evaluated by calculating the initial slope of the pressure-deformation curve. When the pressure is small, a segment of the curve is selected and the slope k of the segment is calculated. h , then scar hardness H = k h The elasticity is evaluated by calculating the hysteresis loop area of ​​the pressure-deformation curve during loading and unloading. max , slowly unload the pressure to 0, obtain the complete loading-unloading curve, and calculate the hysteresis loop area A enclosed by the curve e , then the specific calculation formula of scar elasticity E is as follows: Where, ΔL max Indicates the maximum deformation during loading.

6. The method of intelligently planning radio frequency-assisted rehabilitation based on the postpartum state of a parturient according to claim 1, characterized in that: In S102, the scar status data and physiological data are integrated to establish a maternal health record database. The correlation between the scar status and the physiological parameters is analyzed by big data analysis technology to obtain scar status data including scar area S, circumference C, elasticity H and pigmentation degree P, as well as physiological data including maternal age A, weight W and height Hgt. The Pearson coefficient is used to calculate the correlation analysis between scar hardness and maternal age and weight. Assume that the scar hardness data sequence is H=[h1,h2,...,h n ], the maternal age data sequence is A = [a1, a2, ..., a n ], the weight sequence is W = [w1,w2,...,w n ], where n represents the number of data points, and the Pearson coefficient r of scar hardness and age HA The specific calculation formula is as follows: in, represents the average value of scar hardness data, represents the average of the average age data, h i represents the scar hardness data of the i-th sample, a i represents the age data of the i-th sample, the Pearson correlation coefficient r between scar hardness and weight HW The specific calculation formula is as follows: in, Indicates the average value of weight data, w i represents the weight data of the i-th sample. The absolute value of the correlation coefficient is used to determine the strength of the correlation. 1 indicates a strong positive correlation, -1 indicates a strong negative correlation, and 0 indicates a weak correlation. A scar severity index evaluation system is established, which comprehensively considers scar area, elasticity, and pigmentation degree factors, and adopts a weighted summation method. The specific calculation formula is as follows: SSI=αS+βH+γ(1 / P) Among them, α, β, and γ represent weight coefficients. The scar severity index is used to evaluate the severity of the mother's scar, and a rehabilitation plan is formulated based on the severity of the scar.

7. The method of intelligently planning radiofrequency-assisted rehabilitation based on the postpartum state of a parturient according to claim 1, characterized in that: In S103, based on the scar severity index, the scar severity is divided into three levels, and the specific determination formula is as follows: Among them, G=1 represents mild, G=2 represents moderate, and G=3 represents severe. Based on the scar severity index, the output intensity, pulse frequency and treatment time of the radio frequency energy are precisely controlled. During the treatment, the working status of the radio frequency equipment is monitored in real time to ensure the safe and stable operation of the equipment. At the same time, the body reactions of the mother during the treatment, including skin temperature and pain perception, are monitored. Once any abnormality is found, the treatment is stopped immediately and corresponding measures are taken.

Images