Acupuncture point assisted positioning method for pulmonary treatment

Abstract

The present application relates to the technical field of lung-related acupoint positioning, and particularly relates to a method for acupoint auxiliary positioning of acupuncture for lung treatment. Based on a human back image, first, the relative distance of each point is calculated through the distance distribution of the pixel point and the shooting point, and then the curvature value is derived. Subsequently, edge detection is performed, the angle information of the edge pixel points is extracted, all edge points are classified according to the angle difference and the spatial distribution characteristics, and the edge angle difference of all edge and pixel points is obtained. The edges with mixed distribution of positive and negative curvature values are screened as the target to be analyzed, and the bone quality index is calculated in combination with the internal angle difference fluctuation characteristics and the curvature distribution mode. According to the bone quality index strength and the positive and negative characteristics of the curvature, the edges are accurately divided into the spine region and the scapula region. The present application can accurately identify the spine region and the scapula region on the human back, thereby facilitating relevant personnel to accurately identify acupoints.

Description

Technical Field

[0001] This invention relates to the technical field of acupoint location related to the lungs, and specifically to an auxiliary acupoint location method for lung treatment. Background Technology

[0002] Acupuncture, as an important therapy in Traditional Chinese Medicine (TCM), possesses multiple advantages. Its core value lies in stimulating acupoints on the body surface to activate the body's self-healing abilities, achieving "treating internal diseases from the outside." Positioned as a "green therapy," acupuncture boasts three major advantages: definite efficacy, safety, affordability, and wide applicability. It is particularly adept at addressing pain and functional disorders caused by modern lifestyles. Its essence lies in activating the body's self-healing potential and achieving a dynamic balance of physiological functions. To further ensure the accuracy of acupuncture points, combining acupuncture with image-based assistance can consistently improve treatment efficiency.

[0003] In practice, when using acupuncture to treat the lungs, practitioners often manipulate acupoints such as Feishu (BL13) and Gaohuang (BL43) on the back, Lieque (LU7) and Chize (LU5) on the arm, and Zhongfu (LU1) and Tiantu (CV22) on the chest and abdomen. To accurately locate these acupoints, current techniques frequently employ bone measurement, using the scapula and vertebrae for auxiliary positioning. Therefore, regional identification of the spine and scapula is necessary. However, due to the relatively uniform features of the back, traditional images of the human back cannot accurately represent the patient's back characteristics. Furthermore, the regional features of the spine and scapula are too similar to other back features, making it difficult to distinguish these areas and thus hindering accurate acupoint identification. Summary of the Invention

[0004] To address the technical problem that traditional human back images fail to accurately represent the patient's back features due to their relatively simple characteristics, and that the spine and scapula regions are too similar to other back features, making it difficult to identify these areas and thus hindering accurate acupoint identification, this invention aims to provide an auxiliary acupoint location method for lung treatment. The specific technical solution is as follows: An auxiliary acupoint location method for lung treatment, comprising: acquiring a human back image; obtaining the relative distance of each pixel based on the distance distribution characteristics between different pixels in the human back image and the shooting point; obtaining the curvature of each pixel based on the relative distance; and performing edge detection on each pixel to obtain... The edge angle of each edge pixel; based on the edge angle difference and distribution characteristics between each edge pixel and its surrounding edge pixels, all edge pixels are classified to obtain all edges in the human back image, as well as the edge angle difference between each edge pixel and its surrounding edge pixels; based on the positive and negative curvature characteristics of the edge pixels within each edge, edges are filtered to obtain all edges to be analyzed; based on the distribution characteristics of the edge angle difference and curvature distribution characteristics between different edge pixels in each edge to be analyzed, the bone quality index of each edge to be analyzed is obtained; based on the bone quality index and positive and negative curvature characteristics of each edge to be analyzed, all edges to be analyzed are divided into spinal region edges and scapular region edges; acupoints are located for the patient based on the spinal region edges and the scapular region edges.

[0005] Furthermore, the method for obtaining the relative distance includes: calculating the maximum distance between all pixels and the shooting point; taking the distance between each pixel and the shooting point as a first distance; and taking the difference between the maximum distance and the first distance of each pixel as the relative distance of each pixel.

[0006] Furthermore, the method for obtaining the curvature of each pixel includes: establishing a Cartesian coordinate system with the lower left corner of the human back image as the origin, the horizontal direction as the x-axis, and the vertical direction as the y-axis; obtaining the curvature according to the curvature calculation formula, which is shown below: In the formula, Indicates that it is located at The curvature of the pixel at the location; Indicates to Relative distance function of pixels Seeking information about The second partial derivative; Indicates to Relative distance function of pixels Seeking information about The second partial derivative; Indicates to Relative distance function of pixels First, please ask about The partial derivative of , then find the derivative with respect to The partial derivative; Indicates to Relative distance function of pixels Seeking information about The partial derivative; Indicates to Relative distance function of pixels Seeking information about The partial derivative of .

[0007] Furthermore, the method for obtaining all edges in the human back image, and the edge angle difference between edge pixels and surrounding edge pixels, includes: traversing the human back image from left to right and top to bottom with a preset sliding window starting from the top left corner and following a preset step size; performing no operation when there are no edge pixels within the preset sliding window; and calculating the edge angle difference between each edge pixel and other edge pixels within the preset sliding window when the center pixel of the preset sliding window is an edge pixel, using the following formula: In the formula, Indicates that the preset sliding window is located within The difference in edge angles of pixels at a given location; Indicates that the preset sliding window is located in addition to the one in the middle. The number of pixels other than the pixel at the given location; Indicates that the preset sliding window is located within The gradient angle of the pixel at the location; Indicates that the preset sliding window is located in addition to the one in the middle. The third pixel outside the position The gradient angle of each pixel is calculated; the edge angle difference between each other edge pixel and the center pixel of the window within the preset sliding window is calculated; the other edge pixel with the smallest edge angle difference and closest to the center pixel of the window is taken as the first pixel of the same type as the center pixel of the window; the first pixel of the same type is taken as the center pixel; the above operation is repeated in the window area of ​​the same range as the preset sliding window until there are no other edge pixels in the window area of ​​the same range as the preset sliding window; all the selected center pixels are classified into one category; the preset sliding window is continued to slide, and the above operation is repeated until all pixels are traversed and all pixels are classified; the area formed by the edge pixels in each category is taken as an edge.

[0008] Furthermore, the method for obtaining the edge to be analyzed includes: when the number of edge pixels with positive curvature is less than the number of edge pixels with negative curvature, and the number of edge pixels with positive curvature exceeds a preset first number, the edge is taken as the edge to be analyzed.

[0009] Furthermore, the method for obtaining the bone mass index includes: obtaining the bone mass index according to the bone mass index calculation formula, the bone mass index calculation formula being as follows: In the formula, In the image of the human back, the first Bone quality indicators at the edge of the analysis; Indicates the first The number of edge pixels in the edge to be analyzed; Indicates the first The first edge to be analyzed The edge angle difference of each edge pixel; Indicates the first The mean edge angle difference of all edge pixels in the edge to be analyzed; Indicates the first The mean curvature of all edge pixels in the edge to be analyzed; This represents the average of the edge angle differences of all edges to be analyzed. This represents the absolute value function.

[0010] Furthermore, the method for obtaining the edges of the spinal region and the scapular region includes: calculating the average bone quality index of all edges; taking all edges with a mean curvature greater than 0 and a bone quality index greater than the mean bone quality index as the edges of the spinal region; and taking all edges with a mean curvature less than 0 and a bone quality index greater than the mean bone quality index as the edges of the scapular region.

[0011] An acupuncture point-assisted positioning system for lung treatment includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of the acupuncture point-assisted positioning method for lung treatment as described above.

[0012] A computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the acupuncture point-assisted positioning method for lung treatment described above.

[0013] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the steps of the acupuncture point-assisted positioning method for lung treatment as described above.

[0014] This invention has the following beneficial effects: The invention uses the bone measurement method to assist in the location of acupoints, thus requiring accurate identification of the spinal and scapular regions. Therefore, an image of the human back is first acquired. The distribution of different pixels within the human back image needs to be described. Therefore, based on the distance distribution characteristics between different pixels and the shooting point in the human back image, the relative distance of each pixel is obtained. Because the scapular region exhibits depressions while the spinal region shows regular protrusions, the curvature of the scapular and spinal regions differs from the normal region, creating a gradient and resulting in edge regions. Therefore, the curvature of the pixels is calculated. Since the edge information in the human back image can inform the subsequent identification of the spinal region and... The identification of the scapular region provides the necessary conditions, so edge detection is performed on each pixel to obtain the edge angle of each edge pixel. Since the spine has a straight and regular shape, the edge regions generated by the scapular region are more irregular. Therefore, edge pixels in the image are first acquired and then filtered to determine their regularity. Because the spine region, scapular region, and other back regions differ in curvature and edge features, edges are filtered to remove those from normal back skin areas, resulting in the edges to be analyzed. All edges to be analyzed are further filtered, dividing them into spine region edges and scapular region edges. Acupoints are located on the patient based on the spine region edges and scapular region edges. This invention can accurately identify the spine region and scapular region on the human back, thus helping relevant personnel to accurately identify acupoints. Attached Figure Description

[0015] To more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of an acupuncture point-assisted positioning method for lung treatment, provided as an embodiment of the present invention. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details the specific implementation, structure, features, and effects of an acupuncture point-assisted positioning method for lung treatment proposed according to the present invention. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0018] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0019] The following description, in conjunction with the accompanying drawings, details a specific scheme for an acupuncture point-assisted positioning method for lung treatment provided by the present invention.

[0020] Please see Figure 1 This invention illustrates an acupuncture point-assisted positioning method for lung treatment provided by an embodiment of the present invention. The method includes: step S1: acquiring an image of the human back.

[0021] The embodiments of the present invention are mainly applied to acupoint location scenarios related to lung treatment. Since the present invention uses the bone measurement method to assist in the location of acupoints, it is necessary to accurately identify the spinal region and the scapular region. Therefore, the embodiments of the present invention first acquire an image of the human back, and then identify the spinal region and the scapular region in the image of the human back in subsequent steps.

[0022] In this embodiment of the invention, a patient of moderate build, normal body shape and no skeletal deformities is selected, and an RGB-D camera is used to photograph their back. The photographed image is then denoised, and the denoised image is converted to grayscale to obtain a grayscale image of their back. This grayscale image of the back is used as the human back image required for subsequent operations.

[0023] Step S2: Based on the distance distribution characteristics between different pixels and the shooting point in the human back image, obtain the relative distance of each pixel; based on the relative distance of each pixel, obtain the curvature of each pixel; perform edge detection on each pixel to obtain the edge angle of each edge pixel; based on the edge angle difference and distribution characteristics between each edge pixel and surrounding edge pixels, classify all edge pixels to obtain all edges in the human back image, as well as the edge angle difference between edge pixels and surrounding edge pixels; based on the positive and negative curvature characteristics of edge pixels within each edge, filter the edges to obtain all edges to be analyzed; based on the edge angle difference distribution characteristics and curvature distribution characteristics between different edge pixels in each edge to be analyzed, obtain the bone quality index of each edge to be analyzed; based on the bone quality index and positive and negative curvature characteristics of each edge to be analyzed, divide all edges to be analyzed into spine region edges and scapular region edges.

[0024] Before identifying the spinal and scapular regions, it is first necessary to describe the positional distribution of different pixels within the human back image. Therefore, in this embodiment of the invention, the relative distance of each pixel is obtained based on the distance distribution characteristics between different pixels and the shooting point in the human back image.

[0025] Preferably, in one embodiment of the present invention, the method for obtaining the relative distance includes: since the position of the shooting point is fixed when shooting an image of the human back, the position distribution between different pixels is described by using the position between the shooting point and all pixels in the human back image, that is, calculating the maximum distance between all pixels and the shooting point; taking the distance between each pixel and the shooting point as the first distance; and taking the difference between the maximum distance and the first distance of each pixel as the relative distance of each pixel.

[0026] The most significant difference between the scapula and spine regions and other back regions is that the scapula region is concave, while the spine region is regularly protruding. This results in a difference in curvature between the scapula and spine regions and the normal region, and a certain gradient is generated, leading to the formation of edge regions. Therefore, in this embodiment of the invention, the curvature of the pixel is calculated first.

[0027] Preferably, in one embodiment of the present invention, the method for obtaining the curvature of each pixel includes: establishing a Cartesian coordinate system with the lower left corner of the human back image as the origin, the horizontal direction as the x-axis, and the vertical direction as the y-axis.

[0028] The curvature is obtained using the curvature calculation formula, which is shown below: In the formula, Indicates that it is located at The curvature of the pixel at the location; Indicates to Relative distance function of pixels Seeking information about The second partial derivative; Indicates to Relative distance function of pixels Seeking information about The second partial derivative; Indicates to Relative distance function of pixels First, please ask about The partial derivative of , then find the derivative with respect to The partial derivative; Indicates to Relative distance function of pixels Seeking information about The partial derivative; Indicates to Relative distance function of pixels Seeking information about The partial derivative of .

[0029] Since the formula for calculating curvature is a well-known technique in the field, it will not be elaborated here.

[0030] In addition to curvature, edge information in the human back image can provide conditions for the subsequent identification of the spine region and scapula region. Therefore, in this embodiment of the invention, edge detection is performed on each pixel to obtain the edge angle of each edge pixel.

[0031] In one embodiment of the present invention, the Kirsch operator is used to perform edge detection on a back image. Eight convolutional kernels in different directions are used to detect edge features at various angles in the image, and the gradient angles of all edges in the image are obtained. It should be noted that the Kirsch operator is a technique well-known to those skilled in the art, and the eight directions are... This will not be limited or elaborated upon here.

[0032] The shape and features of the spine and scapulae reveal that the spine extends straight down the central region of the back, exhibiting a linear and regular line. However, the scapular region, due to variations in back muscle shape and the shape and protrusion of the scapulae themselves, results in more irregular edges. Therefore, it is necessary to filter edge pixels to determine their regularity. In this embodiment of the invention, based on the edge angle differences and distribution characteristics between each edge pixel and its surrounding edges, all edge pixels are classified to obtain all edges in the human back image, as well as the edge angle differences between each edge pixel and its surrounding edges.

[0033] Preferably, in one embodiment of the present invention, the method for obtaining all edges in a human back image, and the edge angle difference between edge pixels and surrounding edge pixels, includes: traversing the human back image from left to right and top to bottom using a preset sliding window, starting from the upper left corner of the image and following a preset step size. In one embodiment of the present invention, the preset sliding window is set to... The rectangular area is not limited here.

[0034] When there are no edge pixels within the preset sliding window, it is assumed that the area within the preset sliding window is a regular, flat back region, rather than the spine and scapula region. Therefore, no operation is performed, and the sliding continues. To ensure that the preset sliding window includes as many edge pixels as possible, analysis is performed when the center pixel of the preset sliding window is an edge pixel. The edge angle difference between each edge pixel and other edge pixels within the preset sliding window is calculated using the following formula: In the formula, Indicates that the preset sliding window is located within The edge angle difference of the pixels at the location; Indicates that the preset sliding window is located in addition to the one in the middle. The number of pixels other than the pixel at the given location; Indicates that the preset sliding window is located within The gradient angle of the pixel at the location; Indicates that the preset sliding window is located in addition to the one in the middle. The third pixel outside the position The gradient angle of each pixel.

[0035] In the formula for calculating the edge angle difference, located at... The greater the difference between the gradient angle of a pixel at a given location and the gradient angle of every other edge pixel within the preset sliding window, the more likely the pixel within the preset sliding window is to be at a certain position. The greater the edge angle difference of the pixels at a given location, the more likely it is to be located at a given position. The more irregular the area between the pixel at a given location and other edge pixels within the preset sliding window, the better.

[0036] Calculate the edge angle difference between each other edge pixel and the window center pixel within the preset sliding window. Select the other edge pixel with the smallest edge angle difference and closest to the window center pixel as the first pixel of the same category as the window center pixel. Use the first pixel of the same category as the center pixel. Repeat the above operation in the window area of ​​the same range as the preset sliding window until there are no other edge pixels in the window area of ​​the same range as the preset sliding window. Sort all the selected center pixels into one category. Continue to slide the preset sliding window and repeat the above operation until all pixels have been traversed. Sort all pixels. Use the area formed by the edge pixels in each category as an edge.

[0037] At this point, all edge pixels are classified to obtain all edges in the human back image, and the edge angle difference of each edge pixel in the edge is obtained.

[0038] As can be seen from reality, the image characteristics of the spinal region are: straight and regular lines, with the spinous processes being more prominent compared to the surrounding back area. The image characteristics of the scapular region are: the edges of the back area caused by bony protrusions are relatively irregular, and the lower edge of the scapula exhibits a concave characteristic compared to the surrounding back area. However, both the spinal and scapular regions show significant changes in three-dimensional space compared to the surrounding back area, resulting in very regular curvature without large variations. In contrast, the three-dimensional variations in certain areas of the back caused by muscles, fat, or other factors do not exhibit this characteristic. Therefore, in this embodiment of the invention, the edges are first filtered out, removing the edges of normal back skin areas to obtain the edges to be analyzed.

[0039] Preferably, in one embodiment of the present invention, the method for obtaining the edge to be analyzed includes: when the number of edge pixels with positive curvature is less than the number of edge pixels with negative curvature, and the number of edge pixels with positive curvature exceeds a preset first number, the edge is taken as the edge to be analyzed. In one embodiment of the present invention, the preset first number is set to one-third of the edge pixels. When the condition is met, the area where the edge is located is considered to be uneven and irregular, and does not conform to the edge characteristics of the spinal region or scapular region. Therefore, the edge is considered to belong to the normal back skin area and is filtered out.

[0040] All edges to be analyzed are further filtered and divided into spine region edges and scapular region edges.

[0041] First, the bone density index of each edge to be analyzed is calculated to analyze the degree of depression and protrusion in the back region, and whether the edge is regular. Preferably, in one embodiment of the present invention, the method for obtaining the bone density index includes: obtaining the bone density index according to the bone density index calculation formula, which is shown below: In the formula, In the image of the human back, the first Bone quality indicators at the edge of the analysis; Indicates the first The number of edge pixels in the edge to be analyzed; Indicates the first The first edge to be analyzed The edge angle difference of each edge pixel; Indicates the first The mean edge angle difference of all edge pixels in the edge to be analyzed; Indicates the first The mean curvature of all edge pixels in the edge to be analyzed; This represents the average of the edge angle differences of all edges to be analyzed. This represents the absolute value function.

[0042] In the formula for calculating bone mass index, the first... The difference between the edge angle difference of each edge pixel in the edge to be analyzed and the mean edge angle difference. The smaller the value, the better. If the gradient angles of the edge pixels in the edge to be analyzed are highly consistent, then the lower the disorder of the edge, that is, the more regular the gradient angles of the edge pixels, the closer the edge is to a straight line. The mean edge angle difference of the edge to be analyzed is then compared with the average of the mean edge angle differences of all edges to be analyzed. The smaller the value, the more likely it is to be an edge to be analyzed around the spine; and because the spinous process region of the spine protrudes compared to the surrounding back region, the curvature of the edge pixels in this region is greater than 0. Therefore, when the average curvature of the edge to be analyzed is greater than 0, the larger the average curvature, the more likely it is to be an edge pixel around the spine; for the scapular region, the gradient angle of the edge pixels in the region is more complex, so... The larger the value, the greater the disorder of the edge to be analyzed, and the more likely the edge to belong to the scapular region. The mean edge angle difference of the edge to be analyzed is compared with the average of the mean edge angle differences of all edges to be analyzed. The larger the value, the more complex and varied the edge to be analyzed is compared to all other edges to be analyzed, and the more likely the edge to be analyzed belongs to the scapular region. Due to the concave nature of the lower edge region of the scapula compared to the surrounding back region, the curvature of the edge pixels in this region is less than 0. Therefore, when the average curvature of the edge to be analyzed is less than 0, the smaller the average curvature, the more likely it is to be an edge pixel around the scapula.

[0043] Preferably, in one embodiment of the present invention, the method for obtaining the edges of the spinal region and the scapular region includes: calculating the average bone quality index of all edges; taking all edges with a mean curvature greater than 0 and a bone quality index greater than the average bone quality index as the edges of the spinal region; and taking all edges with a mean curvature less than 0 and a bone quality index greater than the average bone quality index as the edges of the scapular region.

[0044] Step S3: Locate acupoints on the patient based on the edges of the spinal region and the scapular region.

[0045] In one embodiment of the present invention, the spinal and scapular regions on the back image of the patient studied in step S1 are located, enabling relevant personnel to assist in locating all acupoints related to lung treatment based on bone measurement methods. For other patients, the change in acupoint location can be determined by the difference in body proportions between other patients and the patient studied in step S1, thereby achieving the effect of assisting in the location of acupoints for lung treatment.

[0046] This completes the auxiliary location of acupuncture points for lung treatment.

[0047] In summary, the following steps are taken: First, an image of the human back is acquired. Then, based on the distance distribution characteristics between different pixels in the image and the shooting point, the relative distance of each pixel is obtained. Next, the curvature of each pixel is obtained based on its relative distance. Edge detection is performed on each pixel to obtain its edge angle. Finally, based on the edge angle differences and distribution characteristics between each edge pixel and its surrounding edges, all edge pixels are classified to obtain all edges in the human back image, as well as the edge angle differences between edge pixels and their surrounding edges. Edges are then filtered based on the positive and negative curvature characteristics of the edge pixels within each edge to obtain all edges to be analyzed. Based on the distribution characteristics of the edge angle differences and curvature distribution characteristics between different edge pixels in each edge to be analyzed, bone density parameters are obtained for each edge to be analyzed. Based on the bone density parameters and the positive and negative curvature characteristics of each edge to be analyzed, all edges to be analyzed are divided into spinal region edges and scapular region edges. Finally, acupoints are located for the patient based on the spinal region edges and scapular region edges.

[0048] The second objective of this invention is to provide an acupuncture point-assisted positioning system for lung treatment. The system includes a memory, a processor, and a computer program. The memory stores the corresponding computer program, and the processor runs the corresponding computer program. When the computer program runs in the processor, it can implement the methods described in steps S1-S3.

[0049] A third objective of this invention is to provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the methods described in steps S1-S3.

[0050] The fourth objective of this invention is to provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in steps S1-S3.

[0051] It should be noted that the order of the above embodiments of the present invention is merely for descriptive purposes and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require a specific or sequential order to achieve the desired result. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0052] The various embodiments in this specification are described in a progressive manner. The same or similar parts between the various embodiments can be referred to each other. Each embodiment focuses on describing the differences from other embodiments.

Claims

1. A method for auxiliary acupuncture point location in lung treatment, characterized in that, The method includes: acquiring an image of a human back; obtaining the relative distance of each pixel based on the distance distribution characteristics between different pixels in the human back image and the shooting point; obtaining the curvature of each pixel based on the relative distance of each pixel; performing edge detection on each pixel to obtain the edge angle of each edge pixel; classifying all edge pixels based on the edge angle difference and distribution characteristics between each edge pixel and surrounding edge pixels to obtain all edges in the human back image, as well as the edge angle difference between edge pixels and surrounding edge pixels; filtering edges based on the positive and negative curvature characteristics of edge pixels within each edge to obtain all edges to be analyzed; obtaining the bone quality index of each edge to be analyzed based on the edge angle difference distribution characteristics and curvature distribution characteristics between different edge pixels in each edge to be analyzed; dividing all edges to be analyzed into spinal region edges and scapular region edges based on the bone quality index and positive and negative curvature characteristics of each edge to be analyzed; and locating acupoints on the patient based on the spinal region edges and the scapular region edges.

2. The acupuncture point location method for lung treatment according to claim 1, characterized in that, The method for obtaining the relative distance includes: calculating the maximum distance between all pixels and the shooting point; taking the distance between each pixel and the shooting point as the first distance; and taking the difference between the maximum distance and the first distance of each pixel as the relative distance of each pixel.

3. The acupuncture point location method for lung treatment according to claim 1, characterized in that, The method for obtaining the curvature of each pixel includes: establishing a Cartesian coordinate system with the lower left corner of the human back image as the origin, the horizontal direction as the x-axis, and the vertical direction as the y-axis; and obtaining the curvature according to the curvature calculation formula, which is shown below: In the formula, Indicates that it is located at The curvature of the pixel at the location; Indicates to Relative distance function of pixels Seeking information about The second partial derivative; Indicates to Relative distance function of pixels Seeking information about The second partial derivative; Indicates to Relative distance function of pixels First, please ask about The partial derivative of , then find the derivative with respect to The partial derivative; Indicates to Relative distance function of pixels Seeking information about The partial derivative; Indicates to Relative distance function of pixels Seeking information about The partial derivative of .

4. The acupuncture point location method for lung treatment according to claim 1, characterized in that, The method for obtaining all edges in a human back image, and the edge angle difference between edge pixels and surrounding edge pixels, includes: traversing the human back image from left to right and top to bottom with a preset sliding window starting from the top left corner and following a preset step size; performing no operation when there are no edge pixels within the preset sliding window; and calculating the edge angle difference between each edge pixel and other edge pixels within the preset sliding window when the center pixel of the preset sliding window is an edge pixel, using the following formula: In the formula, Indicates that the preset sliding window is located within The edge angle difference of the pixels at the location; Indicates that the preset sliding window is located in addition to the one in the middle. The number of pixels other than the pixel at the given location; Indicates that the preset sliding window is located within The gradient angle of the pixel at the location; Indicates that the preset sliding window is located in addition to the one in the middle. The third pixel outside the position The gradient angle of each pixel is calculated; the edge angle difference between each other edge pixel and the center pixel of the window within the preset sliding window is calculated; the other edge pixel with the smallest edge angle difference and closest to the center pixel of the window is taken as the first pixel of the same type as the center pixel of the window; the first pixel of the same type is taken as the center pixel; the above operation is repeated in the window area of ​​the same range as the preset sliding window until there are no other edge pixels in the window area of ​​the same range as the preset sliding window; all the selected center pixels are classified into one category; the preset sliding window is continued to slide, and the above operation is repeated until all pixels are traversed and all pixels are classified; the area formed by the edge pixels in each category is taken as an edge.

5. The acupuncture point location method for lung treatment according to claim 1, characterized in that, The method for obtaining the edge to be analyzed includes: when the number of edge pixels with positive curvature is less than the number of edge pixels with negative curvature, and the number of edge pixels with positive curvature exceeds a preset first number, the edge is taken as the edge to be analyzed.

6. The acupuncture point location method for lung treatment according to claim 1, characterized in that, The method for obtaining the bone mass index includes: obtaining the bone mass index according to the bone mass index calculation formula, which is shown below: In the formula, In the image of the human back, the first Bone quality indicators at the edge of the analysis; Indicates the first The number of edge pixels in the edge to be analyzed; Indicates the first The first edge to be analyzed The edge angle difference of each edge pixel; Indicates the first The mean edge angle difference of all edge pixels in the edge to be analyzed; Indicates the first The mean curvature of all edge pixels in the edge to be analyzed; This represents the average of the edge angle differences of all edges to be analyzed. This represents the absolute value function.

7. The acupuncture point location method for lung treatment according to claim 1, characterized in that, The method for obtaining the edges of the spinal region and the scapular region includes: calculating the average bone quality index of all edges; taking all edges with a mean curvature greater than 0 and a bone quality index greater than the mean bone quality index as the edges of the spinal region; and taking all edges with a mean curvature less than 0 and a bone quality index greater than the mean bone quality index as the edges of the scapular region.

8. An acupuncture point-assisted positioning system for lung treatment, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the acupuncture point-assisted positioning method for lung treatment as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the acupuncture point-assisted positioning method for lung treatment as described in any one of claims 1 to 7.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the acupuncture point-assisted positioning method for lung treatment as described in any one of claims 1 to 7.

Images