Data evaluation system based on intramuscular nerve acupuncture

Abstract

The invention discloses a data evaluation system based on intramuscular nerve acupuncture, and the system obtains a plurality of human muscle and nerve distribution data through a data collection module, and is used for matching a muscle and nerve distribution model of a person to be punctured. After a person to be punctured is matched with the data acquisition module, dividing the muscle and nerve distribution data by adopting an area distinguishing module to generate a plurality of feature identification paths, then determining a main path chain for the plurality of feature identification paths through a feature recognition module, and determining priorities of other path chains based on the main path chain; the main path chain is assigned with a first weight in the feature assignment module, the other feature identification paths are assigned with a second weight based on the priority, and finally the optimal acupuncture position is evaluated according to the comparison result through the result optimization module according to the comparison result of the main path chain and the other feature identification paths. Accurate and effective acupuncture stimulation of a person to be punctured is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of acupuncture data evaluation, and in particular to a data evaluation system based on intramuscular nerve acupuncture. Background Art

[0002] Intramuscular acupuncture is a treatment technique that involves acupuncture intervention on nerves within the muscle. Its main purpose is to regulate muscle function, improve local blood circulation, relieve pain and promote the recovery of neuromuscular function by stimulating the nerves within the muscle.

[0003] However, in the field of intramuscular nerve acupuncture treatment, the current method of determining acupuncture points has obvious limitations. Although clinical judgment experience has a certain subjective guiding value, it is difficult to accurately locate the best acupuncture point due to individual differences and experience limitations of physicians. Although electromyography can provide some neuromuscular electrical activity information, its detection range is limited. For complex muscle nerve structures, it cannot fully and accurately reflect the best stimulation site. It is difficult for both to find the best acupuncture point, resulting in the inability to achieve accurate and effective acupuncture stimulation during the treatment of muscle nerve function recovery, which greatly affects the recovery effect of muscle nerve function. Summary of the invention

[0004] The purpose of the present invention is to provide a data evaluation system based on intramuscular nerve acupuncture to solve the problems described in the background technology.

[0005] The technical solution of the present invention is achieved in this way: A data evaluation system based on intramuscular nerve acupuncture, comprising: a data acquisition module for acquiring human muscle and nerve distribution data, wherein the muscle and nerve distribution data include muscle thickness and nerve distribution in the muscle; A region differentiation module, used to divide the muscle and nerve distribution data to generate multiple feature identification paths; A feature recognition module, used to determine a main path chain for the plurality of feature identification paths, and determine the priorities of other path chains based on the main path chain; A feature assignment module, used to assign a first weight to the main path chain, and assign a second weight to other feature identification paths based on priority; The result optimization module compares the main path chain with other feature-identified path chains and evaluates the optimal acupuncture position based on the comparison results.

[0006] A further technical solution is that the data acquisition module includes: A data crawling unit, which acquires human muscle and nerve distribution data based on an anatomical database, including muscle thickness and nerve distribution in the muscle; A modeling unit is generated, which is used to construct a muscle shape and a nerve orientation model within the muscle shape according to the muscle and nerve distribution data.

[0007] A further technical solution is that the generation modeling unit constructs a muscle shape and a nerve orientation model within the muscle shape, comprising the following steps: Step S11: Obtaining the length, width, height and curvature geometric parameters of the muscle through two-dimensional modeling technology or three-dimensional modeling technology, and outputting a muscle model; Step S12: using the anatomical database, adding the nerve path distribution into the muscle model, and outputting the nerve path model; Step S13: normalizing the muscle model and the nerve orientation model through model fusion, outputting muscle and nerve distribution data, and outputting the muscle and nerve distribution data to the region differentiation module.

[0008] A further technical solution is that the region differentiation module includes: A model division unit, used for generating a plurality of regions from the muscle and nerve distribution data by using a division method according to the muscle and nerve distribution data; The area identification unit is used to divide each of the areas into a first path to be tested, a second path to be tested and a third path to be tested, and generate a plurality of characteristic identification paths according to the first path to be tested, the second path to be tested and the third path to be tested.

[0009] A further technical solution is that the feature identification path marks the first path to be tested, the second path to be tested and the third path to be tested as the main path chain and the other path chains.

[0010] A further technical solution is that the feature recognition module includes: a path determination unit, configured to use the first path to be tested among the plurality of characteristic identification paths as a main path chain, and use the second path to be tested and the third path to be tested among the characteristic identification paths as other path chains; The priority assigning unit determines the priorities of other path chains based on the main path chain.

[0011] A further technical solution is that the priority assignment unit specifically operates in the following steps: Step S21: selecting a path chain in the feature identification path, using a particle swarm optimization algorithm to calculate the correlation and fitness values ​​of other path chains, and considering the fitness values ​​as the correlation between the path chains; Step S22: selecting a path chain in another feature identification path, and calculating the fitness value, and after iterative calculation, obtaining the correlation between the multiple path chains; Step S23: After determining the main path chain, prioritize the other path chains based on the correlation between them and the main path chain.

[0012] A further technical solution is that, in step S22, the number of iterations is the number of times multiple path chains are selected.

[0013] A further technical solution is that the feature assignment module includes: An information collection unit is used to obtain the past medical history and occupational information of the person to be punctured; A first value assigning unit assigns a first weight to the main path chain based on the past medical records or occupational information based on a physician evaluation method; The second value assigning unit assigns a second weight to the other path chains based on the priority, and the second weight is positively correlated with the priority ranking.

[0014] A further technical solution is that, when there are past medical records, a physician evaluation method is used to assign a first weight to the main path chain based on the past medical records; when there are no past medical records, a first weight is assigned to the main path chain based on occupational information.

[0015] The beneficial effects of the present invention are: The data acquisition module is used to obtain multiple human muscle and nerve distribution data, and the muscle and nerve distribution data of the person to be punctured is obtained before puncture, so as to facilitate the subsequent model matching of the muscle and nerve distribution of the person to be punctured. After the person to be punctured is matched with the data acquisition module, the muscle and nerve distribution data are divided by the regional differentiation module to generate multiple feature identification paths, and then the main path chain is determined for the multiple feature identification paths through the feature recognition module, and the priority of other path chains is determined based on the main path chain. In the feature assignment module, the main path chain is assigned a first weight, and other feature identification paths are assigned a second weight based on the priority. Finally, the result optimization module is used to compare the main path chain with other feature identification path chains, and the optimal acupuncture position is evaluated according to the comparison result, so as to achieve accurate and effective acupuncture stimulation for the person to be punctured. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is a system block diagram of the present invention; Figure 2 A flow chart of the method for constructing neural trends of the present invention; Figure 3 The present invention is a flowchart of the priority assignment unit operation method. DETAILED DESCRIPTION

[0017] In order to better understand the technical content of the present invention, specific embodiments are provided below, and the present invention is further described in conjunction with the accompanying drawings.

[0018] See also Figures 1 to 3 A data evaluation system based on intramuscular nerve acupuncture includes: a data acquisition module, used to obtain human muscle and nerve distribution data, the muscle and nerve distribution data include muscle thickness and nerve distribution in the muscle; a region distinction module, used to divide the muscle and nerve distribution data to generate multiple feature identification paths; a feature recognition module, used to determine a main path chain for multiple feature identification paths, and determine the priority of other path chains based on the main path chain; a feature assignment module, used to assign a first weight to the main path chain, and assign a second weight to other feature identification paths based on the priority; a result optimization module, compared with the main path chain and other feature identification path chains, and evaluated the optimal acupuncture position according to the comparison result.

[0019] Specifically, a plurality of human muscle and nerve distribution data are obtained through the data acquisition module, and the muscle and nerve distribution data of the person to be punctured are obtained before puncture, so as to facilitate the subsequent model matching of the muscle and nerve distribution of the person to be punctured. After the person to be punctured is matched with the data acquisition module, the muscle and nerve distribution data are divided by the regional differentiation module to generate a plurality of feature identification paths, and then the main path chain is determined for the plurality of feature identification paths through the feature recognition module, and the priority of other path chains is determined based on the main path chain, and the main path chain is assigned a first weight in the feature assignment module, and other feature identification paths are assigned a second weight based on the priority, and finally, the result optimization module is used to compare the main path chain with other feature identification path chains, and the optimal acupuncture position is evaluated according to the comparison result, so as to achieve accurate and effective acupuncture stimulation for the person to be punctured.

[0020] In this embodiment, the data acquisition module includes: A data crawling unit acquires human muscle and nerve distribution data based on an anatomical database, including muscle thickness and nerve distribution within the muscle; and a modeling unit is generated to construct a muscle shape and a nerve orientation model within the muscle shape based on the muscle and nerve distribution data.

[0021] In the anatomical database, there are various human body modeling data. The data crawling unit obtains the human muscle and nerve distribution data in the anatomical database, and the muscle and nerve distribution data are used in the generation modeling unit to construct the muscle shape and the nerve direction model in the muscle shape. After collecting the muscle and nerve distribution of the person to be punctured, the nerve direction model in the muscle shape is matched with the nerve direction model in the muscle shape, and the nerve direction model in the muscle shape with a similarity of 99.99% is obtained for matching, which is used to determine the nerve direction in the basic muscle shape of the person to be punctured, so as to facilitate the subsequent puncture evaluation.

[0022] Furthermore, the generative modeling unit constructs a muscle shape and a nerve orientation model within the muscle shape, including the following steps: Step S11: Obtaining the length, width, height and curvature geometric parameters of the muscle through two-dimensional modeling technology or three-dimensional modeling technology, and outputting a muscle model; Step S12: using the anatomical database, adding the nerve path distribution into the muscle model, and outputting the nerve path model; Step S13: normalizing the muscle model and the nerve orientation model through model fusion, outputting muscle and nerve distribution data, and outputting the muscle and nerve distribution data to the region differentiation module.

[0023] Since the thickness of human muscles is not constant, it is necessary to evaluate the thickness of the muscles during puncture. Specifically, two-dimensional modeling technology or three-dimensional modeling technology is used to obtain the length, width, height and curvature geometric parameters of the muscles to be punctured, and the muscle model is output. Among them, the biceps can be obtained by two-dimensional modeling technology of medical imaging, such as the trapezius muscle, and three-dimensional surface modeling technology can be used to divide the muscle surface into multiple small surface patches, and the overall muscle geometry model is constructed by fitting these surface patches. After completing the muscle geometry model, by adding the nerve path, a quadratic curve or spline curve is used to fit the path of the nerve. These points can be used as control points of the curve to make the nerve path model more accurate. Finally, the muscle and nerve path are fused to obtain muscle and nerve distribution data, which is convenient for subsequent puncture evaluation.

[0024] In this embodiment, the region differentiation module includes: The model zoning unit is used to generate multiple areas according to the muscle and nerve distribution data using a division method; the area identification unit is used to divide each of the areas into a first path to be tested, a second path to be tested and a third path to be tested, and generate multiple characteristic identification paths according to the first path to be tested, the second path to be tested and the third path to be tested.

[0025] In the human body, there are multiple muscle and nerve puncture areas that need to be confirmed according to the specific medical location. Among the multiple areas, the areas that need specific acupuncture are divided into the first path to be tested, the second path to be tested, and the third path to be tested, which is convenient for subsequent screening of puncture paths. At the same time, multiple characteristic identification paths are generated in the first path to be tested, the second path to be tested, and the third path to be tested for subsequent path analysis.

[0026] Preferably, the feature identification path marks the first path to be tested, the second path to be tested and the third path to be tested as the main path chain and the other path chains.

[0027] By marking the first path to be tested, the second path to be tested and the third path to be tested as the main path chain and the other path chains, it is convenient for the feature recognition module to perform optimal path selection in the area.

[0028] In this embodiment, the feature identification module includes: a path determination unit, used to take the first path to be tested among the multiple feature identification paths as the main path chain, and take the second path to be tested and the third path to be tested among the feature identification paths as other path chains; and a priority assignment unit, which determines the priorities of other path chains based on the main path chain.

[0029] Furthermore, the specific operation steps of the priority assignment unit are as follows: Step S21: selecting a path chain in the feature identification path, using a particle swarm optimization algorithm to calculate the correlation and fitness values ​​of other path chains, and considering the fitness values ​​as the correlation between the path chains; Step S22: selecting a path chain in another feature identification path, and calculating the fitness value, and after iterative calculation, obtaining the correlation between the multiple path chains; Step S23: After determining the main path chain, prioritize the other path chains based on the correlation between them and the main path chain.

[0030] Wherein, in step S22, the number of iterations is the number of times multiple path chains are selected.

[0031] In the determined area, multiple paths are included, such as the distribution of nerve directions, which are correspondingly identified as the first path to be tested, the second path to be tested, and the third path to be tested. The first path to be tested, the second path to be tested, and the third path to be tested are set as severe numbness points, moderate numbness points, and mild numbness points. When acupuncture is preferred, it is usually based on a single neuron. Therefore, the first path to be tested can be determined as the main path chain. After the main path chain is determined, the second path to be tested and the third path to be tested are output as other path chains. Then, based on the main path chain, the priority of other path chains is judged. When judging the priority, the particle swarm optimization algorithm is used to calculate the correlation between other path chains and the main path chain to evaluate the priority. When calculating the correlation, first randomly select a path chain, and then use the particle swarm optimization algorithm to calculate the fitness value of other path chains based on the correlation. The fitness value is the correlation between the two path chains (the first path to be tested and the second path to be tested or the first path to be tested and the third path to be tested or the second path to be tested and the third path to be tested). Then select another path chain and calculate the fitness value in the same way. After iterating all the eye movement indicators, the correlation between any two path chains can be obtained. Then, when determining the main path chain, the priority of other path chains can be determined according to the correlation.

[0032] The present invention adopts a particle swarm optimization algorithm to calculate the correlation, and has an efficient search function. When calculating the correlation between path chains, there is no need for excessive manual intervention. When looking for the optimal position of intramuscular nerve acupuncture, the particle swarm optimization algorithm can construct a fitness function according to the muscle reaction effect factors after acupuncture, represent the acupuncture position by the position of the particles, and use the particle update mechanism to search for the optimal acupuncture position.

[0033] In this embodiment, the feature assignment module includes: an information collection unit, used to obtain the past medical history and occupational information of the person to be punctured; a first assignment unit, which assigns a first weight to the main path chain based on the past medical history or occupational information based on the physician evaluation method; a second assignment unit, which assigns a second weight to the other path chains based on the priority, and the second weight is positively correlated with the priority ranking.

[0034] Preferably, when there are past medical records, a physician evaluation method is used to assign a first weight to the main path chain based on the past medical records; when there are no past medical records, a first weight is assigned to the main path chain based on occupational information.

[0035] In each area, the main path chain and other path chains after priority sorting can be obtained. In the particle swarm optimization algorithm, the preferred main path chain is the path where the patient wants to perform the optimal acupuncture position. If a path with an optimal position is found in other path chains, it will be rearranged. In this judgment, the main path chain is the path where the patient wants to perform the optimal acupuncture position. When assigning the first weight, the patient's occupation and whether he has corresponding neurological diagnosis experience will be considered. When there is neurological diagnosis experience, it means that the numb area of ​​the patient has a history of treatment. Therefore, the first weight is assigned by referring to the neurological diagnosis medical record through the doctor's evaluation. When there is no neurological diagnosis experience, the first weight is assigned based on the patient's occupational information. For example, when the patient's job requires fixed actions, the job has a greater impact on the patient's nerves. Therefore, at this time, the first weight assigned to the change of the numb area as the main path chain has a higher trust value, and the weights of other path chains can be assigned according to the doctor's actual diagnosis. Since the first weight is determined, the second weight is determined by referring to the priority of other path chains. The second weight is positively correlated with the priority, that is, the higher the priority, the greater the second weight assigned value.

[0036] After assigning values ​​to the main path chain and other path chains respectively, the assigned main path chain is compared with the other path chains, and the optimal acupuncture position is evaluated based on the ratio combination, which helps the physician to make the best choice for the numb area of ​​the person to be punctured, thereby improving the recovery effect of muscle nerve function. If the first weight of the severe numbness point is compared with the moderate numbness point or the mild numbness point, and the moderate numbness point or the mild numbness point is more suitable for acupuncture, then acupuncture treatment is performed from the moderate numbness point or the mild numbness point. If the first weight is more important, acupuncture is required from the severe numbness point. If among the moderate numbness point or the mild numbness point, the moderate numbness point is prioritized, then acupuncture treatment is performed from the moderate numbness point, otherwise acupuncture treatment is performed from the mild numbness point.

[0037] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A data evaluation system based on intramuscular nerve acupuncture, characterized in that: include: A data acquisition module, used to obtain human muscle and nerve distribution data, wherein the muscle and nerve distribution data include muscle thickness and nerve distribution in the muscle; A region differentiation module, used to divide the muscle and nerve distribution data to generate multiple feature identification paths; A feature recognition module, used to determine a main path chain for the plurality of feature identification paths, and determine the priorities of other path chains based on the main path chain; A feature assignment module, used to assign a first weight to the main path chain, and assign a second weight to other feature identification paths based on priority; The result optimization module compares the main path chain with other feature-identified path chains and evaluates the optimal acupuncture position based on the comparison results.

2. A data evaluation system based on intramuscular nerve acupuncture according to claim 1, characterized in that: The data acquisition module comprises: A data crawling unit, which acquires human muscle and nerve distribution data based on an anatomical database, including muscle thickness and nerve distribution in the muscle; A modeling unit is generated, which is used to construct a muscle shape and a nerve orientation model within the muscle shape according to the muscle and nerve distribution data.

3. A data evaluation system based on intramuscular nerve acupuncture according to claim 2, characterized in that: The generative modeling unit constructs a muscle shape and a nerve routing model within the muscle shape, comprising the following steps: Step S11: Obtaining the length, width, height and curvature geometric parameters of the muscle through two-dimensional modeling technology or three-dimensional modeling technology, and outputting a muscle model; Step S12: using the anatomical database, adding the nerve path distribution into the muscle model, and outputting the nerve path model; Step S13: normalizing the muscle model and the nerve orientation model through model fusion, outputting muscle and nerve distribution data, and outputting the muscle and nerve distribution data to the region differentiation module.

4. A data evaluation system based on intramuscular nerve acupuncture according to claim 1 or 3, characterized in that: The area differentiation module comprises: A model division unit, used for generating a plurality of regions from the muscle and nerve distribution data by using a division method according to the muscle and nerve distribution data; The area identification unit is used to divide each of the areas into a first path to be tested, a second path to be tested and a third path to be tested, and generate a plurality of characteristic identification paths according to the first path to be tested, the second path to be tested and the third path to be tested.

5. A data evaluation system based on intramuscular nerve acupuncture according to claim 4, characterized in that: The feature identification path marks the first path to be tested, the second path to be tested, and the third path to be tested as the main path chain and the other path chains.

6. A data evaluation system based on intramuscular nerve acupuncture according to claim 1 or 4, characterized in that: The feature recognition module comprises: a path determination unit, configured to use the first path to be tested among the plurality of characteristic identification paths as a main path chain, and use the second path to be tested and the third path to be tested among the characteristic identification paths as other path chains; The priority assigning unit determines the priorities of other path chains based on the main path chain.

7. A data evaluation system based on intramuscular nerve acupuncture according to claim 6, characterized in that: The specific operation steps of the priority assignment unit are as follows: Step S21: selecting a path chain in the feature identification path, using a particle swarm optimization algorithm to calculate the correlation and fitness values ​​of other path chains, and considering the fitness values ​​as the correlation between the path chains; Step S22: selecting a path chain in another feature identification path, and calculating the fitness value, and after iterative calculation, obtaining the correlation between the multiple path chains; Step S23: After determining the main path chain, prioritize the other path chains based on the correlation between them and the main path chain.

8. A data evaluation system based on intramuscular nerve acupuncture according to claim 7, characterized in that: In step S22, the number of iterations is the number of times multiple path chains are selected.

9. A data evaluation system based on intramuscular nerve acupuncture according to claim 1, characterized in that: The feature assignment module comprises: An information collection unit is used to obtain the past medical history and occupational information of the person to be punctured; A first value assigning unit assigns a first weight to the main path chain based on the past medical records or occupational information based on a physician evaluation method; The second value assigning unit assigns a second weight to the other path chains based on the priority, and the second weight is positively correlated with the priority ranking.

10. A data evaluation system based on intramuscular nerve acupuncture according to claim 9, characterized in that: When there are past medical records, the physician evaluation method is used to assign the first weight to the main path chain based on the past medical records. When there are no past medical records, the first weight is assigned to the main path chain based on occupational information.

Images