Search

KR-20260064087-A - METHOD AND APPARATUS FOR GENERATING CLINICAL DATA OF ACUPUNCTURE

KR20260064087AKR 20260064087 AKR20260064087 AKR 20260064087AKR-20260064087-A

Abstract

A method and apparatus for generating clinical data for acupuncture treatment are provided, comprising the steps of acquiring SFM data from multiple two-dimensional images of a treatment area at different viewpoints, generating a three-dimensional model of the treatment area through neural rendering based on the SFM data, and generating clinical data regarding the treatment area from the three-dimensional model.

Inventors

  • 권기훈
  • 문영민
  • 서준영

Assignees

  • 재단법인 포항산업과학연구원

Dates

Publication Date
20260507
Application Date
20241031

Claims (18)

  1. As a method for generating clinical data for acupuncture procedures, A step of acquiring Structure From Motion (SFM) data from multiple two-dimensional images at different viewpoints of the treatment area of the acupuncture procedure, A step of generating a 3D model of the treatment area through neural rendering based on the above SFM data, and Step of generating clinical data regarding the procedure area in the above 3D model A method including
  2. In paragraph 1, The step of generating clinical data regarding the procedure area in the above three-dimensional model is, A step of removing noise and background by performing first filtering on the above 3D model, and Step of generating the clinical data from the above-mentioned first-filtered three-dimensional model A method including
  3. In paragraph 2, The above first filtering is a clustering-based filtering method.
  4. In paragraph 2, The step of generating the clinical data from the above-mentioned first-filtered three-dimensional model is: A step of extracting 3D needle data corresponding to needles within the treatment area by performing a second filtering on the above first-filtered 3D model. A method including
  5. In Paragraph 4, The above secondary filtering is a method in which filtering is based on skin color information.
  6. In Paragraph 4, The step of generating the clinical data from the above-mentioned first-filtered three-dimensional model is: A step of grouping the 3D needle data by performing a 3D line fitting algorithm, and Step of generating the clinical data from the grouped three-dimensional acupuncture data A method that further includes.
  7. In paragraph 6, The step of generating the clinical data from the grouped three-dimensional acupuncture data is: A step of generating vector information of the needles using the grouped 3D needle data, A step of determining the external length of the needles based on the vector information of the needles, and A step of estimating the treatment depth of the needles based on the actual length information of the needles and the determined external length. Includes, A method in which the above vector information is generated through the estimation of the start and end points of the above needles.
  8. In Paragraph 7, The step of generating the clinical data from the grouped three-dimensional acupuncture data is: A step of estimating the treatment position and treatment direction of the needles based on the vector information of the needles. A method that further includes.
  9. In paragraph 8, The step of generating the clinical data from the grouped three-dimensional acupuncture data is: A step of generating clinical data by performing statistical analysis and/or quantification on the procedure location, procedure direction, and procedure depth of the needles. A method that further includes.
  10. In paragraph 1, The above SFM data includes three-dimensional point data, camera pose data, and keyframe images, a method.
  11. As a device for generating clinical data for acupuncture procedures, The processor and memory are included, the memory stores instructions that cause the processor to perform a plurality of steps, and the plurality of steps are A step of extracting 3D needle data corresponding to needles within the treatment area by performing filtering on a 3D model representing the treatment area where the acupuncture procedure is performed, and Step of generating the clinical data regarding the treatment area from the above 3D acupuncture data A device including
  12. In Paragraph 11, The above plurality of steps are, It further includes the step of grouping the 3D needle data by performing a 3D line fitting algorithm, and The step of generating the clinical data regarding the treatment area from the above three-dimensional acupuncture data is: Step of generating the clinical data from the grouped three-dimensional acupuncture data A device including
  13. In Paragraph 11, The step of extracting 3D needle data corresponding to needles within the treatment area by performing filtering on a 3D model representing the treatment area where the acupuncture procedure is performed is: A step of removing noise and background by performing first filtering on the above 3D model, and A step of extracting the 3D needle data by performing a second filtering on the above first-filtered 3D model. A device including
  14. In Paragraph 13, A device in which the first filtering is clustering-based filtering and the second filtering is skin color information-based filtering.
  15. In Paragraph 11, The step of generating the clinical data regarding the treatment area from the above three-dimensional acupuncture data is: A step of generating vector information of the needles by estimating the start and end points of the needles based on the above 3D needle data, A step of determining the external length of the needles based on the vector information of the needles, and Step of estimating the treatment depth of the needles based on the actual length information of the needles A device including
  16. In Paragraph 15, The step of generating the clinical data regarding the treatment area from the above three-dimensional acupuncture data is: A step of estimating the treatment position and treatment direction of the needles based on the vector information of the needles. A device that further includes
  17. In Paragraph 16, The step of generating the clinical data regarding the treatment area from the above three-dimensional acupuncture data is: A step of generating clinical data by performing statistical analysis and/or quantification on the procedure location, procedure direction, and procedure depth of the needles. A device that further includes
  18. As a device for generating clinical data for acupuncture procedures, A generative artificial neural network that performs neural rendering to generate a 3D model of a treatment area based on SFM (Structure From Motion) data obtained from multiple 2D images of the treatment area at different viewpoints of the acupuncture treatment area, A 3D model analysis processor that performs filtering on a 3D model representing the above-mentioned treatment area to extract 3D needle data corresponding to needles within the above-mentioned treatment area, and generates the above-mentioned clinical data regarding the above-mentioned treatment area from the 3D needle data, and Memory that stores instructions for the above 3D model analysis processor to perform a process A device including

Description

Method and apparatus for generating clinical data of acupuncture This description relates to a method and apparatus for generating clinical data for acupuncture procedures. This description is an outcome of research conducted in 2024 with funding from the Ministry of Science and ICT and supported by the National Research Foundation of Korea. (No. 2022M3A9B6082794) Acupuncture is the most representative treatment method in Korean traditional medicine, serving as a meridian stimulation procedure aimed at alleviating or preventing various health problems by stimulating specific points on the body. However, practitioners of acupuncture (doctors of Korean traditional medicine) rely on experience, and there are limitations in quantifying and scientifically analyzing the information regarding the procedure. To analyze and quantify clinical data from acupoint stimulation procedures, it is essential to acquire data on the treatment area using vision sensors (cameras, LiDAR, etc.) and analyze it using computer vision technology, but there are various problems. For example, 2D data (images) acquired through 2D vision sensors such as cameras lack 3D information, making meaningful quantification difficult. Furthermore, even if 3D data (point clouds) is acquired through 3D vision sensors such as RGB-D, LiDAR, and 3D scanners, data on thin and small objects, such as needles, may not be properly acquired depending on the sensor's performance. Additionally, the high cost of sensors and the significant amount of time required for precise scanning can cause inconvenience to patients and practitioners. FIG. 1 is a flowchart illustrating a method for generating clinical data of an acupuncture procedure according to one embodiment. FIG. 2 is a drawing showing two-dimensional images of a surgical area taken at multiple points in time according to one embodiment and a three-dimensional model generated therefrom. FIG. 3 is a diagram illustrating a training method for a generative artificial neural network according to one embodiment. FIG. 4 is a flowchart illustrating a method for estimating the procedure position, procedure direction, and procedure depth of an acupuncture procedure according to one embodiment from a three-dimensional model of a procedure area. FIG. 5 is a diagram showing the process of estimating the procedure location, procedure direction, and procedure depth of an acupuncture procedure according to one embodiment as a visual flow. FIG. 6 is a diagram showing a generative artificial neural network according to one embodiment. FIG. 7 is a block diagram showing a 3D model analysis device according to one embodiment. The embodiments of this description are described below with reference to the attached drawings so that those skilled in the art can easily implement them. However, this description may be implemented in various different forms and is not limited to the embodiments described herein. Furthermore, in order to clearly explain this description in the drawings, parts unrelated to the explanation have been omitted, and similar parts throughout the specification are denoted by similar reference numerals. In this description, each of the phrases such as “A or B”, “at least one of A and B”, “at least one of A or B”, “A, B or C”, “at least one of A, B and C”, and “at least one of A, B, or C” may include any one of the items listed together in the corresponding phrase, or all possible combinations thereof. In this description, when a part is described as "including" a certain component, it means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Expressions written in the singular in this description may be interpreted as singular or plural unless explicit expressions such as "one" or "singular" are used. In this description, "and/or" includes each of the mentioned components and all combinations of one or more. In this description, terms including ordinal numbers, such as first, second, etc., may be used to describe various components, but said components are not limited by said terms. Such terms are used solely for the purpose of distinguishing one component from another. For example, without departing from the scope of the present disclosure, the first component may be named the second component, and similarly, the second component may be named the first component. In the flowchart described herein with reference to the drawings, the order of operations may be changed, multiple operations may be merged or some operations may be divided, and certain operations may not be performed. The Artificial Intelligence model (AI model) of the present disclosure is a machine learning model that learns at least one task and may be implemented as a computer program executed by a processor. The task learned by the AI model may refer to a problem to be solved through machine learning or a task to be performed through machine learning. The AI model may be impl