KR-102960760-B1 - METHOD AND APPARATUS FOR DIAGNOSING DISEASES BY USING ARTIFICIAL INTELLIGENCE MODEL

KR102960760B1KR 102960760 B1KR102960760 B1KR 102960760B1KR-102960760-B1

Abstract

An apparatus for diagnosing a disease using an artificial intelligence model according to one aspect comprises at least one memory; and at least one processor; wherein the processor acquires Raman signal data from a biological solution of a subject using a Raman signal amplifier, generates at least one Raman signal derivative data through a predetermined preprocessing of the Raman signal data, and inputs the Raman signal derivative data as input data to at least one diagnostic model to acquire disease information of the subject as output data.

Inventors

김지은
이경성
황재호
배정윤

Assignees

주식회사 이모코그

Dates

Publication Date: 20260507
Application Date: 20240527
Priority Date: 20230526

Claims (10)

A step of acquiring Raman signal data from a subject's biological solution using a Raman signal amplifier; A step of generating a first Raman signal derived data and a second Raman signal derived data through a predetermined preprocessing of the above Raman signal data; and The method includes the step of inputting the first Raman signal derivative data and the second Raman signal derivative data as input data into at least one diagnostic model to obtain disease information of the subject as output data. The step of obtaining the disease information of the above-mentioned subject is, The method includes the step of inputting a first Raman signal derived data and a second Raman signal derived data, respectively, to at least one first sub-diagnostic model and at least one second sub-diagnostic model included in the above diagnostic model; The above first Raman signal derived data is data generated by extracting features at each predetermined interval of the above Raman signal data, and The above second Raman signal derivative data is data generated by converting the above Raman signal data into an image through a predetermined preprocessing, A method for diagnosing diseases using an artificial intelligence model.
In Article 1, The above Raman signal data is, A method of obtaining data by irradiating light onto a material containing the above-mentioned Raman signal amplifier.
In Article 1, The above Raman signal amplifier is, A method comprising a silica shell layer having an internal receiving space and a nanoparticle having a plasmonic metal, wherein the nanoparticle is disposed in one region of the receiving space inside the silica shell layer.
In Article 1, A method in which a first diagnostic model and a second diagnostic model included in the above diagnostic model each include a plurality of sub-diagnostic models, and the plurality of sub-diagnostic models are each trained using different training data to diagnose different diseases.
In Article 1, The above diagnostic model is at least one of a first diagnostic model and a second diagnostic model trained using Raman signal data of a patient with a disease as training data.
In Article 1, The above-mentioned acquisition step is, A method comprising the step of obtaining disease information of the subject by combining the output data of each of the first sub-diagnostic model and the second sub-diagnostic model.
In Article 6, The above-mentioned acquisition step is, A step of inputting the output data of each of the first sub-diagnostic model and the second sub-diagnostic model as input data to the trained ensemble model; and A method comprising the step of obtaining disease information of the subject as output data of the ensemble model.
In Article 5, A method in which the first diagnostic model and the second diagnostic model are retrained using the acquired disease information of the subject as training data.
A computer-readable recording medium having a program for executing the method of claim 1 on a computer.
Memory in which at least one program is stored; and It includes at least one processor that executes the above at least one program, and The above-mentioned at least one processor is, Raman signal data is acquired from the subject's biological solution using a Raman signal amplifier, and A first Raman signal derived data and a second Raman signal derived data are generated through a predetermined preprocessing of the above Raman signal data, and The first Raman signal derivative data and the second Raman signal derivative data are input into at least one diagnostic model as input data to obtain disease information of the subject as output data, and The first Raman signal derived data and the second Raman signal derived data are input to at least one first sub-diagnostic model and at least one second sub-diagnostic model included in the above diagnostic model, respectively. The above first Raman signal derived data is data generated by extracting at least one feature at each predetermined interval of the above Raman signal data, and The above second Raman signal derivative data is data generated by converting the above Raman signal data into an image through a predetermined preprocessing, A device that diagnoses diseases using an artificial intelligence model.

Description

Method and apparatus for diagnosing diseases using an artificial intelligence model The present disclosure relates to a method and apparatus for diagnosing a disease using an artificial intelligence model. Surface-enhanced Raman scattering (SERS) spectroscopy is a spectroscopy method designed to complement Raman scattering spectroscopy, which has weak signals and low reproducibility. It utilizes the phenomenon in which the Raman scattering intensity of molecules adsorbed on the surface of metal nanostructures, such as gold and silver, increases rapidly by more than 10⁶ to 10⁸ times. Surface-Enhanced Raman Scattering (SERS) spectroscopy can obtain a large amount of information with a single measurement and is an ultra-sensitive technique capable of directly measuring a single molecule. Because it can directly measure information regarding the vibrational states or molecular structures, it is recognized as a powerful analytical method for chemical, biological, and biochemical analysis. Recently, Surface Enhanced Raman Scattering (SAS) has garnered attention as a method for precisely acquiring comprehensive information about biomolecules from biological samples; however, conventional detection methods for biomolecules utilizing SAS require specific binding. Consequently, there has been a problem in that screening and early diagnosis are difficult for intractable cancers and diseases, such as pancreatic cancer, because there are no biomarkers among blood indicators with excellent diagnostic performance. Accordingly, there is a need for diagnostic methods and systems utilizing surface-enhanced Raman scattering spectroscopy that can be used even when there are no biomarkers with excellent diagnostic performance among biomarkers, such as intractable cancers and intractable diseases like pancreatic cancer. Therefore, the present invention aims to diagnose various diseases, not just pancreatic cancer, using surface-enhanced Raman scattering spectroscopy and an artificial intelligence model. FIG. 1 is a diagram illustrating an example of a method for diagnosing a disease using an artificial intelligence model according to one embodiment. FIG. 2 is a block diagram illustrating an example of a device for diagnosing a disease using an artificial intelligence model according to one embodiment. FIG. 3 is a flowchart illustrating an example of a method for diagnosing a disease using an artificial intelligence model according to one embodiment. FIGS. 4a to 4d are drawings for illustrating an example of a structure for surface-enhanced Raman scattering spectroscopy according to one embodiment. FIG. 5 is a diagram illustrating an example of a composition for surface-enhanced Raman scattering spectroscopy according to one embodiment. FIG. 6 is a diagram illustrating an example of a method for learning a diagnostic model that diagnoses a disease according to one embodiment. FIG. 7 is a diagram illustrating an example of a method for obtaining disease information of a subject according to one embodiment. The terms used in the embodiments have been selected to be as close as possible to currently widely used general terms; however, these may vary depending on the intent of those skilled in the art, case law, the emergence of new technologies, etc. Additionally, in specific cases, terms have been selected at the applicant's discretion, and in such cases, their meanings will be described in detail in the relevant description section. Therefore, terms used in the specification must be defined not merely by their names, but based on their meanings and the content throughout the specification. When a part of the specification is described as "comprising" a certain component, this means that, unless specifically stated otherwise, it does not exclude other components but may include additional components. Furthermore, terms such as "~ unit" or "~ module" as used in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware or software, or as a combination of hardware and software. Additionally, terms including ordinal numbers, such as "first" or "second," used in the specification may be used to describe various components, but said components should not be limited by said terms. Such terms may be used for the purpose of distinguishing one component from another. The present disclosure will be described in detail below with reference to the attached drawings. Specifically, a method for diagnosing a disease using an artificial intelligence model according to one embodiment will be described in more detail with reference to FIGS. 1 to 7. However, embodiments may be implemented in various different forms and are not limited to the examples described herein. FIG. 1 is a diagram illustrating an example of a method for diagnosing a disease using an artificial intelligence model according to one embodiment. Hereinafter, with reference to FIG. 1, an example of a method for diagno