KR20210134121A - System for gastric cancer risk prediction based-on gastroscopy image analtsis using artificial intelligence - Google Patents

System for gastric cancer risk prediction based-on gastroscopy image analtsis using artificial intelligence Download PDF

Info

Publication number
KR20210134121A
KR20210134121A KR1020200052393A KR20200052393A KR20210134121A KR 20210134121 A KR20210134121 A KR 20210134121A KR 1020200052393 A KR1020200052393 A KR 1020200052393A KR 20200052393 A KR20200052393 A KR 20200052393A KR 20210134121 A KR20210134121 A KR 20210134121A
Authority
KR
South Korea
Prior art keywords
gastric cancer
cancer risk
gastritis
disease
artificial intelligence
Prior art date
Application number
KR1020200052393A
Other languages
Korean (ko)
Inventor
문승대
고원진
Original Assignee
주식회사 아펙스에이아이
인하대학교 산학협력단
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 주식회사 아펙스에이아이, 인하대학교 산학협력단 filed Critical 주식회사 아펙스에이아이
Priority to KR1020200052393A priority Critical patent/KR20210134121A/en
Publication of KR20210134121A publication Critical patent/KR20210134121A/en

Links

Images

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/20ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for computer-aided diagnosis, e.g. based on medical expert systems
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/00002Operational features of endoscopes
    • A61B1/00004Operational features of endoscopes characterised by electronic signal processing
    • A61B1/00009Operational features of endoscopes characterised by electronic signal processing of image signals during a use of endoscope
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/273Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor for the upper alimentary canal, e.g. oesophagoscopes, gastroscopes
    • A61B1/2736Gastroscopes
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/42Detecting, measuring or recording for evaluating the gastrointestinal, the endocrine or the exocrine systems
    • A61B5/4222Evaluating particular parts, e.g. particular organs
    • A61B5/4238Evaluating particular parts, e.g. particular organs stomach
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00Measuring for diagnostic purposes; Identification of persons
    • A61B5/72Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7271Specific aspects of physiological measurement analysis
    • A61B5/7275Determining trends in physiological measurement data; Predicting development of a medical condition based on physiological measurements, e.g. determining a risk factor
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/30ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for calculating health indices; for individual health risk assessment
    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H50/00ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
    • G16H50/70ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics for mining of medical data, e.g. analysing previous cases of other patients
    • AHUMAN NECESSITIES
    • A61MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61BDIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B18/00Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body
    • A61B2018/00315Surgical instruments, devices or methods for transferring non-mechanical forms of energy to or from the body for treatment of particular body parts
    • A61B2018/00482Digestive system

Landscapes

  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Public Health (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Pathology (AREA)
  • Surgery (AREA)
  • Physics & Mathematics (AREA)
  • Biophysics (AREA)
  • Data Mining & Analysis (AREA)
  • Molecular Biology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Veterinary Medicine (AREA)
  • Animal Behavior & Ethology (AREA)
  • Primary Health Care (AREA)
  • Epidemiology (AREA)
  • Databases & Information Systems (AREA)
  • Optics & Photonics (AREA)
  • Gastroenterology & Hepatology (AREA)
  • Signal Processing (AREA)
  • Physiology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Endocrinology (AREA)
  • Psychiatry (AREA)
  • Theoretical Computer Science (AREA)
  • Computing Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computational Linguistics (AREA)
  • Apparatus For Radiation Diagnosis (AREA)
  • Measuring And Recording Apparatus For Diagnosis (AREA)

Abstract

The present invention relates to a gastric cancer risk prediction system based on gastroscopic image analysis using artificial intelligence. According to the present invention, a gastric cancer risk prediction system based on gastroscopy image analysis using artificial intelligence comprises: a disease image reading unit that uses artificial intelligence to diagnose the existence of superficial gastritis, atrophic gastritis, and intestinal metaplasia; a disease diagnosis unit that diagnoses Helicobacter pylori and reflux gastritis on the basis of the results of the disease image reading unit; and a final gastric cancer risk calculator that analyzes the results of the disease image reading unit and the disease diagnosis unit to generate final gastric cancer risk information. According to the present invention, artificial intelligence s used to perform gastroscopic image analysis, and thus the development degree and occurrence position of superficial gastritis, atrophic gastritis, and intestinal epithelial metaplasia are diagnosed. On the basis thereof, the diagnosis of Helicobacter infection and reflux esophagitis is performed. Thus, it is possible to quantitatively diagnose the risk of stomach cancer by calculating the total index of the final gastric cancer risk.

Description

인공지능을 이용한 위내시경 영상 분석 기반의 위암 위험성 예측 시스템{SYSTEM FOR GASTRIC CANCER RISK PREDICTION BASED-ON GASTROSCOPY IMAGE ANALTSIS USING ARTIFICIAL INTELLIGENCE}Gastric cancer risk prediction system based on gastroscopy image analysis using artificial intelligence

본 발명은 인공지능을 이용한 위내시경 영상 분석 기반의 위암 위험성 예측 시스템에 관한 것으로, 인공지능을 이용하여 위 내시경 영상을 분석하여 위암 위험성을 예측하는 인공지능을 이용한 위내시경 영상 분석 기반의 위암 위험성 예측 시스템에 관한 것이다.The present invention relates to a gastric cancer risk prediction system based on gastroscopy image analysis using artificial intelligence. It's about the system.

위암 발생은 위암 발생의 만성 위염과 같은 기저 질환이 성장 하여 위암으로 변형 되거나 기저 질환에 의하여 촉진 된다.The occurrence of gastric cancer is caused by the growth of an underlying disease such as chronic gastritis of gastric cancer, which is transformed into gastric cancer or promoted by the underlying disease.

인간의 몸을 구성하고 있는 가장 작은 단위인 세포는 정상적일 때 세포 내 조절기능에 의해 분열하며 성장하고 죽어 없어지기도 하면서 세포 수 균형을 유지한다. 어떤 원인으로 세포가 손상을 받는 경우, 치료를 받아 회복 하여 정상적인 세포로 역할을 하게 되지만, 회복이 안 된 경우는 스스로 죽게 된다.Cells, the smallest unit constituting the human body, divide and grow, die and disappear due to intracellular regulatory functions when normal, maintaining cell number balance. If a cell is damaged for any reason, it recovers through treatment and functions as a normal cell, but if it is not recovered, it dies by itself.

그러나 여러 가지 이유로 인해 이러한 증식과 억제가 조절되지 않는 비정상적인 세포들이 과다하게 증식할 뿐만 아니라 주위 조직 및 장 기에 침입하여 종괴 형성 및 정상 조직의 파괴를 초래하는 상태를 암(cancer)이라 정의한다. However, for various reasons, abnormal cells whose proliferation and inhibition are not controlled not only proliferate excessively, but also invade surrounding tissues and organs, resulting in mass formation and destruction of normal tissues, which is defined as cancer.

암은 이렇듯 억제 가 안 되는 세포의 증식으로, 정상적인 세포와 장기의 구조와 기능을 파괴하기에 그 진단과 치료의 중요성은 매우 중요하다. Cancer is the proliferation of cells that cannot be suppressed, and the importance of diagnosis and treatment is very important because it destroys the structure and function of normal cells and organs.

암은 세포가 무한히 증식해 정상적인 세포의 기능을 방해하는 질병으로, 폐암, 위암(gastric cancer, GC), 유방 암(breast cancer, BRC), 대장암(colorectal cancer, CRC) 등이 대표적이나, 실질적으로는 어느 조직에서나 발생할 수 있다.Cancer is a disease in which cells proliferate indefinitely and interfere with the function of normal cells. can occur in any organization.

초창기 암 진단은 암 세포의 성장에 따른 생체 조직의 외적 변화에 근거하였으나, 근래에 들어 혈액, 당쇄(glyco chain), DNA 등 생물의 조직 또는 세포에 존재하는 미량의 생체 분자를 이용한 진 단 및 검출이 시도되고 있다. 그러나 가장 보편적으로 사용되는 암 진단 방법은 생체 조직 검사를 통해 얻어진 조직 샘플을 이용하거나, 영상을 이용한 진단이다. Early cancer diagnosis was based on external changes in living tissue according to the growth of cancer cells, but in recent years, diagnosis and detection using trace amounts of biomolecules present in living tissues or cells, such as blood, glyco chain, and DNA. this is being tried However, the most commonly used cancer diagnosis method is a diagnosis using a tissue sample obtained through a biopsy or an image.

위암은 전 세계적으로 보면, 한국, 일본 등에서 많은 발생을 보이며 미국, 유럽 등의 서구에서는 발생률이 낮은 암이다. 한국의 경우 발생률 1위, 사망률은 폐암에 이어 2위를 차지하고 있다. 위암의 분류를 살펴보면 전체의 95%가 위벽의 점막의 샘세포에서 생기는 선암이다. 그 외 림프계에서 발생하는 림프종, 간질조직에서 발생하는 위장관 간질성 종양이 있다.Stomach cancer has a high incidence in Korea and Japan, and has a low incidence in Western countries such as the United States and Europe. In Korea, it ranks first in incidence and second in mortality after lung cancer. If you look at the classification of gastric cancer, 95% of all gastric cancers are adenocarcinomas arising from the gland cells of the mucous membrane of the stomach. Others include lymphoma originating in the lymphatic system and gastrointestinal interstitial tumor originating in interstitial tissue.

그 중 생체 조직 검사는 환자에게 큰 고통을 야기하며, 고비용이 들뿐만 아니라, 진단까지 긴 시간이 소요되는 단점이 있다. 또한, 환자가 실제 암에 걸린 경우, 생체 조직 검사 과정 중 암의 전이가 유발될 수 있는 위험이 있으며, 생체 조직 검사를 통해 조직 샘플을 얻을 수 없는 부위의 경우, 외과적인 수술을 통해 의심되는 조직의 적출이 이루어지기 전에는 질병의 진단이 불가능한 단점이 있다.Among them, biopsy has disadvantages in that it causes great pain to the patient, is expensive, and takes a long time to diagnose. In addition, if the patient has actual cancer, there is a risk that cancer metastasis may be induced during the biopsy process. There is a disadvantage that it is impossible to diagnose the disease until the extraction of the disease is made.

영상을 이용한 진단에서는 엑스레이(X-ray) 영상, 질병 표적 물질이 부착된 조영제를 사용하여 획득한 핵자기공명(nuclear magnetic resonance, NMR) 영상 등을 기반으로 암을 판정한다. In the diagnosis using images, cancer is determined based on an X-ray image or a nuclear magnetic resonance (NMR) image obtained using a contrast agent to which a disease target material is attached.

그러나 이러한 영상 진단은 임상의 또는 판독의의 숙련도에 따라 오진의 가능성이 있으며, 영상을 얻는 기기의 정밀도에 크게 의존하는 단점이 있다. However, such imaging diagnosis has a disadvantage in that there is a possibility of a misdiagnosis depending on the skill level of a clinician or an interpreter, and it largely depends on the precision of an image acquisition device.

더 나아가, 가장 정밀한 기기조차도 수 mm 이하의 종양은 검출이 불가능하여, 발병 초기 단계에서는 검출이 어려운 단점이 있으며, 영상을 얻기 위해 환자 또는 질병 보유 가능자가 유전자의 돌연변이를 유발할 수 있는 고에너지의 전자기파에 노출되므로, 또 다른 질병을 야기할 수 있을 뿐만 아니라, 영상을 통한 진단 횟수에 제한이 있는 단점이 있다. Furthermore, even the most precise instruments cannot detect tumors of several millimeters or smaller, so it is difficult to detect in the early stages of the disease. Because it is exposed to , it may cause another disease, and there is a disadvantage in that the number of diagnosis through images is limited.

조기 위암(ECG)의 대부분은 임상 증상이나 징후가 없으므로 스크리닝 전략없이 적시에 탐지하고 치료하기 어려운 문제점이 발생한다. 더불어 위의 이형성증과 같은 전암성병변을 가진 환자는 위암에 걸릴 상당한 위험이 있다. Since most of the early gastric cancer (ECG) has no clinical symptoms or signs, it is difficult to detect and treat in a timely manner without a screening strategy. In addition, patients with precancerous lesions such as gastric dysplasia are at a significant risk for gastric cancer.

기존의 위에 발생한 신생물은 의사가 위내시경을 통해 내시경 이미지에 포함된 위 내부의 형태 및 크기를 감안 하여 위암 여부를 일차적으로 판단하고, 조직검사로 확진을 내렸다. For neoplasms in the existing stomach, the doctor first judged the presence of gastric cancer through a gastroscopy, taking into account the shape and size of the stomach included in the endoscopic image, and confirmed the diagnosis by biopsy.

그러나, 이 방법은 의사마다 경험이 달라 진단을 다르게 내릴 수 있으며, 의사가 없는 지역에서는 정확한 진단이 이루어질 수 없는 문제점이 발생하며, 내시경 장치를 통해 획득된 비정상적인 병변의 발견은 일반적으로 병변의 이상 형태나 점막의 색 변화에 따라 결정되며, 진단 정확도는 훈련 및 광학 기술 및 chromoendoscopy으로 개선되는 것으로 알려졌다. However, this method can make different diagnoses due to different doctors' experiences, and there is a problem that an accurate diagnosis cannot be made in an area without a doctor. It is determined by the color change of the mucous membrane, and the diagnostic accuracy is known to be improved with training and optical techniques and chromoendoscopy.

따라서, 위 내시경 영상을 이용하여 위암의 위험성에 대한 지수를 산출할 수 있는 방법이 필요하게 되었다.Therefore, there is a need for a method capable of calculating an index for the risk of gastric cancer using an endoscopy image.

본 발명의 배경이 되는 기술은 대한민국 공개특허 제10-2020-0038120호(2020.04.10. 공개)에 개시되어 있다. The technology that is the background of the present invention is disclosed in Korean Patent Laid-Open No. 10-2020-0038120 (published on April 10, 2020).

본 발명이 이루고자 하는 기술적 과제는 인공지능을 이용하여 위 내시경 영상을 분석하여 위암 위험성을 예측하는 인공지능에 이용한 위내시경 영상 분석을 통한 위암 위험성 예측 시스템을 제공하기 위한 것이다.An object of the present invention is to provide a gastric cancer risk prediction system through gastroscopy image analysis used for artificial intelligence to predict gastric cancer risk by analyzing a gastroscopic image using artificial intelligence.

이러한 기술적 과제를 이루기 위한 본 발명의 실시예에 따르면, 인공지능을 이용한 위내시경 영상 분석 기반의 위암 위험성 예측 시스템에 있어서, 인공지능을 이용하여 표재성 위염, 위축성 위염, 장상피화생의 발명 유무를 진단하는 질환 영상 판독부, 질환 영상 판독부의 결과를 기반으로 헬리코 박터, 역류성 위염을 진단하는 질환 진단부, 질환 영상 판독부와 질환 진단부의 결과를 분석하여 최종의 위암 위험도 정보를 생성하는 최종 위암 위험성 산출부를 포함한다.According to an embodiment of the present invention for achieving this technical task, in the gastric cancer risk prediction system based on gastroendoscopic image analysis using artificial intelligence, the existence of superficial gastritis, atrophic gastritis, and intestinal metaplasia is diagnosed using artificial intelligence. The disease image reading unit that analyzes the results of the disease image reading unit, the disease diagnosis unit that diagnoses Helicobacter pylori, gastritis reflux based on the results of the disease image reader, and the final gastric cancer risk that generates the final gastric cancer risk information by analyzing the results of the disease image reading unit and the disease diagnosis unit Includes output.

상기 질환 영상 판독부는, 상기 인공지능에 의한 위내시경 영상 분석을 하여 표재성 위염, 위축성 위염, 장상피화생의 발생 유무, 발생 위치, 발생 부위의 크기, 색깔, 구조를 판독할 수 있다.The disease image reading unit may analyze the gastroscopic image by the artificial intelligence to read the presence or absence of superficial gastritis, atrophic gastritis, and intestinal metaplasia, the location of occurrence, the size, color, and structure of the site of occurrence.

상기 질환 진단부는, 상기 질환 영상 판독부의 결과를 분석하여 복수의 질환의 관계를 분석하여 사전에 정의된 표에 의하여 헬리코박터, 역류성 위염을 진단할 수 있다.The disease diagnosis unit may analyze a result of the disease image reading unit to analyze a relationship between a plurality of diseases to diagnose Helicobacter pylori and gastritis reflux according to a predefined table.

상기 위암 위험성 산출부는, 상기 표재성 위염, 위축성 위염, 장상피화생, 헬리코박터 및 역류성 위염 각각에 대한 총 위험도를 산출하고, 산출된 총 위험도의 합으로 최종 위암 위험성을 예측할 수 있다.The gastric cancer risk calculation unit calculates the total risk for each of the superficial gastritis, atrophic gastritis, intestinal metaplasia, Helicobacter pylori and reflux gastritis, and can predict the final gastric cancer risk by the sum of the calculated total risks.

이와 같이 본 발명에 따르면, 인공지능을 이용하여 위 내시경 영상 분석을 수행하여 표재성 위염, 위축성 위염, 장상피화생에 대한 진단과 발달정도, 발병 위치를 진단하며 이를 근거로 헬리코박터 감염, 역류성 식도염의 진단을 수행하기 때문에 최종 위암 위험성의 총 지수를 산출 하여 위암 위험성을 정량적으로 진단할 수 있다.As described above, according to the present invention, the diagnosis of superficial gastritis, atrophic gastritis, and intestinal epithelial metaplasia by performing gastroendoscopic image analysis using artificial intelligence, the degree of development, and the location of the onset are diagnosed, and based on this, the diagnosis of Helicobacter pylori infection and reflux esophagitis Therefore, it is possible to quantitatively diagnose the risk of gastric cancer by calculating the total index of the final gastric cancer risk.

도 1은 본 발명의 실시예에 따른 위암 위험성 예측 시스템을 설명하기 위한 도면이다.1 is a view for explaining a gastric cancer risk prediction system according to an embodiment of the present invention.

아래에서는 첨부한 도면을 참조하여 본 발명이 속하는 기술 분야에서 통상의 지식을 가진 자가 용이하게 실시할 수 있도록 본 발명의 실시 예를 상세히 설명한다. 그러나 본 발명은 여러 가지 상이한 형태로 구현될 수 있으며 여기에서 설명하는 실시예에 한정되지 않는다. 그리고 도면에서 본 발명을 명확하게 설명하기 위해서 설명과 관계없는 부분은 생략하였으며 명세서 전체를 통하여 유사한 부분에 대해서는 유사한 도면 부호를 붙였다.Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily carry out the present invention. However, the present invention may be embodied in many different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

명세서 전체에서, 어떤 부분이 어떤 구성요소를 "포함"한다고 할 때, 이는 특별히 반대되는 기재가 없는 한 다른 구성요소를 제외하는 것이 아니라 다른 구성요소를 더 포함할 수 있는 것을 의미한다.Throughout the specification, when a part "includes" a certain element, it means that other elements may be further included, rather than excluding other elements, unless otherwise stated.

그러면 첨부한 도면을 참고로 하여 본 발명의 실시 예에 대하여 본 발명이 속하는 기술 분야에서 통상의 지식을 가진 자가 용이하게 실시할 수 있도록 상세히 설명한다.Then, with reference to the accompanying drawings, embodiments of the present invention will be described in detail so that those of ordinary skill in the art to which the present invention pertains can easily implement them.

도 1을 이용하여 본 발명의 실시예에 따른 위암 위험성 예측 시스템을 설명한다.A gastric cancer risk prediction system according to an embodiment of the present invention will be described with reference to FIG. 1 .

도 1은 본 발명의 실시예에 따른 위암 위험성 예측 시스템을 설명하기 위한 도면이다.1 is a view for explaining a gastric cancer risk prediction system according to an embodiment of the present invention.

도 1에서 나타낸 것처럼, 위암 위험성 예측 시스템(100)은 질환 영상 판독부(100), 질환 진단부(200) 및 위암 위험성 산출부(300)를 포함한다.As shown in FIG. 1 , the gastric cancer risk prediction system 100 includes a disease image reading unit 100 , a disease diagnosis unit 200 , and a gastric cancer risk calculation unit 300 .

먼저, 질환 영상 판독부(100)는 위 내시경을 촬영한 측정 대상자의 복수개의 위 내시경 영상을 획득한다.First, the disease image reading unit 100 acquires a plurality of gastroendoscopic images of a subject who has taken a gastroscope.

여기서, 복수의 위 내시경 영상은 위의 9개의 위치(전정부 소만부, 전정부 대만부, 위각부, 몸체부 소만부 중하부, 몸체부 대만부 중하부, 몸체부 소만부 상부, 몸체부 대만부 상부, 들문(Cardia), 위바닥(Fundus)에 해당하는 영상이다.Here, a plurality of gastroscopy images are shown in 9 positions of the stomach (the vestibular small portion, the vestibular large portion, the gastrocnemius portion, the body small portion mid-lower portion, the body portion large portion mid-lower portion, the body small portion upper portion, the body portion Taiwan This is an image corresponding to the upper part, the cardia, and the upper floor (Fundus).

그리고, 질환 영상 판독부(100)는 획득한 복수개의 위 내시경 영상을 인공지능에 적용하여 표재성 위염, 위축성 위염 및 장상피화생의 발생 유무를 판단한다.In addition, the disease image reading unit 100 determines the occurrence of superficial gastritis, atrophic gastritis and intestinal epithelial metaplasia by applying the acquired plurality of gastroscopic images to artificial intelligence.

그리고, 질환 영상 판독부(100)는 표재성 위염, 위축성 위염 및 장상피화생의 각각의 발생 위치, 크기, 색깔 및 표면의 구조를 분석하여 표제성 위염의 위험 지수, 위축성 위염의 위험 지수 및 장상피화생의 위험 지수를 추출한다.In addition, the disease image reading unit 100 analyzes the location, size, color, and surface structure of each occurrence of superficial gastritis, atrophic gastritis and intestinal epithelial metaplasia, and the risk index of superficial gastritis, the risk index of atrophic gastritis and intestinal epithelialization Extract the life risk index.

다음으로, 질환 진단부(200)는 인공지능으로 분석된 영상을 이용하여 헬리코박터 감염여부 및 역류성 식도염을 진단한다.Next, the disease diagnosis unit 200 diagnoses Helicobacter pylori infection and reflux esophagitis using the image analyzed by artificial intelligence.

이때, 질환 진단부(200)는 헬리코박터 및 역류성 식도염 각각의 위험 지수를 추출한다.At this time, the disease diagnosis unit 200 extracts each risk index of Helicobacter pylori and reflux esophagitis.

다음으로, 위암 위험성 산출부(300)는 질환 영상 판독부(100)와 질환 진단부(200)로부터 추출된 위험 지수를 분석하여 최종 위암 위험도를 추출한다.Next, the gastric cancer risk calculation unit 300 extracts the final gastric cancer risk by analyzing the risk index extracted from the disease image reading unit 100 and the disease diagnosis unit 200 .

도 1에서 나타낸 것처럼, 위암 위험성 산출부(300)는 각각의 표재성 위염, 위축성 위염 및 장상피화생, 헬리코박터 감염여부 및 역류성 식도염의 발달 단계에 따른 위험도와 발병 위치에 따른 위험도를 각각 산출한다.As shown in FIG. 1 , the gastric cancer risk calculator 300 calculates the risk according to the developmental stage of each superficial gastritis, atrophic gastritis and intestinal epithelial metaplasia, Helicobacter infection, and reflux esophagitis and the risk according to the location of the onset, respectively.

예를 들어, 표제성 위염의 위험 지수를 a1이고, 발달 단계에 따른 표제성 위염의 위험 지수를 a2, 발병 위치에 따른 위험 지수를 a3라고 하면, 표제성 위염에 대한 총 위험도는 a1, a2 및 a3를 곱한 값인 x1으로 연산된다.For example, if the risk index for head gastritis is a1, the risk index for head gastritis according to the developmental stage is a2, and the risk index according to the location of onset is a3, then the total risk for head gastritis is a1, a2 and It is calculated as x1, which is a value multiplied by a3.

또한, 위암 위험성 산출부(300)는 위축성 위염에 대한 총 위험도, 장상피화생에 대한 총 위험도 및 역류성 식도염에 대한 총 위험도도 표제성 위염에 대한 총 위험도를 연산한 방법을 이용하여 각각 연산한다.In addition, the gastric cancer risk calculator 300 calculates the total risk for atrophic gastritis, the total risk for intestinal epithelial metaplasia, and the total risk for reflux esophagitis, respectively, using a method of calculating the total risk for title gastritis.

이와 달리, 헬리코박터에 대한 총 위험도는 감염여부에 따라 0 또는 1을 헬리코박터 위험 지수에 곱하여 연산된다.In contrast, the total risk for Helicobacter is calculated by multiplying the Helicobacter risk index by 0 or 1 depending on whether or not the infection is present.

그러면, 도 1에서 나타낸 것처럼, 위암 위험성 산출부(300)는 표제성 위염에 대한 총 위험도, 위축성 위염에 대한 총 위험도, 장상피화생에 대한 총 위험도 및 역류성 식도염에 대한 총 위험도 및 헬리코박터에 대한 총 위험도를 합산하여 위암 위험성의 총 지수를 연산한다.Then, as shown in FIG. 1 , the gastric cancer risk calculation unit 300 calculates the total risk for title gastritis, the total risk for atrophic gastritis, the total risk for intestinal epithelial metaplasia and the total risk for reflux esophagitis and the total risk for Helicobacter pylori. By summing the risks, the total index of gastric cancer risk is calculated.

이와 같이 본 발명의 실시예에 따르면, 인공지능을 이용하여 위 내시경 영상 분석을 수행하여 표재성 위염, 위축성 위염, 장상피화생에 대한 진단과 발달정도, 발병 위치를 진단하며 이를 근거로 헬리코박터 감염, 역류성 식도염의 진단을 수행하기 때문에 최종 위암 위험성의 총 지수를 산출 하여 위암 위험성을 정량적으로 진단할 수 있다.As described above, according to an embodiment of the present invention, gastroendoscopic image analysis is performed using artificial intelligence to diagnose superficial gastritis, atrophic gastritis, and intestinal metaplasia, the degree of development, and the location of the onset. Based on this, Helicobacter infection, reflux Since the diagnosis of esophagitis is performed, the risk of gastric cancer can be quantitatively diagnosed by calculating the total index of the final gastric cancer risk.

본 발명은 도면에 도시된 실시 예를 참고로 설명 되었으나 이는 예시적인 것이 불과하며, 본 기술 분야의 통상의 지식을 가진 자라면 이로부터 다양한 변형 및 균등한 다른 실시 예가 가능하다는 점을 이해할 것이다. 따라서, 본 발명의 진정한 기술적 보호 범위는 첨부된 특허청구범위의 기술적 사상에 의하여 정해져야 할 것이다.Although the present invention has been described with reference to the embodiment shown in the drawings, which is merely exemplary, those skilled in the art will understand that various modifications and equivalent other embodiments are possible therefrom. Accordingly, the true technical protection scope of the present invention should be determined by the technical spirit of the appended claims.

100: 질환 영상 판독부, 200: 질환 진단부,
300: 위암 위험성 산출부
100: disease image reading unit, 200: disease diagnosis unit,
300: stomach cancer risk calculator

Claims (4)

인공지능을 이용한 위내시경 영상 분석 기반의 위암 위험성 예측 시스템에 있어서,
인공지능을 이용하여 표재성 위염, 위축성 위염, 장상피화생의 발명 유무를 진단하는 질환 영상 판독부,
질환 영상 판독부의 결과를 기반으로 헬리코박터, 역류성 위염을 진단하는 질환 진단부,
질환 영상 판독부와 질환 진단부의 결과를 분석하여 최종의 위암 위험도 정보를 생성하는 최종 위암 위험성 산출부를 포함하는 위암 위험성 예측 시스템.
In the gastric cancer risk prediction system based on gastroscopy image analysis using artificial intelligence,
A disease image reading unit that uses artificial intelligence to diagnose the presence of superficial gastritis, atrophic gastritis, and intestinal metaplasia;
Disease diagnosis unit that diagnoses Helicobacter pylori, gastritis reflux based on the results of the disease image reading unit;
A gastric cancer risk prediction system including a final gastric cancer risk calculator that analyzes the results of the disease image reading unit and the disease diagnosis unit to generate final gastric cancer risk information.
제1항에 있어서,
상기 질환 영상 판독부는,
상기 인공지능에 의한 위내시경 영상 분석을 하여 표재성 위염, 위축성 위염, 장상피화생의 발생 유무, 발생 위치, 발생 부위의 크기, 색깔, 구조를 판독하는 위암 위험성 예측 시스템.
According to claim 1,
The disease image reading unit,
A gastric cancer risk prediction system that analyzes the gastroscopic image by the artificial intelligence to read the presence or absence of superficial gastritis, atrophic gastritis, and intestinal metaplasia, the location of occurrence, the size, color, and structure of the site of occurrence.
제2항에 있어서,
상기 질환 진단부는,
상기 질환 영상 판독부의 결과를 분석하여 복수의 질환의 관계를 분석하여 사전에 정의된 표에 의하여 헬리코박터, 역류성 위염을 진단하는 위암 위험성 예측 시스템.
3. The method of claim 2,
The disease diagnosis unit,
A gastric cancer risk prediction system for diagnosing Helicobacter pylori and reflux gastritis according to a predefined table by analyzing the results of the disease image reading unit to analyze the relationship between a plurality of diseases.
제2항에 있어서,
상기 위암 위험성 산출부는,
상기 표재성 위염, 위축성 위염, 장상피화생, 헬리코박터 및 역류성 위염 각각에 대한 총 위험도를 산출하고, 산출된 총 위험도의 합으로 최종 위암 위험성을 예측하는 위암 위험성 예측 시스템.
3. The method of claim 2,
The stomach cancer risk calculation unit,
A gastric cancer risk prediction system that calculates the total risk for each of the superficial gastritis, atrophic gastritis, intestinal metaplasia, Helicobacter pylori, and gastritis reflux, and predicts the final gastric cancer risk by the sum of the calculated total risks.
KR1020200052393A 2020-04-29 2020-04-29 System for gastric cancer risk prediction based-on gastroscopy image analtsis using artificial intelligence KR20210134121A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020200052393A KR20210134121A (en) 2020-04-29 2020-04-29 System for gastric cancer risk prediction based-on gastroscopy image analtsis using artificial intelligence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020200052393A KR20210134121A (en) 2020-04-29 2020-04-29 System for gastric cancer risk prediction based-on gastroscopy image analtsis using artificial intelligence

Publications (1)

Publication Number Publication Date
KR20210134121A true KR20210134121A (en) 2021-11-09

Family

ID=78487071

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020200052393A KR20210134121A (en) 2020-04-29 2020-04-29 System for gastric cancer risk prediction based-on gastroscopy image analtsis using artificial intelligence

Country Status (1)

Country Link
KR (1) KR20210134121A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102572544B1 (en) * 2022-12-01 2023-08-30 프리베노틱스 주식회사 An electronic device for providing information of a plurality of lesions by analyzing an endoscopic image, and an endoscopy system including the electronic device
CN117238532A (en) * 2023-11-10 2023-12-15 武汉楚精灵医疗科技有限公司 Intelligent follow-up method and device

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102572544B1 (en) * 2022-12-01 2023-08-30 프리베노틱스 주식회사 An electronic device for providing information of a plurality of lesions by analyzing an endoscopic image, and an endoscopy system including the electronic device
CN117238532A (en) * 2023-11-10 2023-12-15 武汉楚精灵医疗科技有限公司 Intelligent follow-up method and device
CN117238532B (en) * 2023-11-10 2024-01-30 武汉楚精灵医疗科技有限公司 Intelligent follow-up method and device

Similar Documents

Publication Publication Date Title
KR102210806B1 (en) Apparatus and method for diagnosing gastric lesion using deep learning of endoscopic images
JP7037220B2 (en) A computer-readable recording medium that stores a disease diagnosis support system using endoscopic images of the digestive organs, a method of operating the diagnosis support system, a diagnosis support program, and this diagnosis support program.
JP7017198B2 (en) A computer-readable recording medium that stores a disease diagnosis support method, diagnosis support system, diagnosis support program, and this diagnosis support program using endoscopic images of the digestive organs.
US11270433B2 (en) Disease diagnosis support method employing endoscopic images of a digestive organ, a diagnosis support system, a diagnosis support program and a computer-readable recording medium having the diagnosis support program stored therein
EP3811845A1 (en) Method of assisting disease diagnosis based on endoscope image of digestive organ, diagnosis assistance system, diagnosis assistance program, and computer-readable recording medium having said diagnosis assistance program stored thereon
US7819824B2 (en) Method and a dual-array transducer probe for real time mechanical imaging of prostate
US7922674B2 (en) Method and device for real time mechanical imaging of prostate
KR102168485B1 (en) Endoscopic device and method for diagnosing gastric lesion based on gastric endoscopic image obtained in real time
WO2021054477A2 (en) Disease diagnostic support method using endoscopic image of digestive system, diagnostic support system, diagnostic support program, and computer-readable recording medium having said diagnostic support program stored therein
KR20210134121A (en) System for gastric cancer risk prediction based-on gastroscopy image analtsis using artificial intelligence
Penna et al. A technique for blood detection in wireless capsule endoscopy images
US20230301503A1 (en) Artificial intelligence-based gastroscopic image analysis method
Zhu et al. The diagnostic value of narrow-band imaging for early and invasive lung cancer: a meta-analysis
KR20230097646A (en) Artificial intelligence-based gastroscopy diagnosis supporting system and method to improve gastro polyp and cancer detection rate
KR20210016171A (en) The method of providing disease information using medical image
KR20220121956A (en) System for digestive cancer risk prediction based-on digestive image analtsis using artificial intelligence
JP7441452B2 (en) Training data generation method, learned model generation method, and disease onset prediction method
KR20220121957A (en) System for esophageal cancer risk prediction based-on endoscope image analtsis using artificial intelligence
KR20220121955A (en) System for colorectal cancer risk prediction based-on colonoscopy image analtsis using artificial intelligence
Na et al. Detection and Identification of Pancreatic Cancer Using Probabilistic Neural Network
VENKATESWARLU et al. A CONTEMPORARY TECHNIQUE FOR LUNG DISEASE PREDICTION USING AND DL AND ML
Geraats Optical Innovations in Endobronchial Diagnostics
MALLIGA et al. A CONTEMPORARY TECHNIQUE FOR LUNG DISEASE PREDICTION USING MACHINE LEARNING
Kim et al. S1385 Impact of Race and Ethnicity on Risks of Cardia and Non-Cardia Gastric Adenocarcinomas in the US, 2000-2019: A Large Single-Center Retrospective Cohort Study
KR101106584B1 (en) Disease Diagnosis Apparatus, Marker Screening Method and Marker Using TOF-SIMS