WO2023282500A1 - Procédé, appareil et programme pour l'étiquetage automatique des données de balayage de diapositive - Google Patents

Procédé, appareil et programme pour l'étiquetage automatique des données de balayage de diapositive Download PDF

Info

Publication number
WO2023282500A1
WO2023282500A1 PCT/KR2022/008759 KR2022008759W WO2023282500A1 WO 2023282500 A1 WO2023282500 A1 WO 2023282500A1 KR 2022008759 W KR2022008759 W KR 2022008759W WO 2023282500 A1 WO2023282500 A1 WO 2023282500A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
specimen
slide
scan data
printing
Prior art date
Application number
PCT/KR2022/008759
Other languages
English (en)
Korean (ko)
Inventor
김태정
Original Assignee
가톨릭대학교 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 가톨릭대학교 산학협력단 filed Critical 가톨릭대학교 산학협력단
Publication of WO2023282500A1 publication Critical patent/WO2023282500A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/20—Image preprocessing
    • G06V10/24—Aligning, centring, orientation detection or correction of the image
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/22—Character recognition characterised by the type of writing
    • G06V30/226—Character recognition characterised by the type of writing of cursive writing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/20—ICT specially adapted for the handling or processing of medical images for handling medical images, e.g. DICOM, HL7 or PACS
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H30/00—ICT specially adapted for the handling or processing of medical images
    • G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
    • G—PHYSICS
    • G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H70/00—ICT specially adapted for the handling or processing of medical references
    • G16H70/60—ICT specially adapted for the handling or processing of medical references relating to pathologies

Definitions

  • the present invention for solving the above problems is to recognize and classify a specimen image and a labeling image in a scanned image of a slide, and to recognize and classify a printing image and a handwriting image in a labeling image.
  • the present invention intends to construct a database by accurately separating management information of a printing image and a handwriting image using an artificial intelligence model.
  • FIG. 4 is a diagram illustrating classification of a scanned image of a slide according to a process.
  • each slide has samples collected, and a label printed with the name of the medical institution and the pathology number used in the medical institution is attached to the top, and it can be seen that there is a pathology number written by a person on it. .
  • the processor 110 learns an artificial intelligence model using a matching result of management information and a sample image built based on a plurality of slide recognition results.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Medical Informatics (AREA)
  • Epidemiology (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Public Health (AREA)
  • Multimedia (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Radiology & Medical Imaging (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)

Abstract

La présente invention concerne un procédé pour étiqueter automatiquement des données de balayage de diapositive, une image d'échantillon et une image d'étiquetage pouvant être reconnues et classées à partir d'une image de balayage d'une diapositive, une image d'impression et une image écrite pouvant être reconnues et classées à partir de l'image d'étiquetage, l'image d'impression et l'image écrite étant analysées, des informations de gestion respectives étant générées, et les informations de gestion respectives étant mises en correspondance avec l'image d'échantillon et stockées dans une base de données, exécutant ainsi la pathologie numérique.
PCT/KR2022/008759 2021-07-08 2022-06-21 Procédé, appareil et programme pour l'étiquetage automatique des données de balayage de diapositive WO2023282500A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2021-0089973 2021-07-08
KR1020210089973A KR102440919B1 (ko) 2021-07-08 2021-07-08 슬라이드 스캔 데이터의 자동 레이블링 방법, 장치 및 프로그램

Publications (1)

Publication Number Publication Date
WO2023282500A1 true WO2023282500A1 (fr) 2023-01-12

Family

ID=83281356

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2022/008759 WO2023282500A1 (fr) 2021-07-08 2022-06-21 Procédé, appareil et programme pour l'étiquetage automatique des données de balayage de diapositive

Country Status (2)

Country Link
KR (1) KR102440919B1 (fr)
WO (1) WO2023282500A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116364248B (zh) * 2023-03-15 2023-10-20 北京透彻未来科技有限公司 基于玻片标签自动识别技术的病理图像自动上传匹配方法

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR101452339B1 (ko) * 2013-12-30 2014-10-22 주식회사 세다스미디어 카세트 병리번호 인식과 슬라이드 자동 출력 방식을 이용한 인공지능 병리번호 매칭 시스템 및 방법
KR101550225B1 (ko) * 2014-04-04 2015-09-07 인하공업전문대학산학협력단 인공지능 병리 번호 인식 시스템 및 방법
US20200365241A1 (en) * 2013-02-20 2020-11-19 Leavitt Medical, Inc. Systems for managing biopsy specimens

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP5627698B2 (ja) 2009-10-19 2014-11-19 ベンタナ メディカル システムズ， インコーポレイテッド 撮像システムおよび技法
KR20200117222A (ko) * 2019-04-03 2020-10-14 서울대학교병원 병리 진단 지원 장치 및 방법
KR102236513B1 (ko) * 2019-05-24 2021-04-06 주식회사 필로시스 스캐닝 장치 및 이의 구동방법
KR102542037B1 (ko) * 2019-09-26 2023-06-12 주식회사 루닛 인공지능 모델을 사용 기관에 특화시키는 학습 방법, 이를 수행하는 장치

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20200365241A1 (en) * 2013-02-20 2020-11-19 Leavitt Medical, Inc. Systems for managing biopsy specimens
KR101452339B1 (ko) * 2013-12-30 2014-10-22 주식회사 세다스미디어 카세트 병리번호 인식과 슬라이드 자동 출력 방식을 이용한 인공지능 병리번호 매칭 시스템 및 방법
KR101550225B1 (ko) * 2014-04-04 2015-09-07 인하공업전문대학산학협력단 인공지능 병리 번호 인식 시스템 및 방법

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
ANONYMOUS: "Label extraction and AI for digital pathology", AVENTIOR INC., 17 June 2021 (2021-06-17), XP093021161, Retrieved from the Internet <URL:https://info-957.medium.com/label-extraction-and-ai-for-digital-pathology-d0ba644c1a9> [retrieved on 20230206] *
BELAD ABDEL, SANTOSH K C, POULAIN D'ANDECY VINCENT : "Handwritten and Printed Text Separation in Real Document", ARXIV: 1303.4614V1, 19 March 2013 (2013-03-19), XP093021159, Retrieved from the Internet <URL:https://arxiv.org/pdf/1303.4614v1.pdf> [retrieved on 20230206] *

Also Published As

Publication number Publication date
KR102440919B1 (ko) 2022-09-06

Similar Documents

Publication Publication Date Title
WO2017213398A1 (fr) Modèle d&#39;apprentissage pour détection de région faciale saillante
WO2018106005A1 (fr) Système de diagnostic d&#39;une maladie à l&#39;aide d&#39;un réseau neuronal et procédé associé
WO2019235828A1 (fr) Système de diagnostic de maladie à deux faces et méthode associée
WO2011096651A2 (fr) Procédé et dispositif d&#39;identification de visage
WO2023287064A1 (fr) Procédé et système de construction d&#39;une base de données d&#39;entraînement au moyen d&#39;une technologie de détection automatique de données anormales et d&#39;étiquetage automatique
WO2020096098A1 (fr) Procédé de gestion de travail d&#39;annotation et appareil et système le prenant en charge
WO2022145519A1 (fr) Procédé et dispositif de visualisation d&#39;électrocardiogramme à l&#39;aide d&#39;un apprentissage profond
WO2021194056A1 (fr) Procédé de formation d&#39;un réseau d&#39;apprentissage profond basé sur une intelligence artificielle et dispositif d&#39;apprentissage l&#39;utilisant
WO2023282500A1 (fr) Procédé, appareil et programme pour l&#39;étiquetage automatique des données de balayage de diapositive
WO2020111754A2 (fr) Procédé pour fournir un système de diagnostic utilisant l&#39;apprentissage semi-supervisé, et système de diagnostic l&#39;utilisant
WO2021230660A1 (fr) Procédé et appareil de génération automatique d&#39;un pool de travailleurs sur la base d&#39;éléments fonctionnels et de niveaux de difficulté de projets basés sur l&#39;externalisation ouverte
WO2020032559A2 (fr) Système et procédé de diagnostic de maladie à l&#39;aide d&#39;un réseau neuronal
WO2020101457A2 (fr) Procédé de diagnostic de consensus à base d&#39;apprentissage supervisé et système associé
WO2022114653A1 (fr) Système et procédé de calcul de limite de données
WO2020004749A1 (fr) Appareil et procédé permettant à un équipement d&#39;apprendre, à l&#39;aide d&#39;un fichier vidéo
WO2021225296A1 (fr) Procédé d&#39;apprentissage actif pouvant être expliqué, destiné à être utilisé pour un détecteur d&#39;objet, à l&#39;aide d&#39;un codeur profond et dispositif d&#39;apprentissage actif l&#39;utilisant
WO2022146050A1 (fr) Procédé et système d&#39;entraînement d&#39;intelligence artificielle fédéré pour le diagnostic de la dépression
WO2021133076A1 (fr) Procédé et dispositif de gestion du prix unitaire de travail d&#39;un projet basé sur l&#39;externalisation ouverte pour la génération de données d&#39;apprentissage d&#39;intelligence artificielle
WO2019194356A1 (fr) Dispositif électronique et son procédé de commande
WO2022158843A1 (fr) Procédé d&#39;affinage d&#39;image d&#39;échantillon de tissu, et système informatique le mettant en œuvre
WO2022211323A1 (fr) Procédé de reconnaissance d&#39;une disposition atypique d&#39;un document image
WO2022005111A1 (fr) Procédé d&#39;accord automatique d&#39;une prérogative d&#39;inspection à un ouvrier en fonction des résultats de tâches d&#39;un projet à production participative de génération de données d&#39;apprentissage d&#39;intelligence artificielle, appareil associé et programme informatique associé
WO2018088649A1 (fr) Procédé de détection de reflet
WO2021132831A1 (fr) Procédé permettant d&#39;augmenter ou de diminuer le nombre de travailleurs et d&#39;inspecteurs dans un projet basé sur une externalisation ouverte afin de créer des données d&#39;apprentissage d&#39;intelligence artificielle
WO2020256517A2 (fr) Procédé et système de traitement de mappage de phase automatique basés sur des informations d&#39;image omnidirectionnelle

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22837854

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE