[go: up one dir, main page]

WO2020255290A1 - Procédé d'analyse d'image d'organe et procédé d'apprentissage - Google Patents

Procédé d'analyse d'image d'organe et procédé d'apprentissage Download PDF

Info

Publication number
WO2020255290A1
WO2020255290A1 PCT/JP2019/024259 JP2019024259W WO2020255290A1 WO 2020255290 A1 WO2020255290 A1 WO 2020255290A1 JP 2019024259 W JP2019024259 W JP 2019024259W WO 2020255290 A1 WO2020255290 A1 WO 2020255290A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
learning
organ
femur
images
Prior art date
Legal status (The legal status 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 status listed.)
Ceased
Application number
PCT/JP2019/024259
Other languages
English (en)
Japanese (ja)
Inventor
翔太 押川
▲高▼橋　渉
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shimadzu Corp
Original Assignee
Shimadzu Corp
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 Shimadzu Corp filed Critical Shimadzu Corp
Priority to PCT/JP2019/024259 priority Critical patent/WO2020255290A1/fr
Publication of WO2020255290A1 publication Critical patent/WO2020255290A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B6/00—Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment

Definitions

  • the X-ray irradiation unit 1 irradiates the subject T with X-rays.
  • the X-ray detection unit 2 detects the X-rays emitted from the X-ray irradiation unit 1 to the subject T.
  • the X-ray apparatus 100 calculates (measures) the circularity of the head 303 (see FIG. 10) of the femur 300 (see FIG. 2) of the subject T and calculates the bone density of the femur 300 of the subject T, for example. Used for (measurement).
  • the machine learning in step 103 includes a plurality of label images 40 (see FIG. 5) and a plurality of learning input images 20 (a plurality of learning images 21 and a plurality of learning inverted images 23) (see FIG. 4).
  • the correct answer information 301a (see FIG. 5) among the plurality of label images 40 is used.
  • the pelvis image 301b is an example of the "adjacent bone image" in the claims.
  • the femur image 300b corresponding to the femur 300 is extracted on the inverted photographed image 10c in which the left bone region A is horizontally inverted.
  • the pelvis image 301b corresponding to the pelvis 301 is extracted on the inverted photographed image 10c in which the left bone region A is horizontally inverted.
  • the member image 302b corresponding to the member 302 is extracted on the inverted photographed image 10c in which the left bone region A is horizontally inverted.
  • a step of performing a first machine learning for extracting a femur image 300b corresponding to 300 is provided. Further, the organ image analysis method includes a step of extracting a femur image 300b on the captured image 10 based on the learning result of the first machine learning. As a result, the femur image 300b corresponding to the femur 300 can be individually extracted on the captured image 10 based on the learning result of the first machine learning. As a result, since the femur image 300b can be analyzed based on the individually extracted images, it is possible to facilitate the selection of only the femur 300 as the analysis target.
  • the learning method acquires a plurality of learning input images 20 in which the bone region A including the femur 300 and the pelvis 301 adjacent to the femur 300 is displayed. It includes a step and a step of acquiring a plurality of label images 40 including correct answer information 300a at a position where the femur 300 is displayed in each of the plurality of learning input images 20. Further, in the above learning method, the femur 300 is photographed by the X-ray imaging apparatus 100 using the plurality of label images 40 and the plurality of input images 20 for learning, and the femur 300 is displayed on the captured image 10 in which the bone region A is displayed.
  • the step of acquiring the plurality of learning input images is a step of acquiring the plurality of learning input images in which members other than the bone portion embedded in the bone portion region are displayed.
  • a step of performing a third machine learning for extracting a member image corresponding to the member on the first captured image by using the plurality of member label images and the plurality of learning input images, and A step of extracting the member image on the first captured image based on the learning result of the third machine learning is further provided.
  • the modified femur label image and the plurality of first captured images were taken by the X-ray apparatus, and on the second captured image in which the bone region was displayed, the femur was formed.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Medical Informatics (AREA)
  • Engineering & Computer Science (AREA)
  • Radiology & Medical Imaging (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Optics & Photonics (AREA)
  • Pathology (AREA)
  • Physics & Mathematics (AREA)
  • High Energy & Nuclear Physics (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Image Analysis (AREA)

Abstract

L'invention concerne un procédé d'analyse d'image d'organe qui consiste à : effectuer un premier apprentissage machine à l'aide d'une pluralité de premières images de marqueur d'organe (40) comprenant des informations de réponse correcte (300a) pour la position à laquelle un premier organe (300) est affiché sur chacune d'une pluralité d'images d'entrée d'apprentissage (20) ; et extraire une première image d'organe (300b) sur une première image capturée (10) sur la base du résultat d'apprentissage du premier apprentissage machine.
PCT/JP2019/024259 2019-06-19 2019-06-19 Procédé d'analyse d'image d'organe et procédé d'apprentissage Ceased WO2020255290A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/JP2019/024259 WO2020255290A1 (fr) 2019-06-19 2019-06-19 Procédé d'analyse d'image d'organe et procédé d'apprentissage

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2019/024259 WO2020255290A1 (fr) 2019-06-19 2019-06-19 Procédé d'analyse d'image d'organe et procédé d'apprentissage

Publications (1)

Publication Number Publication Date
WO2020255290A1 true WO2020255290A1 (fr) 2020-12-24

Family

ID=74037003

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2019/024259 Ceased WO2020255290A1 (fr) 2019-06-19 2019-06-19 Procédé d'analyse d'image d'organe et procédé d'apprentissage

Country Status (1)

Country Link
WO (1) WO2020255290A1 (fr)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH03102477A (ja) * 1989-06-26 1991-04-26 Fuji Photo Film Co Ltd 放射線画像処理装置
JP2000033082A (ja) * 1998-07-17 2000-02-02 Konica Corp 放射線画像の画像処理装置
JP2009515594A (ja) * 2005-11-11 2009-04-16 ホロジック， インコーポレイテッド 三次元骨密度モデルを使用して将来の骨折の危険性の推定
JP2013533765A (ja) * 2010-06-16 2013-08-29 エーツー・サージカル 骨の３ｄ医用画像から幾何学的要素を自動的に判定する方法およびシステム
JP2015530193A (ja) * 2012-09-27 2015-10-15 シーメンス プロダクト ライフサイクル マネージメント ソフトウェアー インコーポレイテッドＳｉｅｍｅｎｓ Ｐｒｏｄｕｃｔ Ｌｉｆｅｃｙｃｌｅ Ｍａｎａｇｅｍｅｎｔ Ｓｏｆｔｗａｒｅ Ｉｎｃ． ３ｄコンピュータ断層撮影のための複数の骨のセグメンテーション
JP2019016279A (ja) * 2017-07-10 2019-01-31 株式会社三菱総合研究所 情報処理装置及び情報処理方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH03102477A (ja) * 1989-06-26 1991-04-26 Fuji Photo Film Co Ltd 放射線画像処理装置
JP2000033082A (ja) * 1998-07-17 2000-02-02 Konica Corp 放射線画像の画像処理装置
JP2009515594A (ja) * 2005-11-11 2009-04-16 ホロジック， インコーポレイテッド 三次元骨密度モデルを使用して将来の骨折の危険性の推定
JP2013533765A (ja) * 2010-06-16 2013-08-29 エーツー・サージカル 骨の３ｄ医用画像から幾何学的要素を自動的に判定する方法およびシステム
JP2015530193A (ja) * 2012-09-27 2015-10-15 シーメンス プロダクト ライフサイクル マネージメント ソフトウェアー インコーポレイテッドＳｉｅｍｅｎｓ Ｐｒｏｄｕｃｔ Ｌｉｆｅｃｙｃｌｅ Ｍａｎａｇｅｍｅｎｔ Ｓｏｆｔｗａｒｅ Ｉｎｃ． ３ｄコンピュータ断層撮影のための複数の骨のセグメンテーション
JP2019016279A (ja) * 2017-07-10 2019-01-31 株式会社三菱総合研究所 情報処理装置及び情報処理方法

Similar Documents

Publication Publication Date Title
CN112165900B (zh) 图像解析方法、分割方法、骨密度测量方法、学习模型生成方法和图像生成装置
EP2250965B1 (fr) Procédé d'acquisition d'images, dispositif et système de radiographie
KR20170125599A (ko) 치과용 3차원 데이터 처리장치 및 그 방법
JP2017507689A (ja) 少なくとも１つの解剖学的構造の３ｄ参照コンピュータモデルを生成するための方法
Kim et al. 3D reconstruction of leg bones from X-ray images using CNN-based feature analysis
CN106793983A (zh) X射线摄影装置
US12364877B2 (en) Medical image processing device, storage medium, medical device, and treatment system
KR20210028559A (ko) 화상 해석 방법, 화상 처리 장치, 골밀도 측정 장치 및 학습 모델의 작성 방법
US20220148180A1 (en) Medical image processing device, storage medium, medical device, and treatment system
US12026927B2 (en) Learning device, learning method, learning program, trained model, radiographic image processing device, radiographic image processing method, and radiographic image processing program
JP4416823B2 (ja) 画像処理装置、画像処理方法、及びコンピュータプログラム
CN112438744A (zh) 骨密度测定装置和骨密度测定方法
WO2020255290A1 (fr) Procédé d'analyse d'image d'organe et procédé d'apprentissage
KR102394444B1 (ko) 듀얼 에너지 단층촬영 장치, 및 이를 이용한 금속 이미지 구분 방법
JP2019208832A (ja) 歯科分析システムおよび歯科分析ｘ線システム
US20240221111A1 (en) Stitching multiple images to create a panoramic image
KR102744021B1 (ko) 골부 화상 해석 방법 및 학습 방법
WO2023195443A1 (fr) Dispositif de traitement d'image, procédé d'exploitation de dispositif de traitement d'image, et programme
US11937970B2 (en) System and method for calibrating a camera feature detection system of an x-ray system
KR20200090102A (ko) 엑스선 영상 장치 및 그 제어 방법
EP4368109A1 (fr) Procédé d'apprentissage d'un modèle de correction de diffusion destiné à être utilisé dans un système d'imagerie par rayons x
WO2025012874A1 (fr) Procédé et système de détermination de la santé osseuse
WO2019012688A1 (fr) Système de radiothérapie par faisceau de particules
Kügler et al. How bad is good enough: Noisy annotations for instrument pose estimation
JP2024063537A (ja) 情報処理装置及びその制御方法、放射線撮影システム、プログラム

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: 19933910

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19933910

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: JP