Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020110775 - IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND PROGRAM

Publication Number WO/2020/110775
Publication Date 04.06.2020
International Application No. PCT/JP2019/044868
International Filing Date 15.11.2019
IPC
A61B 6/03 2006.01
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
6Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
02Devices for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
03Computerised tomographs
A61B 6/00 2006.01
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
6Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
G06N 3/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
G06T 7/10 2017.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
10Segmentation; Edge detection
G16H 30/40 2018.01
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
30ICT specially adapted for the handling or processing of medical images
40for processing medical images, e.g. editing
CPC
A61B 6/00
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
6Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
A61B 6/03
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
6Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
02Devices for diagnosis sequentially in different planes; Stereoscopic radiation diagnosis
03Computerised tomographs
G06N 3/04
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
G06T 7/10
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
7Image analysis
10Segmentation; Edge detection
G16H 30/40
GPHYSICS
16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
30ICT specially adapted for the handling or processing of medical images
40for processing medical images, e.g. editing
Applicants
  • 富士フイルム株式会社 FUJIFILM CORPORATION [JP]/[JP]
Inventors
  • ケシュワニ ディーパック KESHWANI, Deepak
  • 北村 嘉郎 KITAMURA, Yoshiro
Agents
  • 松浦 憲三 MATSUURA, Kenzo
Priority Data
2018-22502030.11.2018JP
Publication Language Japanese (JA)
Filing Language Japanese (JA)
Designated States
Title
(EN) IMAGE PROCESSING DEVICE, IMAGE PROCESSING METHOD, AND PROGRAM
(FR) DISPOSITIF DE TRAITEMENT D'IMAGE, PROCÉDÉ DE TRAITEMENT D'IMAGE ET PROGRAMME
(JA) 画像処理装置、画像処理方法、及びプログラム
Abstract
(EN)
This image processing device, image processing method, and program can suppress errors in medical image segmentation. This image processing device is provided with a segmentation unit (42) which applies deep learning to perform segmentation for classifying medical images into specific classes on the basis of local features of a medical image (200), and a global feature classification unit (46) which applies deep learning to classify medical images by global features, which are features of the medical image as a whole. The segmentation unit shares weights in the first low-level layer, which is a low-level layer, with a second low-level layer, which is a low-level layer in the global feature classification unit.
(FR)
Ce dispositif de traitement d'image, le procédé de traitement d'image et le programme peuvent supprimer des erreurs dans une segmentation d'image médicale. Ce dispositif de traitement d'image est pourvu d'une unité de segmentation (42) qui applique un apprentissage profond pour effectuer une segmentation pour classifier des images médicales en classes spécifiques sur la base de caractéristiques locales d'une image médicale (200), et une unité de classification de caractéristiques globales (46) qui applique un apprentissage profond pour classifier des images médicales par des caractéristiques globales, qui sont des caractéristiques de l'image médicale dans son ensemble. L'unité de segmentation partage des poids dans la première couche de bas niveau, qui est une couche de bas niveau, avec une seconde couche de bas niveau, qui est une couche de bas niveau dans l'unité de classification de caractéristiques globales.
(JA)
医用画像のセグメンテーションにおける誤りを抑制し得る画像処理装置、画像処理方法、及びプログラムを提供する。深層学習を適用して、医用画像(200)の局所の特徴に基づき医用画像を特定のクラスに分類するセグメンテーションを行うセグメンテーション部(42)と、深層学習を適用して、医用画像を医用画像の全体の特徴であるグローバル特徴に分類するグローバル特徴分類部(46)と、を備え、セグメンテーション部は、低次層である第一低次層の重みを、グローバル特徴分類部における低次層である第二低次層と共有する。
Latest bibliographic data on file with the International Bureau