Processing

Please wait...

PATENTSCOPE will be unavailable a few hours for maintenance reason on Saturday 31.10.2020 at 7:00 AM CET
Settings

Settings

Goto Application

1. WO2019057975 - METHOD AND APPARATUS FOR DERIVING A SET OF TRAINING DATA

Publication Number WO/2019/057975
Publication Date 28.03.2019
International Application No. PCT/EP2018/075825
International Filing Date 24.09.2018
IPC
G16H 50/20 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
50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
20for computer-aided diagnosis, e.g. based on medical expert systems
CPC
G06K 9/6257
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
KRECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
9Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
62Methods or arrangements for recognition using electronic means
6217Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
6256Obtaining sets of training patterns; Bootstrap methods, e.g. bagging, boosting
6257characterised by the organisation or the structure of the process, e.g. boosting cascade
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
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
G16H 50/20
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
50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
20for computer-aided diagnosis, e.g. based on medical expert systems
G16H 50/70
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
50ICT specially adapted for medical diagnosis, medical simulation or medical data mining; ICT specially adapted for detecting, monitoring or modelling epidemics or pandemics
70for mining of medical data, e.g. analysing previous cases of other patients
Applicants
  • OPTELLUM LIMITED [GB]/[GB]
  • KADIR, Timor [GB]/[GB] (US)
  • PICKUP, Lyndsey [GB]/[GB] (US)
  • POTESIL, Vaclav [CZ]/[GB] (US)
  • DECLERCK, Jerome [FR]/[GB] (US)
Inventors
  • KADIR, Timor
  • PICKUP, Lyndsey
  • POTESIL, Vaclav
  • DECLERCK, Jerome
Agents
  • WRAY, Antony
Priority Data
1715336.222.09.2017GB
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) METHOD AND APPARATUS FOR DERIVING A SET OF TRAINING DATA
(FR) PROCÉDÉ ET APPAREIL DE DÉRIVATION D'UN ENSEMBLE DE DONNÉES D'APPRENTISSAGE
Abstract
(EN)
A Computer Aided Diagnosis, CAD, training system (400) is described for training a CAD device (310) to receive and process at least one input medical image and produce an output that indicates a probability of a medical condition of a patient. The CAD device (310) comprises: an input circuit (305) configured to receive and assemble training data that comprises: medical data of patients that have been identified as having at least one medical condition, and medical data of patients that have been identified as not having the at least one medical condition. A parsing circuit (315) is configured to: separate the assembled training data into data sets, such that a first data set contains only the medical data of patients that have the at least one medical condition and a second data set contains only the medical data of patients that do not have the condition; and parse at least one of the data sets into at least two subsets (328), whereby a first subset is distinguished over a second subset of the at least two subsets (328) by at least one attribute. A data classifier circuit (330)is configured to associate different weights to the separated assembled training data, such that the first subset is prioritised during training of the CAD device.
(FR)
L'invention concerne un système d'apprentissage d'aide au diagnostic médical (CAD) (400), destiné à l'apprentissage d'un dispositif CAD (310) afin qu'il reçoive et traite au moins une image médicale d'entrée et produise une sortie qui indique une probabilité d'un état pathologique d'un patient. Le dispositif CAD (310) comprend : un circuit d'entrée (305) configuré pour recevoir et assembler des données d'apprentissage qui comprennent : des données médicales de patients qui ont été identifiés comme présentant au moins un état pathologique, et des données médicales de patients qui ont été identifiés comme ne présentant pas ledit état pathologique. Un circuit d'analyse (315) est configuré pour séparer les données d'apprentissage assemblées en ensembles de données, de sorte qu'un premier ensemble de données ne contient que les données médicales de patients qui présentent ledit état pathologique et qu'un second ensemble de données ne contient que les données médicales de patients qui ne présentent pas l'état pathologique; et pour décomposer au moins l'un des ensembles de données en au moins deux sous-ensembles (328), moyennant quoi un premier sous-ensemble est différencié d'un second sous-ensemble desdits deux sous-ensembles (328) ou plus par au moins un attribut. Un circuit classificateur de données (330) est configuré pour associer différents poids aux données d'apprentissage assemblées séparées, de sorte que le premier sous-ensemble est prioritaire pendant l'apprentissage du dispositif CAD.
Also published as
Latest bibliographic data on file with the International Bureau