Processing

Please wait...

Settings

Settings

Goto Application

1. WO2019211307 - MODALITY-AGNOSTIC METHOD FOR MEDICAL IMAGE REPRESENTATION

Publication Number WO/2019/211307
Publication Date 07.11.2019
International Application No. PCT/EP2019/061117
International Filing Date 30.04.2019
IPC
G16H 30/40 2018.1
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
G16H 20/30 2018.1
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
20ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
30relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
CPC
A61N 5/1039
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
NELECTROTHERAPY; MAGNETOTHERAPY; RADIATION THERAPY; ULTRASOUND THERAPY
5Radiation therapy
10X-ray therapy; Gamma-ray therapy; Particle-irradiation therapy
103Treatment planning systems
1039using functional images, e.g. PET or MRI
G06K 9/6274
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
6267Classification techniques
6268relating to the classification paradigm, e.g. parametric or non-parametric approaches
627based on distances between the pattern to be recognised and training or reference patterns
6271based on distances to prototypes
6274based on distances to neighbourhood prototypes, e.g. Restricted Coulomb Energy Networks
G06K 9/6289
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
6288Fusion techniques, i.e. combining data from various sources, e.g. sensor fusion
6289of input or preprocessed data
G06N 20/10
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
20Machine learning
10using kernel methods, e.g. support vector machines [SVM]
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
G06N 3/0445
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
0445Feedback networks, e.g. hopfield nets, associative networks
Applicants
  • ELEKTA AB [SE]/[SE]
Inventors
  • SJOLUND, Jens Olof
  • ADLER, Jonas Anders
Agents
  • SCHWEGMAN LUNDBERG WOESSNER LIMITED
Priority Data
15/986,06522.05.2018US
62/664,87930.04.2018US
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) MODALITY-AGNOSTIC METHOD FOR MEDICAL IMAGE REPRESENTATION
(FR) PROCÉDÉ INDÉPENDANT DE LA MODALITÉ POUR UNE REPRÉSENTATION D'IMAGE MÉDICALE
Abstract
(EN) Techniques for the operation and use of a model that learns the general representation of multimodal images are disclosed. In various examples, methods from representation learning are used to find a common basis for representation of medical images. These include aspects of encoding, fusion, and downstream tasks, with use of the general representation and model. In an example, a method for generating a modality-agnostic model includes receiving imaging data, encoding the imaging data by mapping data to a latent representation, fusing the encoded data to conserve latent variables corresponding to the latent representation, and training a model using the latent representation. In an example, a method for processing imaging data using a trained modality-agnostic model includes receiving imaging data, encoding the data to the defined encoding, processing the encoded data with a trained model, and performing imaging processing operations based on output of the trained model.
(FR) La présente invention concerne des techniques pour le fonctionnement et l'utilisation d'un modèle qui apprend la représentation générale d'images multimodales. Dans différents exemples, des procédés d'apprentissage de représentation sont utilisés pour trouver une base commune pour la représentation d'images médicales. Ceux-ci comprennent des aspects de codage, de fusion et de tâches en aval, en faisant appel à la représentation générale et au modèle. Dans un exemple, un procédé de génération d'un modèle indépendant de la modalité comprend la réception de données d'imagerie, le codage des données d'imagerie par cartographie de données à une représentation latente, la fusion des données codées pour conserver des variables latentes correspondant à la représentation latente, et l'apprentissage d'un modèle à l'aide de la représentation latente. Dans un exemple, un procédé de traitement de données d'imagerie à l'aide d'un modèle indépendant de la modalité appris comprend la réception de données d'imagerie, le codage des données en codage défini, le traitement des données codées au moyen d'un modèle appris, et la réalisation d'opérations de traitement d'imagerie sur la base de la sortie du modèle appris.
Related patent documents
Latest bibliographic data on file with the International Bureau