Processing

Please wait...

Settings

Settings

Goto Application

1. WO2022049039 - SPECTRAL X-RAY MATERIAL DECOMPOSITION METHOD

Publication Number WO/2022/049039
Publication Date 10.03.2022
International Application No. PCT/EP2021/073920
International Filing Date 31.08.2021
IPC
A61B 6/00 2006.1
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
6Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
G06N 3/04 2006.1
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
G06K 9/62 2006.1
GPHYSICS
06COMPUTING; CALCULATING OR 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
CPC
A61B 6/4241
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
6Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
42with arrangements for detecting radiation specially adapted for radiation diagnosis
4208characterised by using a particular type of detector
4241using energy resolving detectors, e.g. photon counting
A61B 6/482
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
6Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
48Diagnostic techniques
482involving multiple energy imaging
A61B 6/5205
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
6Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
52Devices using data or image processing specially adapted for radiation diagnosis
5205involving processing of raw data to produce diagnostic data
G06N 3/0454
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
0454using a combination of multiple neural nets
G06N 3/084
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
084Back-propagation
G06V 10/774
Applicants
  • KONINKLIJKE PHILIPS N.V. [NL]/[NL]
Inventors
  • SOSSIN, Artur
  • BRENDEL, Bernhard Johannes
Agents
  • PHILIPS INTELLECTUAL PROPERTY & STANDARDS
Priority Data
20194235.603.09.2020EP
Publication Language English (en)
Filing Language English (EN)
Designated States
Title
(EN) SPECTRAL X-RAY MATERIAL DECOMPOSITION METHOD
(FR) PROCÉDÉ DE DÉCOMPOSITION SPECTRALE DE MATIÈRE AUX RAYONS X
Abstract
(EN) A method for material decomposition of an object based on spectral X-ray scan data for the object and based on application of a frequency split approach. The method comprises using two AI models in parallel to perform the material decomposition analysis based on input spectral X- ray data, wherein the models are configured such that one exhibits higher bias and lower variance (lower noise) than the other. The input spectral X-ray data is fed to both models. The output material composition data from the low bias model is low-pass filtered and the output material composition data from the low variance model is high pass filtered. The outputs from the two models are linearly combined, either before the filtering or after. The resulting combined material decomposition data has both lower bias and lower noise compared to the output generated if just one AI model were to be used.
(FR) Procédé de décomposition de la matière d'un objet sur la base de données spectrales de balayage aux rayons X de l'objet et sur la base de l'application d'une approche de division de fréquence. Le procédé consiste à utiliser en parallèle deux modèles d'IA pour effectuer l'analyse de décomposition de la matière sur la base de données spectrales de rayons X d'entrée, les modèles étant conçus de telle sorte que l'un présente une polarisation supérieure et une variance inférieure (bruit plus faible) que l'autre. Les données spectrales de rayons X d'entrée sont fournies aux deux modèles. Les données de sortie sur la composition de la matière provenant du modèle à faible polarisation sont filtrées passe-bas et les données de sortie sur la composition de la matière provenant du modèle à faible variance sont filtrées passe-haut. Les sorties des deux modèles sont combinées linéairement, soit avant soit après le filtrage. Les données de décomposition de la matière combinées résultantes ont à la fois une polarisation inférieure et un bruit inférieur par rapport à la sortie générée si un seul modèle d'IA était utilisé.
Related patent documents
Latest bibliographic data on file with the International Bureau