Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020113148 - SINGLE OR A FEW VIEWS COMPUTED TOMOGRAPHY IMAGING WITH DEEP NEURAL NETWORK

Publication Number WO/2020/113148
Publication Date 04.06.2020
International Application No. PCT/US2019/063835
International Filing Date 29.11.2019
IPC
A61B 5/00 2006.01
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
5Measuring for diagnostic purposes; Identification of persons
A61B 6/02 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
A61B 8/13 2006.01
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
8Diagnosis using ultrasonic, sonic or infrasonic waves
13Tomography
G05B 19/02 2006.01
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
19Programme-control systems
02electric
G06T 11/00 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
112D image generation
H04N 19/51 2014.01
HELECTRICITY
04ELECTRIC COMMUNICATION TECHNIQUE
NPICTORIAL COMMUNICATION, e.g. TELEVISION
19Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
50using predictive coding
503involving temporal prediction
51Motion estimation or motion compensation
CPC
A61B 5/7267
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
5Detecting, measuring or recording for diagnostic purposes
72Signal processing specially adapted for physiological signals or for diagnostic purposes
7235Details of waveform analysis
7264Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
7267involving training the classification device
A61B 6/032
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
032Transmission computed tomography [CT]
A61B 6/463
AHUMAN NECESSITIES
61MEDICAL OR VETERINARY SCIENCE; HYGIENE
BDIAGNOSIS; SURGERY; IDENTIFICATION
6Apparatus for radiation diagnosis, e.g. combined with radiation therapy equipment
46with special arrangements for interfacing with the operator or the patient
461Displaying means of special interest
463characterised by displaying multiple images or images and diagnostic data on one display
A61B 6/5211
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
5211involving processing of medical diagnostic data
G05B 19/02
GPHYSICS
05CONTROLLING; REGULATING
BCONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
19Programme-control systems
02electric
G06T 11/00
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
112D [Two Dimensional] image generation
Applicants
  • THE BOARD OF TRUSTEES OF THE LELAND SANFORD JUNIOR UNIVERSITY [US]/[US]
Inventors
  • SHEN, Liyue
  • ZHAO, Wei
  • XING, Lei
Agents
  • JACOBS, Ron
  • MCFARLANE, Thomas, J.
  • LODENKAMPER, Robert
Priority Data
62/772,88529.11.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) SINGLE OR A FEW VIEWS COMPUTED TOMOGRAPHY IMAGING WITH DEEP NEURAL NETWORK
(FR) IMAGERIE DE TOMOGRAPHIE À VUE UNIQUE OU À PEU DE VUES AU MOYEN D'UN RÉSEAU NEURONAL PROFOND
Abstract
(EN)
A method for tomographic imaging comprising acquiring [200] a set of one or more 2D projection images [202] and reconstructing [204] a 3D volumetric image [216] from the set of one or more 2D projection images [202] using a residual deep learning network comprising an encoder network, a transform module and a decoder network, wherein the reconstructing comprises: transforming [206] by the encoder network the set of one or more 2D projection images [202] to 2D features [208]; mapping [210] by the transform module the 2D features [208] to 3D features [212]; and generating [214] by the decoder network the 3D volumetric image [216] from the 3D features [212]. Preferably, the encoder network comprises 2D convolution residual blocks and the decoder network comprises 3D blocks without residual shortcuts within each of the 3D blocks.
(FR)
Un procédé d'imagerie tomographique consiste à acquérir [200] un ensemble d'une ou de plusieurs images de projection 2D [202] et à reconstruire [204] une image volumétrique 3D [216] à partir de l'ensemble d'une ou de plusieurs images de projection 2D [202] à l'aide d'un réseau d'apprentissage profond résiduel comprenant un réseau de codage, un module de transformation et un réseau de décodage, la reconstruction consistant à : transformer [206], au moyen du réseau de codage, l'ensemble d'une ou de plusieurs images de projection 2D [202] en des caractéristiques 2D [208] ; mapper [210], au moyen du module de transformation, les caractéristiques 2D [208] en caractéristiques 3D [212] ; et générer [214], au moyen du réseau de décodage, l'image volumétrique 3D [216] à partir des caractéristiques 3D [212]. De préférence, le réseau de codage comprend des blocs résiduels de convolution 2D et le réseau décodage comprend des blocs 3D sans raccourcis résiduels dans chacun des blocs 3D.
Latest bibliographic data on file with the International Bureau