Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
IMAGE PROCESSING DEVICE AND IMAGE PROCESSING METHOD
Document Type and Number:
WIPO Patent Application WO/2023/149403
Kind Code:
A1
Abstract:
This image processing method creates a tomographic image of a subject by repeating a reconstruction step S1, a CNN processing step S2, and an updating step S3 multiple times, starting from an initial state. In the reconstruction step S1, a process according to a list mode iterative approximation reconstruction method is performed to create a first image. In the CNN processing step S2, input information is input to the CNN according to the DIP technology, a second image is created by the CNN, and the CNN is trained. In the updating step S3, a third image is updated on the basis of the first image and the second image. Thus, a device and method are implemented that are capable of creating a noise-reduced tomographic image on the basis of the list data collected by a radiation tomography imaging device.

Inventors:
OTE KIBO (JP)
HASHIMOTO FUMIO (JP)
ONISHI YUYA (JP)
Application Number:
PCT/JP2023/002910
Publication Date:
August 10, 2023
Filing Date:
January 30, 2023
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HAMAMATSU PHOTONICS KK (JP)
International Classes:
G01T1/161; A61B6/03
Domestic Patent References:
WO2020201755A12020-10-08
Foreign References:
JP2021117866A2021-08-10
JP2020128882A2020-08-27
JP2021018109A2021-02-15
JP2020036877A2020-03-12
US20210074036A12021-03-11
Other References:
GONG KUANG; GUAN JIAHUI; KIM KYUNGSANG; ZHANG XUEZHU; YANG JAEWON; SEO YOUNGHO; EL FAKHRI GEORGES; QI JINYI; LI QUANZHENG: "Iterative PET Image Reconstruction Using Convolutional Neural Network Representation", IEEE TRANSACTIONS ON MEDICAL IMAGING, IEEE, USA, vol. 38, no. 3, 1 March 2019 (2019-03-01), USA, pages 675 - 685, XP011712614, ISSN: 0278-0062, DOI: 10.1109/TMI.2018.2869871
Attorney, Agent or Firm:
HASEGAWA Yoshiki et al. (JP)
Download PDF: