Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD FOR HIGH-RESOLUTION IMAGE RECONSTRUCTION
Document Type and Number:
WIPO Patent Application WO/2023/283795
Kind Code:
A1
Abstract:
Described herein are methods and non-transitory computer-readable media configured to obtain a plurality of images from a plurality of image scanning orientations for an object. A rigid registration is performed to the plurality of images to obtain a transformation matrix (206) to normalize the plurality of images from their respective image spaces to a normalized image space (208). Each normalized image comprises a plurality of voxels (212). A machine learning model (250) comprising an implicit representation of a high-resolution image (226) is trained using the normalized images, wherein the high-resolution image (226) comprises more voxels (222) than the voxels (212) in the normalized images. The high-resolution image is generated based on the trained machine learning model (250). The pluraity of images are a plurality of anisotropic 2D images, while the high resolution image can be a 2D or 3D high resolution image.

Inventors:
YU JINGYI (CN)
ZHANG YUYAO (CN)
XU LAN (CN)
LI YUWEI (CN)
WU QING (CN)
Application Number:
PCT/CN2021/105862
Publication Date:
January 19, 2023
Filing Date:
July 12, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV SHANGHAI TECHNOLOGY (CN)
International Classes:
G06T5/00; G06N3/02
Foreign References:
CN111353935A2020-06-30
CN110464353A2019-11-19
CN112102385A2020-12-18
CN102592137A2012-07-18
US20200072931A12020-03-05
US20130102877A12013-04-25
Attorney, Agent or Firm:
SHANGHAI SAVVY INTELLECTUAL PROPERTY AGENCY (CN)
Download PDF: