Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
DISSIMILAR-PAIRED NEURAL NETWORK ARCHITECTURE FOR DATA SEGMENTATION
Document Type and Number:
WIPO Patent Application WO/2022/111546
Kind Code:
A1
Abstract:
A computer-implemented system (CIS) is provided for processing and/or analyzing non-contrast-enhance computer tomography medical imaging input data is described. The CIS contains (i) twin U-Net architectures with equal weights, which are built on a Siamese architecture, and (ii) a Dissimilar block operably linked to the two U-Net architectures, and built on top of the Siamese-U-Net architecture to form a Dissimilar-Siamese-U-Net architecture. The computer-implemented system can be used in diagnosing acute ischemic stroke and/or thromoboembolus, by analyzing separate and independent input images of the left and right hemispheres of a brain. The diagnosis is based on a detection of the presence of a hyperdense middle cerebral artery sign.

Inventors:
YU PHILIP LEUNG HO (CN)
YOU JIA (CN)
TSANG ANDERSON CHUN ON (CN)
LEUNG GILBERTO KA KIT (CN)
Application Number:
PCT/CN2021/132919
Publication Date:
June 02, 2022
Filing Date:
November 24, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
UNIV HONG KONG (CN)
International Classes:
G06N3/04
Foreign References:
CN111724397A2020-09-29
US20120114205A12012-05-10
Other References:
AAKASH AGRAWAL: "Dissimilarity learning via Siamese network predicts brain imaging data", ARXIV.ORG, CORNELL UNIVERSITY LIBRARY, 201 OLIN LIBRARY CORNELL UNIVERSITY ITHACA, NY 14853, 1 July 2019 (2019-07-01), 201 Olin Library Cornell University Ithaca, NY 14853 , XP081438278
Attorney, Agent or Firm:
LIU, SHEN & ASSOCIATES (CN)
Download PDF: