Invention Grant
- Patent Title: Training a multi-stage network to reconstruct MR images
-
Application No.: US17178674Application Date: 2021-02-18
-
Publication No.: US11720794B2Publication Date: 2023-08-08
- Inventor: Bryan Clifford , Thorsten Feiweier , Steffen Bollman , Stephen Farman Cauley
- Applicant: Siemens Healthcare GmbH , The General Hospital Corporation
- Applicant Address: DE MA Erlangen
- Assignee: Siemens Healthcare GmbH,The General Hospital Corporation
- Current Assignee: Siemens Healthcare GmbH,The General Hospital Corporation
- Current Assignee Address: DE Erlangen; US MA Boston
- Main IPC: G06N3/08
- IPC: G06N3/08 ; G06N3/045 ; G06T11/00

Abstract:
A system and method include generation of modified imaging data and modified acquisition parameters of a training example based on the target imaging data and target acquisition parameters of each of a plurality of target examples, and generation, for each training example, of an initial reconstructed image based on the modified imaging data and modified acquisition parameters of the training example. A first network stage of a multi-stage network is trained based on the modified imaging data, modified acquisition parameters and initial reconstructed image of each training example, a first output image is generated for each training example by inputting the modified imaging data, modified acquisition parameters and initial reconstructed image of the training example to the trained first network stage, and a second network stage of the multi-stage network is trained based on the modified imaging data, modified acquisition parameters and first output image of each training example.
Public/Granted literature
- US20220261629A1 TRAINING A MULTI-STAGE NETWORK TO RECONSTRUCT MR IMAGES Public/Granted day:2022-08-18
Information query