Invention Grant
- Patent Title: Systems and methods for low-dose AI-based imaging
-
Application No.: US17163719Application Date: 2021-02-01
-
Publication No.: US11890124B2Publication Date: 2024-02-06
- Inventor: Andre D. A. Souza , Michael Philip Marrama , Patrick A. Helm , Mehdi Rahman , Kyo C. Jin , Michael D. Ketcha
- Applicant: Medtronic Navigation, Inc.
- Applicant Address: US CO Louisville
- Assignee: Medtronic Navigation, Inc.
- Current Assignee: Medtronic Navigation, Inc.
- Current Assignee Address: US CO Louisville
- Agency: Sheridan Ross P.C.
- Main IPC: A61B6/00
- IPC: A61B6/00 ; G06T11/00 ; G16H50/20 ; G06N3/08

Abstract:
A low-dose imaging method includes receiving a sparse image set of a portion of a patient's anatomy; up-sampling the sparse image set, in the sinogram domain and using a first neural network, to yield an up-sampled sinogram; generating, from the up-sampled sinogram, an initial reconstruction; and removing, from the initial reconstruction and using a second neural network, one or more artifacts in the initial reconstruction to yield a final output volume.
Public/Granted literature
- US20220240879A1 SYSTEMS AND METHODS FOR LOW-DOSE AI-BASED IMAGING Public/Granted day:2022-08-04
Information query