Invention Grant
- Patent Title: Methods and system for selective removal of streak artifacts and noise from images using deep neural networks
-
Application No.: US16827422Application Date: 2020-03-23
-
Publication No.: US11341616B2Publication Date: 2022-05-24
- Inventor: Xinzeng Wang , Daniel Vance Litwiller , Sagar Mandava , Robert Marc Lebel , Graeme Colin McKinnon , Ersin Bayram
- Applicant: GE Precision Healthcare LLC
- Applicant Address: US WI Milwaukee
- Assignee: GE Precision Healthcare LLC
- Current Assignee: GE Precision Healthcare LLC
- Current Assignee Address: US WI Milwaukee
- Main IPC: G06T5/00
- IPC: G06T5/00 ; G06T7/00 ; G06N3/08 ; G16H30/40

Abstract:
Methods and systems are provided for independently removing streak artifacts and noise from medical images, using trained deep neural networks. In one embodiment, streak artifacts and noise may be selectively and independently removed from a medical image by receiving the medical image comprising streak artifacts and noise, mapping the medical image to a streak residual and a noise residual using the trained deep neural network, subtracting the streak residual from the medical image to a first extent, and subtracting the noise residual from the medical image to a second extent, to produce a de-noised medical image, and displaying the de-noised medical image via a display device.
Public/Granted literature
Information query