US 11,983,847 B2
Method and device for noise reduction in image recordings
Thomas Flohr, Uehlfeld (DE); Rainer Raupach, Heroldsbach (DE); and Bernhard Schmidt, Fuerth (DE)
Assigned to Siemens Healthineers AG, Forchheim (DE)
Filed by Siemens Healthcare GmbH, Erlangen (DE)
Filed on Sep. 28, 2020, as Appl. No. 17/034,148.
Claims priority of application No. 10 2019 215 460.3 (DE), filed on Oct. 9, 2019.
Prior Publication US 2021/0110517 A1, Apr. 15, 2021
Int. Cl. G06T 5/00 (2006.01); G06N 20/00 (2019.01)
CPC G06T 5/002 (2013.01) [G06N 20/00 (2019.01); G06T 2207/10081 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30004 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A method for noise reduction in an image, comprising:
providing an input image, the input image being a reconstructed computed tomography (CT) image;
de-noising the input image and producing a de-noised input image; and
adapting a noise texture of the de-noised input image via an adaptation method to produce an adapted image, the adaptation method including replacing the noise texture of the de-noised input image by a noise texture of the adapted image via an algorithm which adapts the de-noised input image based on an adaptation function, the noise texture of the de-noised input image being hyper-Gaussian, the noise texture of the adapted image being Gaussian,
wherein a noise amplitude of the de-noised input image is retained during the adaptation method.