US 12,082,771 B2
Method for adaptive denoising and sharpening and visualization systems implementing the method
Andreas Härstedt Jørgensen, Rødovre (DK); and Finn Sonnenborg, Frederikssund (DK)
Assigned to AMBU A/S, Ballerup (DK)
Filed by AMBU A/S, Ballerup (DK)
Filed on Apr. 11, 2022, as Appl. No. 17/717,969.
Application 17/717,969 is a continuation of application No. 15/931,576, filed on May 13, 2020, granted, now 11,328,390.
Prior Publication US 2022/0245770 A1, Aug. 4, 2022
Int. Cl. G06T 5/00 (2024.01); A61B 1/00 (2006.01); A61B 1/05 (2006.01); G06K 9/40 (2006.01); G06T 5/70 (2024.01); G06T 5/73 (2024.01)
CPC A61B 1/000094 (2022.02) [A61B 1/000095 (2022.02); A61B 1/05 (2013.01); G06T 5/70 (2024.01); G06T 5/73 (2024.01); G06T 2200/24 (2013.01); G06T 2207/10016 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method to adaptively generate denoised images from images obtained live from a videoscope, the method comprising:
by a video processing apparatus (VPA) communicatively connected to the videoscope:
receiving live image signals from the videoscope via a connector configured to receive a removable plug of the videoscope or a wireless transceiver communicatively connecting an image sensor positioned distally of an insertion tube of the videoscope with the VPA, the life image signals being based on the images;
determining an amplification gain level used by the image sensor of the videoscope to generate the image signals;
receiving a user input indicative of a noise threshold, the noise threshold being a numerical value selected from a plurality of values and configured to determine a denoising level and a sharpening level;
selecting the denoising level from a plurality of denoising levels based on the noise threshold and the amplification gain level;
selecting the sharpening level from a plurality of sharpening levels based on the noise threshold and the amplification gain level; and
generating the denoised images using the denosing level and the sharpening level to denoise and sharpen the images, the denoised images having a noise level corresponding to the noise threshold.