CONFERENCE PROCEEDINGS
Advanced Search
Home > Proceedings > Volume 12925 > Article
Poster + Paper
1 April 2024 Noise gate: a physics-driven control method for deep learning denoising in x-ray imaging
Magdalena Herbst, Marcel Beister, Stephan Dwars, Dominik Eckert, Ludwig Ritschl, Christopher Syben, Steffen Kappler
Author Affiliations +
Proceedings Volume 12925, Medical Imaging 2024: Physics of Medical Imaging; 129253X (2024) https://doi.org/10.1117/12.3006446
Event: SPIE Medical Imaging, 2024, San Diego, California, United States
Conference Poster
Abstract
Denoising algorithms are sensitive to the noise level and noise power spectrum of the input image and their ability to adapt to this. In the worst-case, image structures can be accidentally removed or even added. This holds up for analytical image filters but even more for deep learning-based denoising algorithms due to their high parameter space and their data-driven nature. We propose to use the knowledge about the noise distribution of the image at hand to limit the influence and ability of denoising algorithms to a known and plausible range. Specifically, we can use the physical knowledge of X-ray radiography by considering the Poisson noise distribution and the noise power spectrum of the detector. Through this approach, we can limit the change of the acquired signal by the denoising algorithm to the expected noise range, and therefore prevent the removal or hallucination of small relevant structures. The presented method allows to use denoising algorithms and especially deep learning-based methods in a controlled and safe fashion in medical x-ray imaging.
© (2024) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Citation Download Citation
Magdalena Herbst, Marcel Beister, Stephan Dwars, Dominik Eckert, Ludwig Ritschl, Christopher Syben, and Steffen Kappler "Noise gate: a physics-driven control method for deep learning denoising in x-ray imaging", Proc. SPIE 12925, Medical Imaging 2024: Physics of Medical Imaging, 129253X (1 April 2024); https://doi.org/10.1117/12.3006446
ACCESS THE FULL ARTICLE
ORGANIZATIONAL
Sign in with credentials provided by your organization.
INSTITUTIONAL
Select your institution to access the SPIE Digital Library.
SELECT YOUR INSTITUTION
PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.
PERSONAL SIGN IN
No SPIE Account? Create one
PURCHASE THIS CONTENT
SUBSCRIBE TO DIGITAL LIBRARY
50 downloads per 1-year subscription
Members: $195
Non-members: $335 ADD TO CART
25 downloads per 1 - year subscription
Members: $145
Non-members: $250 ADD TO CART
PURCHASE SINGLE ARTICLE
Includes PDF, HTML & Video, when available
Members: $17.00
Non-members: $21.00 ADD TO CART
PROCEEDINGS
 4 PAGES + POSTER
DOWNLOAD PAPER SAVE TO MY LIBRARY
DOWNLOAD
POSTER
GET CITATION
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Denoising
X-ray imaging
Deep learning
Tunable filters
X-rays
RELATED CONTENT
Subscribe to Digital Library
Receive Erratum Email Alert
Back to Top