Pixel-wise bias approximation and correction for convolutional neural network noise reduction in CT

Nathan R. Huber, Hao Gong, Thomas Huber, David Campeau, Hsieh Scott, Shuai Leng, Lifeng Yu, Cynthia McCollough

Research output: Chapter in Book/Report/Conference proceedingConference contribution


This study introduces a framework to approximate the bias inflicted by CNN noise reduction of CT exams. First, CNN noise reduction was used to approximate the noise-free image and noise-only image of a CT scan. The noise and signal were then recombined with spatial decoupling to simulate an ensemble of 100 images. CNN noise reduction was applied to the simulated ensemble and pixel-wise bias calculated. This bias approximation technique was validated within natural images and phantoms. The technique was then tested on ten whole-body-low-dose CT (WBLD-CT) patient exams. Bias correction led to improved contrast of lung and bone structures.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2022
Subtitle of host publicationPhysics of Medical Imaging
EditorsWei Zhao, Lifeng Yu
ISBN (Electronic)9781510649378
StatePublished - 2022
EventMedical Imaging 2022: Physics of Medical Imaging - Virtual, Online
Duration: Mar 21 2022Mar 27 2022

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
ISSN (Print)1605-7422


ConferenceMedical Imaging 2022: Physics of Medical Imaging
CityVirtual, Online


  • Bias
  • Bootstrap Approximation
  • CNN Denoising
  • Uncertainty
  • Whole-Body-Low-Dose CT

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Atomic and Molecular Physics, and Optics
  • Biomaterials
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'Pixel-wise bias approximation and correction for convolutional neural network noise reduction in CT'. Together they form a unique fingerprint.

Cite this