Performance of a deep learning-based CT image denoising method: Generalizability over dose, reconstruction kernel, and slice thickness.

Journal: Medical physics
Published Date: Jan 19, 2022

Abstract

PURPOSE: Deep learning (DL) is rapidly finding applications in low-dose CT image denoising. While having the potential to improve the image quality (IQ) over the filtered back projection method (FBP) and produce images quickly, performance generalizability of the data-driven DL methods is not fully understood yet. The main purpose of this work is to investigate the performance generalizability of a low-dose CT image denoising neural network in data acquired under different scan conditions, particularly relating to these three parameters: reconstruction kernel, slice thickness, and dose (noise) level. A secondary goal is to identify any underlying data property associated with the CT scan settings that might help predict the generalizability of the denoising network.

Authors

  • Rongping Zeng
    Center for Devices and Radiological Health, US Food and Drug Administration (FDA), Silver Spring, Maryland, USA.
  • Claire Yilin Lin
    KLA Corporation, Milpitas, California, USA.
  • Qin Li
    Department of Spine Surgery, The Third Hospital of Mianyang, Sichuan Mental Health Center, Mianyang, China.
  • Lu Jiang
    Institute of Materials Research and Engineering (IMRE), A*STAR, 2 Fusionopolis Way, #08-03 Innovis, Singapore 138634.
  • Marlene Skopec
    National Institutes of Health, Bethesda, Maryland, USA.
  • Jeffrey A Fessler
    Department of Electrical Engineering and Computer Science, University of Michigan, Ann Arbor, MI, 48109 USA.
  • Kyle J Myers
    Division of Imaging, Diagnostics, and Software Reliability, Office of Science and Engineering Laboratories, Center for Devices and Radiological Health, Food and Drug Administration (FDA), Silver Spring, MD, USA.

Keywords

External Resources

Popular Topics
Recent Journals