Convolutional neural network (CNN)-based CT denoising methods have attracted great interest for improving the image quality of low-dose CT (LDCT) images. However, CNN requires a large amount of paired data consisting of normal-dose CT (NDCT) and LDCT images, which are generally not available. In this work, we aim to synthesize paired data from NDCT images with an accurate image domain noise insertion technique and investigate its effect on the denoising performance of CNN. Fan-beam CT images were reconstructed using extended cardiac-torso phantoms with Poisson noise added to projection data to simulate NDCT and LDCT. We estimated local noise power spectra and a variance map from a NDCT image using information on photon statistics and reconstruction parameters. We then synthesized image domain noise by filtering and scaling white Gaussian noise using the local noise power spectrum and variance map, respectively. The CNN architecture was U-net, and the loss function was a weighted summation of mean squared error, perceptual loss, and adversarial loss. CNN was trained with NDCT and LDCT (CNN-Ideal) or NDCT and synthesized LDCT (CNN-Proposed). To evaluate denoising performance, we measured the root mean squared error (RMSE), structural similarity index (SSIM), noise power spectrum (NPS), and modulation transfer function (MTF). The MTF was estimated from the edge spread function of a circular object with 12 mm diameter and 60 HU contrast. Denoising results from CNN-Ideal and CNN-Proposed show no significant difference in all metrics while providing high scores in RMSE and SSIM compared to NDCT and similar NPS shapes to that of NDCT.
|Title of host publication||Medical Imaging 2021|
|Subtitle of host publication||Physics of Medical Imaging|
|Editors||Hilde Bosmans, Wei Zhao, Lifeng Yu|
|Publication status||Published - 2021|
|Event||Medical Imaging 2021: Physics of Medical Imaging - Virtual, Online, United States|
Duration: 2021 Feb 15 → 2021 Feb 19
|Name||Progress in Biomedical Optics and Imaging - Proceedings of SPIE|
|Conference||Medical Imaging 2021: Physics of Medical Imaging|
|Period||21/2/15 → 21/2/19|
Bibliographical noteFunding Information:
This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Ministry of Science and ICT (NRF-2019R1A2C2084936, 2020R1A4A1016619).
© COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.
All Science Journal Classification (ASJC) codes
- Electronic, Optical and Magnetic Materials
- Atomic and Molecular Physics, and Optics
- Radiology Nuclear Medicine and imaging