KLI

CycleGAN denoising of extreme low-dose cardiac CT using wavelet-assisted noise disentanglement

Metadata Downloads
Abstract
Abstract
In electrocardiography (ECG) gated cardiac CT angiography (CCTA), multiple images covering the entire cardiac cycle are taken continuously, so reduction of the accumulated radiation dose could be an important issue for patient safety. Although ECG-gated dose modulation (so-called ECG pulsing) is used to acquire many phases of CT images at a low dose, the reduction of the radiation dose introduces noise into the image reconstruction. To address this, we developed a high performance unsupervised deep learning method using noise disentanglement that can effectively learn the noise patterns even from extreme low dose CT images. For noise disentanglement, we use a wavelet transform to extract the high-frequency signals that contain the most noise. Since matched low-dose and high-dose cardiac CT data are impossible to obtain in practice, our neural network was trained in an unsupervised manner using cycleGAN for the extracted high frequency signals from the low-dose and unpaired high-dose CT images. Once the network is trained, denoised images are obtained by subtracting the estimated noise components from the input images. Image quality evaluation of the denoised images from only 4% dose CT images was performed by experienced radiologists for several anatomical structures. Visual grading analysis was conducted according to the sharpness level, noise level, and structural visibility. Also, the signal-to-noise ratio was calculated. The evaluation results showed that the quality of the images produced by the proposed method is much improved compared to low-dose CT images and to the baseline cycleGAN results. The proposed noise-disentangled cycleGAN with wavelet transform effectively removed noise from extreme low-dose CT images compared to the existing baseline algorithms. It can be an important denoising platform for low-dose CT.
Author(s)
구자욱양태성예종철양동현
Issued Date
2021
Type
Article
Keyword
Adversarial trainingCoronary CT angiographyCycle consistencyLow-dose CTUnsupervised learningWavelet transform
DOI
10.1016/j.media.2021.102209
URI
https://oak.ulsan.ac.kr/handle/2021.oak/8264
https://ulsan-primo.hosted.exlibrisgroup.com/primo-explore/fulldisplay?docid=TN_cdi_proquest_miscellaneous_2566037344&context=PC&vid=ULSAN&lang=ko_KR&search_scope=default_scope&adaptor=primo_central_multiple_fe&tab=default_tab&query=any,contains,CycleGAN%20denoising%20of%20extreme%20low-dose%20cardiac%20CT%20using%20wavelet-assisted%20noise%20disentanglement&offset=0&pcAvailability=true
Publisher
MEDICAL IMAGE ANALYSIS
Location
영국
Language
영어
ISSN
1361-8415
Citation Volume
74
Citation Start Page
102209
Citation End Page
102209
Appears in Collections:
Medicine > Medicine
Authorize & License
  • Authorize공개
Files in This Item:
  • There are no files associated with this item.

Items in Repository are protected by copyright, with all rights reserved, unless otherwise indicated.