2022
DOI: 10.1002/mp.15952
|View full text |Cite
|
Sign up to set email alerts
|

Domain‐adaptive denoising network for low‐dose CT via noise estimation and transfer learning

Abstract: Background: In recent years, low-dose computed tomography (LDCT) has played an important role in the diagnosis CT to reduce the potential adverse effects of X-ray radiation on patients, while maintaining the same diagnostic image quality. Purpose: Deep learning (DL)-based methods have played an increasingly important role in the field of LDCT imaging. However, its performance is highly dependent on the consistency of feature distributions between training data and test data. Due to patient's breathing movement… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
9
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 18 publications
(9 citation statements)
references
References 49 publications
0
9
0
Order By: Relevance
“…The predominant DL models for CT denoising are GANs and CNNs. As shown in Figure 2a, out of 99 publications examined, 61 studies use the models based on CNN, 59–119 while 30 studies are based on GAN 120–149 . Additionally, two studies adopt Transformer‐based approaches 150,151 .…”
Section: Dl‐based Noise Reduction Methodsmentioning
confidence: 99%
See 2 more Smart Citations
“…The predominant DL models for CT denoising are GANs and CNNs. As shown in Figure 2a, out of 99 publications examined, 61 studies use the models based on CNN, 59–119 while 30 studies are based on GAN 120–149 . Additionally, two studies adopt Transformer‐based approaches 150,151 .…”
Section: Dl‐based Noise Reduction Methodsmentioning
confidence: 99%
“…The predominant DL models for CT denoising are GANs and CNNs. As shown in Figure 2a , out of 99 publications examined, 61 studies use the models based on CNN, 59 , 60 , 61 , 62 , 63 , 64 , 65 , 66 , 67 , 68 , 69 , 70 , 71 , 72 , 73 , 74 , 75 , 76 , 77 , 78 , 79 , 80 , 81 , 82 , 83 , 84 , 85 , 86 , 87 , 88 , 89 , 90 , 91 , 92 , 93 , 94 , 95 , 96 , 97 , 98 , 99 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 , …”
Section: Dl‐based Noise Reduction Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…In recent years, supervised deep learning (DL) based methods have been dedicated to improve low-dose CT (LDCT) imaging performance , Chen et al 2017, Kang et al 2017, Chen et al 2018, Yao et al 2021, Zhou et al 2022, Wang et al 2022. For example, Zhou et al proposed a dual-domain underto-fully-complete progressive restoration network (DuDoUFNet) to simultaneously reduce noise and metal artifacts in LDCT images (Zhou et al 2022).…”
Section: Introductionmentioning
confidence: 99%
“…For example, Zhou et al proposed a dual-domain underto-fully-complete progressive restoration network (DuDoUFNet) to simultaneously reduce noise and metal artifacts in LDCT images (Zhou et al 2022). Wang et al trained a deep neural network (DNN) model with the public simulated dataset at the first stage and fine-tuned this model with a torso phantom dataset at the second transfer training stage (Wang et al 2022). Although the above supervised DL-based methods can reduce noiseinduced artifacts at some extent, these methods might lead to overfitting and instability in the CT imaging task, which do not generalize well from training data to testing data.…”
Section: Introductionmentioning
confidence: 99%