2021
DOI: 10.1016/j.ejmp.2020.11.027
|View full text |Cite
|
Sign up to set email alerts
|

Validation of low-dose lung cancer PET-CT protocol and PET image improvement using machine learning

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
5
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
2

Relationship

0
7

Authors

Journals

citations
Cited by 10 publications
(5 citation statements)
references
References 25 publications
0
5
0
Order By: Relevance
“…Positron emission tomography (PET) is a quantitative imaging modality that is used to study functional processes using specific radiotracers (e.g. metabolism using [ 18 F]-fluorodeoxyglucose (FDG), prostate cancer detection using [ 68 Ga]-PSMA). The quality and quantitative accuracy of PET images are influenced by several factors such as scanner specifications (e.g.…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…Positron emission tomography (PET) is a quantitative imaging modality that is used to study functional processes using specific radiotracers (e.g. metabolism using [ 18 F]-fluorodeoxyglucose (FDG), prostate cancer detection using [ 68 Ga]-PSMA). The quality and quantitative accuracy of PET images are influenced by several factors such as scanner specifications (e.g.…”
Section: Introductionmentioning
confidence: 99%
“…DLE methods have shown promising performance for image denoising [9] with comparable performance to DLR methods [14]. Moreover, image-based machine/deep learning techniques have enabled ultra-low dose PET scans maintaining clinically relevant information in terms of diagnostic accuracy and quantitative SUV measurements [18,19]. The great potential for DLE motivated the current study, in which we trained and evaluated a DLE model.…”
Section: Introductionmentioning
confidence: 99%
“…Our approximation differs from Fahey et al [22] recommendations, who proposed to maintain tube voltage at 120 kVp and to use the lowest tube current-time product setting (5 mAs). Nai et al [27] have also proposed a low dose PET/CT protocol for lung cancer screening with reduced current-time product (from 140 mAs to 40 mAs with CAE) but tube voltage fixed at 120 kV. However, in our experience, the reduction of tube voltage from 120 kV to 100 kV achieves a significant CTDI vol reduction without any image degradation.…”
Section: Discussionmentioning
confidence: 74%
“…Artificial intelligence has had a substantial global impact across all fields, and nuclear medicine is no exception. Numerous machine or deep learning techniques have been developed to reduce noise, and nonlinear transformations have been studied to predict standard doses based on low-dose images [84][85][86][87]. In addition, manufacturers have made attempts to improve PET image quality by developing AI filters that can perform Timeof-Flight (ToF) modeling, even for non-ToF systems [88].…”
Section: Future Perspectivesmentioning
confidence: 99%