2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI) 2021
DOI: 10.1109/isbi48211.2021.9433825
|View full text |Cite
|
Sign up to set email alerts
|

No-Reference Denoising Of Low-Dose Ct Projections

Abstract: Low-dose computed tomography (LDCT) became a clear trend in radiology with an aspiration to refrain from delivering excessive X-ray radiation to the patients. The reduction of the radiation dose decreases the risks to the patients but raises the noise level, affecting the quality of the images and their ultimate diagnostic value. One mitigation option is to consider pairs of low-dose and high-dose CT projections to train a denoising model using deep learning algorithms; however, such pairs are rarely available… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 8 publications
(6 citation statements)
references
References 12 publications
(11 reference statements)
0
6
0
Order By: Relevance
“…We observe that, for the proposed method, IGC is able to enhance the sharpness of the overblurred regions and suppress the streak artifacts near high contrast edges. For TD method, 12 IGC helps suppress more noise. We attribute this to the role of IGC for maintaining gradient between sequential projections, which suppresses noise and outliers and preserves sharpness.…”
Section: Resultsmentioning
confidence: 99%
See 2 more Smart Citations
“…We observe that, for the proposed method, IGC is able to enhance the sharpness of the overblurred regions and suppress the streak artifacts near high contrast edges. For TD method, 12 IGC helps suppress more noise. We attribute this to the role of IGC for maintaining gradient between sequential projections, which suppresses noise and outliers and preserves sharpness.…”
Section: Resultsmentioning
confidence: 99%
“…These methods use the same network architecture shown in Figure 2 and adopt the MAE loss for model training. The time‐distributed model 12 in projection domain (TD‐PD) with IGC or without IGC is also investigated.…”
Section: Methodsmentioning
confidence: 99%
See 1 more Smart Citation
“…Inspired by previous work [16,22,21] and our understanding of CT imaging. We propose to employ a self-supervised learning model,Noise2Projection, to do low-dose CT image reconstruction using raw projection data.…”
Section: Introductionmentioning
confidence: 98%
“…As a step further, selfsupervised learning, which requires neither clean targets nor noisy image pairs in denoising tasks, has been proposed [2,12,13,16,22], but they add complexity to the model, and training process making it less efficient. In recent work [21], a self-supervised learning models have been developed to do projection data noise reduction with a promising result. However, the method has only been evaluated on simulated data and has yet to be validated on clinical data.…”
Section: Introductionmentioning
confidence: 99%