A Self-supervised Deep Learning Network for Low-Dose CT Reconstruction

Liang, Kaichao; Zhang, Li; Yang, Yirong; Yang, Honggang; Xing, Yuxiang

doi:10.1109/nssmic.2018.8824600

Cited by 9 publications

(9 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Semi-supervised learning falls between unsupervised learning (with no labeled training data) and supervised learning (with only labeled training data). Some of semi-supervised and unsupervised studies reviewed are [39,66,74,[127][128][129][130][131][132][133][134][135][136][137][138][139][140]. For example, [129] proposed an unsupervised model-based deep learning (MBDL) for LDCT reconstruction.…”

Section: Applications In Semi-supervised/unsupervised Mannermentioning

confidence: 99%

The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review

Zhang

Yang

Shi

2022

Complex Intell. Syst.

View full text Add to dashboard Cite

Conventional reconstruction techniques, such as filtered back projection (FBP) and iterative reconstruction (IR), which have been utilised widely in the image reconstruction process of computed tomography (CT) are not suitable in the case of low-dose CT applications, because of the unsatisfying quality of the reconstructed image and inefficient reconstruction time. Therefore, as the demand for CT radiation dose reduction continues to increase, the use of artificial intelligence (AI) in image reconstruction has become a trend that attracts more and more attention. This systematic review examined various deep learning methods to determine their characteristics, availability, intended use and expected outputs concerning low-dose CT image reconstruction. Utilising the methodology of Kitchenham and Charter, we performed a systematic search of the literature from 2016 to 2021 in Springer, Science Direct, arXiv, PubMed, ACM, IEEE, and Scopus. This review showed that algorithms using deep learning technology are superior to traditional IR methods in noise suppression, artifact reduction and structure preservation, in terms of improving the image quality of low-dose reconstructed images. In conclusion, we provided an overview of the use of deep learning approaches in low-dose CT image reconstruction together with their benefits, limitations, and opportunities for improvement.

show abstract

Section: Applications In Semi-supervised/unsupervised Mannermentioning

confidence: 99%

The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review

Zhang

Yang

Shi

2022

Complex Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…22 Liang et al reconstructed computed tomography (CT) images using three algorithms and reported improved root mean squared error and structure similarity index compared with the values measured in original CT images. 23 Hu compared a GAN, CNN, and modified GAN using Wasserstein distance and reported that the latter was most effective in the noise reduction from CBCT images. 24 Hegazy reported improved the relative error by 5.7%, and the standardized absolute difference by 8.2% using modified U-net algorithm compared to the conventional method.…”

Section: ) Image Quality Enhancementmentioning

confidence: 99%

Application of Deep Learning in Dentistry and Implantology

Kang¹,

Duong²,

Park³

2020

kaomi

View full text Add to dashboard Cite

Artificial intelligence and deep learning algorithms are infiltrating various fields of medicine and dentistry. The purpose of the current study was to review literatures applying deep learning algorithms to the dentistry and implantology. Electronic literature search through MEDLINE and IEEE Xplore library database was performed at 2019 October by combining free-text terms and entry terms associated with 'dentistry' and 'deep learning'. The searched literature was screened by title/abstract level and full text level. Following data were extracted from the included studies: information of author, publication year, the aim of the study, architecture of deep learning, input data, output data, and performance of the deep learning algorithm in the study. 340 studies were retrieved from the databases and 62 studies were included in the study. Deep learning algorithms were applied to tooth localization and numbering, detection of dental caries/periodontal disease/ periapical disease/oral cancerous lesion, localization of cephalometric landmarks, image quality enhancement, prediction and compensation of deformation error in additive manufacturing of prosthesis. Convolutional neural network was used for periapical radiograph, panoramic radiograph, or computed tomography in most of included studies. Deep learning algorithms are expected to help clinicians diagnose and make decisions by extracting dental data, detecting diseases and abnormal lesions, and improving image quality.

show abstract

“…By downsampling the total number of acquired projections, the radiation dose received by patients could be dramatically reduced. In the low-milliampere-seconds scanning method, the tube output is reduced, and the noise of the CT images is substantially elevated (2)(3)(4). However, sparse-view CT images reconstructed from the conventional filtered backprojection (FBP) algorithm experience strong streaking artifacts and a loss of anatomical structure due to angular undersampling.…”

Section: Introductionmentioning

confidence: 99%

Attention-based dual-branch deep network for sparse-view computed tomography image reconstruction

Gao¹,

Su²,

Zhang³

et al. 2023

Quant Imaging Med Surg

View full text Add to dashboard Cite

Background: The widespread application of X-ray computed tomography (CT) imaging in medical screening makes radiation safety a major concern for public health. Sparse-view CT is a promising solution to reduce the radiation dose. However, the reconstructed CT images obtained using sparse-view CT may suffer severe streaking artifacts and structural information loss. Methods: In this study, a novel attention-based dual-branch end-to-end deep network based on the attention mechanism. More specifically, an attention-based dual-branch network (ADB-Net) is proposed to solve the problem of CT image reconstruction. In this network, downsampled sinogram input is processed through 2 parallel branches (CT branch and signogram branch) of the ADB-Net to independently extract the distinct, high-level feature maps. These feature maps are fused in a specified attention module from 3 perspectives (channel, plane, and spatial) to allow complementary optimizations that can mitigate the streaking artifacts and the structure loss in sparse-view CT imaging. Results: Numerical simulations, an anthropomorphic thorax phantom, and in vivo preclinical experiments were conducted to verify the sparse-view CT imaging performance of the ADB-Net. The proposed network achieved a root-mean-square error (RMSE) of 20.6160, a structural similarity (SSIM) of 0.9257, and a peak signal-to-noise ratio (PSNR) of 38.8246 on numerical data. The visualization results demonstrate that this newly developed network can consistently remove the streaking artifacts while maintaining the fine structures. Conclusions: The proposed attention-based dual-branch deep network, ADB-Net, provides a promising alternative to reconstruct high-quality sparse-view CT images for low-dose CT imaging.

show abstract

A Self-supervised Deep Learning Network for Low-Dose CT Reconstruction

Cited by 9 publications

References 11 publications

The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review

The use of deep learning methods in low-dose computed tomography image reconstruction: a systematic review

Application of Deep Learning in Dentistry and Implantology

Attention-based dual-branch deep network for sparse-view computed tomography image reconstruction

Contact Info

Product

Resources

About