Deep learning image reconstruction algorithm reduces image noise while alters radiomics features in dual-energy CT in comparison with conventional iterative reconstruction algorithms: a phantom study

Zhong, Jingyu; Xia, Yunyan; Chen, Yong; Li, Jianying; Lü, Wei; Shi, Xiaomeng; Feng, Jianxing; Yan, Fuhua; Yao, Weiwu; Zhang, Huan

doi:10.1007/s00330-022-09119-1

Cited by 18 publications

(6 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radiomics is a rapidly evolving field in medical imaging, and studies have confirmed its applications and potential in guiding clinical decision-making and precision medicine [ 25 ]. Radiomics-based carotid artery CTA methodologies are an objective and effective means of assessing carotid atherosclerotic plaques and stratifying related risk [ 35 ].…”

Section: Discussionmentioning

confidence: 99%

“…Radiomics have been utilized to effectively predictive the risk of ischemic stroke based on quantitative analyses of intraplaque compositions [ [21] , [22] , [23] ]. Although radiomic features can still be affected by low pixel density in a region of interest, deep learning-based image reconstruction can significantly improve the robustness of important radiomic features [ 24 , 25 ].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving radiomic modeling for the identification of symptomatic carotid atherosclerotic plaques using deep learning-based 3D super-resolution CT angiography

Wang,

Guo,

Wang

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Improving radiomic modeling for the identification of symptomatic carotid atherosclerotic plaques using deep learning-based 3D super-resolution CT angiography

Wang,

Guo,

Wang

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…All the guidelines did not recommend reducing the dose of ICM for high-risk patients at expense of image quality, but it might be reasonable to use the minimum amount of contrast media to satisfy the diagnostic efficacy. Further studies are encouraged to apply advanced acquisition and reconstruction techniques to reduce the requisite ICM dose [ 53 – 56 , 62 ]. A promising measure of systemic ICM exposure is the contrast-dose/absolute GFR ratio [ 57 ].…”

Section: Discussionmentioning

confidence: 99%

Just give the contrast? Appraisal of guidelines on intravenous iodinated contrast media use in patients with kidney disease

Zhong,

Chen,

Xing

et al. 2024

Insights Imaging

Self Cite

View full text Add to dashboard Cite

Objective To appraise the quality of guidelines on intravenous iodinated contrast media (ICM) use in patients with kidney disease, and to compare the recommendations among them. Methods We searched four literature databases, eight guideline libraries, and ten homepages of radiological societies to identify English and Chinese guidelines on intravenous ICM use in patients with kidney disease published between January 2018 and June 2023. The quality of the guidelines was assessed with the Scientific, Transparent, and Applicable Rankings (STAR) tool. Results Ten guidelines were included, with a median STAR score of 46.0 (range 28.5–61.5). The guidelines performed well in “Recommendations” domain (31/40, 78%), while poor in “Registry” (0/20, 0%) and “Protocol” domains (0/20, 0%). Nine guidelines recommended estimated glomerular filtration rate (eGFR) < 30 mL/min/1.73 m2 as the cutoff for referring patients to discuss the risk-benefit balance of ICM administration. Three guidelines further suggested that patients with an eGFR < 45 mL/min/1.73 m2 and high-risk factors also need referring. Variable recommendations were seen in the acceptable time interval between renal function test and ICM administration, and that between scan and repeated scan. Nine guidelines recommended to use iso-osmolar or low-osmolar ICM, while no consensus has been reached for the dosing of ICM. Nine guidelines supported hydration after ICM use, but their protocols varied. Drugs or blood purification therapy were not recommended as preventative means. Conclusion Guidelines on intravenous ICM use in patients with kidney disease have heterogeneous quality. The scientific societies may consider joint statements on controversial recommendations for variable timing and protocols. Critical relevance statement The heterogeneous quality of guidelines, and their controversial recommendations, leave gaps in workflow timing, dosing, and post-administration hydration protocols of contrast-enhanced CT scans for patients with kidney diseases, calling for more evidence to establish a safer and more practicable workflow. Key points • Guidelines concerning iodinated contrast media use in kidney disease patients vary. • Controversy remains in workflow timing, contrast dosing, and post-administration hydration protocols. • Investigations are encouraged to establish a safer iodinated contrast media use workflow. Graphical Abstract

show abstract

“…Deep learning algorithms can effectively reduce noise in medical images, leading to improved image quality and diagnostic confidence (20). For instance, in low-dose CT scans, where noise levels are inherently high, deep learning models can be trained to suppress noise while preserving critical image details (21).…”

Section: Deep Learning Transforms Medical Imaging: Unveiling Applicat...mentioning

confidence: 99%

Synergizing photon-counting CT with deep learning: potential enhancements in medical imaging

Mese,

Altintas Taslicay,

Sivrioglu

2023

Acta Radiol

View full text Add to dashboard Cite

This review article highlights the potential of integrating photon-counting computed tomography (CT) and deep learning algorithms in medical imaging to enhance diagnostic accuracy, improve image quality, and reduce radiation exposure. The use of photon-counting CT provides superior image quality, reduced radiation dose, and material decomposition capabilities, while deep learning algorithms excel in automating image analysis and improving diagnostic accuracy. The integration of these technologies can lead to enhanced material decomposition and classification, spectral image analysis, predictive modeling for individualized medicine, workflow optimization, and radiation dose management. However, data requirements, computational resources, and regulatory and ethical concerns remain challenges that need to be addressed to fully realize the potential of this technology. The fusion of photon-counting CT and deep learning algorithms is poised to revolutionize medical imaging and transform patient care.

show abstract

Deep learning image reconstruction algorithm reduces image noise while alters radiomics features in dual-energy CT in comparison with conventional iterative reconstruction algorithms: a phantom study

Cited by 18 publications

References 57 publications

Improving radiomic modeling for the identification of symptomatic carotid atherosclerotic plaques using deep learning-based 3D super-resolution CT angiography

Improving radiomic modeling for the identification of symptomatic carotid atherosclerotic plaques using deep learning-based 3D super-resolution CT angiography

Just give the contrast? Appraisal of guidelines on intravenous iodinated contrast media use in patients with kidney disease

Synergizing photon-counting CT with deep learning: potential enhancements in medical imaging

Contact Info

Product

Resources

About