The use of deep learning towards dose optimization in low-dose computed tomography: A scoping review

Immonen, E.; Wong, Jeannie Hsiu Ding; Nieminen, Miika T.; Kekkonen, L.; Roine, Susanna; Törnroos, Sanna; Lança, Luís; Guan, Feng; Metsälä, Eija

doi:10.1016/j.radi.2021.07.010

Cited by 33 publications

(21 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been shown that the CT value of pulmonary lesions in NP was lower than that in non-NP and may help predict NP early [ 95 ]. In order to reduce radiation damage, recent studies tried to adopt a machine-learning radiomics model based on radiographic features observed on non-enhanced CT scans or low-dose CT scans to recognize pulmonary consolidation in the early stage of NP in children [ 96 , 97 ]. Moreover, studies have found that lower kV combined with high Iterative Reconstruction in the CT pulmonary angiogram can maintain image quality [ 98 , 99 ].…”

Section: Prediction and Early Recognitionmentioning

confidence: 99%

Necrotizing Pneumonia in Children: Early Recognition and Management

Chen

Wang

et al. 2023

JCM

View full text Add to dashboard Cite

Necrotizing pneumonia (NP) is an uncommon complicated pneumonia with an increasing incidence. Early recognition and timely management can bring excellent outcomes. The diagnosis of NP depends on chest computed tomography, which has radiation damage and may miss the optimal treatment time. The present review aimed to elaborate on the reported predictors for NP. The possible pathogenesis of Streptococcus pneumoniae, Staphylococcus aureus, Mycoplasma pneumoniae and coinfection, clinical manifestations and management were also discussed. Although there is still a long way for these predictors to be used in clinical, it is necessary to investigate early predictors for NP in children.

show abstract

Section: Prediction and Early Recognitionmentioning

confidence: 99%

Necrotizing Pneumonia in Children: Early Recognition and Management

Chen

Wang

et al. 2023

JCM

View full text Add to dashboard Cite

show abstract

“…As a result, to solve this issue, a machine learning framework was developed that allowed for reconstructing image parameters and denoising the quality of the image when low radiation was used. This resulted in improved image quality to equate to the regular-dose CT image quality, thus allowing patients to be exposed to less radiation while still obtaining a diagnostic result [ 30 ].…”

Section: Ai: Cardiology Imaging Applicationsmentioning

confidence: 99%

Artificial Intelligence Advances in the World of Cardiovascular Imaging

Patel

Makaryus

2022

Healthcare

View full text Add to dashboard Cite

The tremendous advances in digital information and communication technology have entered everything from our daily lives to the most intricate aspects of medical and surgical care. These advances are seen in electronic and mobile health and allow many new applications to further improve and make the diagnoses of patient diseases and conditions more precise. In the area of digital radiology with respect to diagnostics, the use of advanced imaging tools and techniques is now at the center of evaluation and treatment. Digital acquisition and analysis are central to diagnostic capabilities, especially in the field of cardiovascular imaging. Furthermore, the introduction of artificial intelligence (AI) into the world of digital cardiovascular imaging greatly broadens the capabilities of the field both with respect to advancement as well as with respect to complete and accurate diagnosis of cardiovascular conditions. The application of AI in recognition, diagnostics, protocol automation, and quality control for the analysis of cardiovascular imaging modalities such as echocardiography, nuclear cardiac imaging, cardiovascular computed tomography, cardiovascular magnetic resonance imaging, and other imaging, is a major advance that is improving rapidly and continuously. We document the innovations in the field of cardiovascular imaging that have been brought about by the acceptance and implementation of AI in relation to healthcare professionals and patients in the cardiovascular field.

show abstract

“…4 Usually, by changing the scanning parameters such as tube current, pitch, tube potential/voltage and rotation/exposure time, CT dose reduction can be achieved significantly. While, this may lead to compromised CT image quality in terms of spatial/density contrast and resolution, and may introduce noise and artifacts, 5 which can be reflected by image quality evaluation metrics. 6 Therefore, how to improve the quality of LDCT is of great significance for early disease screening in clinical practice.…”

Section: Introductionmentioning

confidence: 99%

Transfer learning framework for low‐dose CT reconstruction based on marginal distribution adaptation in multiscale

et al. 2023

View full text Add to dashboard Cite

Background: With the increasing use of computed tomography (CT) in clinical practice, limiting CT radiation exposure to reduce potential cancer risks has become one of the important directions of medical imaging research. As the dose decreases, the reconstructed CT image will be severely degraded by projection noise. Purpose: As an important method of image processing, supervised deep learning has been widely used in the restoration of low-dose CT (LDCT) in recent years. However, the normal-dose CT (NDCT) corresponding to a specific LDCT (it is regarded as the label of the LDCT, which is necessary for supervised learning) is very difficult to obtain so that the application of supervised learning methods in LDCT reconstruction is limited. It is necessary to construct a unsupervised deep learning framework for LDCT reconstruction that does not depend on paired LDCT-NDCT datasets. Methods: We presented an unsupervised learning framework for the transferring from the identity mapping to the low-dose reconstruction task, called marginal distribution adaptation in multiscale (MDAM). For NDCTs as source domain data, MDAM is an identity map with two parts: firstly, it establishes a dimensionality reduction mapping, which can obtain the same feature distribution from NDCTs and LDCTs; and then NDCTs is retrieved by reconstructing the image overview and details from the low-dimensional features. For the purpose of the feature transfer between source domain and target domain (LDCTs), we introduce the multiscale feature extraction in the MDAM, and then eliminate differences in probability distributions of these multiscale features between NDCTs and LDCTs through wavelet decomposition and domain adaptation learning. Results: Image quality evaluation metrics and subjective quality scores show that, as an unsupervised method, the performance of the MDAM approaches or even surpasses some state-of -the-art supervised methods. Especially, MDAM has been favorably evaluated in terms of noise suppression, structural preservation, and lesion detection. Conclusions: We demonstrated that, the MDAM framework can reconstruct corresponding NDCTs from LDCTs with high accuracy, and without relying on any labeles. Moreover, it is more suitable for clinical application compared with supervised learning methods.

show abstract

The use of deep learning towards dose optimization in low-dose computed tomography: A scoping review

Cited by 33 publications

References 28 publications

Necrotizing Pneumonia in Children: Early Recognition and Management

Necrotizing Pneumonia in Children: Early Recognition and Management

Artificial Intelligence Advances in the World of Cardiovascular Imaging

Transfer learning framework for low‐dose CT reconstruction based on marginal distribution adaptation in multiscale

Contact Info

Product

Resources

About