Rationale And Objectives: Generative adversarial networks (GANs) are deep learning models aimed at generating fake realistic looking images. These novel models made a great impact on the computer vision field. Our study aims to review the literature on GANs applications in radiology.
Materials And Methods: This systematic review followed the PRISMA guidelines. Electronic datasets were searched for studies describing applications of GANs in radiology. We included studies published up-to September 2019.
Results: Data were extracted from 33 studies published between 2017 and 2019. Eighteen studies focused on CT images generation, ten on MRI, three on PET/MRI and PET/CT, one on ultrasound and one on X-ray. Applications in radiology included image reconstruction and denoising for dose and scan time reduction (fourteen studies), data augmentation (six studies), transfer between modalities (eight studies) and image segmentation (five studies). All studies reported that generated images improved the performance of the developed algorithms.
Conclusion: GANs are increasingly studied for various radiology applications. They enable the creation of new data, which can be used to improve clinical care, education and research.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.acra.2019.12.024 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Exercise capacity after long-term physical activity on prescription provided by physiotherapists.
Scand J Prim Health Care
January 2025
Unit of Physiotherapy, Department of Health and Rehabilitation, Institute of Neuroscience and Physiology, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.
Research has shown that physical activity on prescription (PAP), used in Swedish healthcare, increases patients' physical activity, but data are lacking regarding the long-term effects of PAP on exercise capacity. Therefor exercise capacity was evaluated in patients with metabolic risk factors, after 4.5 years of PAP treatment provided by physiotherapists in primary healthcare.
View Article and Find Full Text PDFRedefining supplier selection in healthcare sector: a novel framework for supplier classification.
J Health Organ Manag
January 2025
Amrita School of Business - Amritapuri Kollam Campus, Kollam, India.
Purpose: This paper aims to delve into the critical aspect of supplier selection in the healthcare sector, emphasizing the significance of strategic sourcing in enhancing operational efficiency and quality of services. The primary aim is to develop a comprehensive framework for supplier evaluation that aligns with the unique requirements of hospitals, ultimately improving procurement processes and patient care outcomes.
Design/methodology/approach: The study leverages the renowned Carter's 7 C model as a foundational framework for supplier assessment, supplemented by insights gathered from interviews with experts in the New Product Introduction, Purchasing and Procurement departments of a leading hospital in India.
Integrating Retinal Segmentation Metrics with Machine Learning for Predictions from Mouse SD-OCT Scans.
Curr Eye Res
January 2025
Department of Ophthalmology, Edward S. Harkness Eye Institute, Columbia University, Vagelos College of Physicians and Surgeons, New York, NY, USA.
Purpose: This study aimed to initially test whether machine learning approaches could categorically predict two simple biological features, mouse age and mouse species, using the retinal segmentation metrics.
Methods: The retinal layer thickness data obtained from C57BL/6 and DBA/2J mice were processed for machine learning after segmenting mouse retinal SD-OCT scans. Twenty-two models were trained to predict the mouse groups.
A Dual-Pathway Responsive Mechanophore for Intelligent Luminescent Polymer Materials.
J Am Chem Soc
January 2025
Stoddart Institute of Molecular Science, Department of Chemistry, Zhejiang University, Hangzhou 310058, PR China.
Mechanoluminescent units, when integrated into polymer matrices, undergo structural transformations in response to mechanical force, resulting in changes in fluorescence. This phenomenon holds considerable promise for the development of stress-sensing materials. Despite the high demand for robust, tunable mechanoluminescent mechanophores for force assessment and smart force-responsive materials, strategies for their design and synthesis remain underdeveloped.
View Article and Find Full Text PDFCost-Utility Analysis of LifeVest® in Post-Myocardial Infarction Patients at Risk of Sudden Cardiac Death in England.
Pharmacoecon Open
January 2025
Optimax Access Ltd, Kenneth Dibben House, Enterprise Rd, Chilworth, Southampton University Science Park, Southampton, UK.
Background: Patients with a left ventricular ejection fraction ≤ 35% are at increased risk of sudden cardiac death (SCD) within the first months after a myocardial infarction (MI). The wearable cardioverter defibrillator (WCD) is an established, safe and effective solution which can protect patients from SCD during the first months after an MI, when the risk of SCD is at its peak. This study aimed to evaluate the cost-effectiveness of WCD combined with guideline-directed medical therapy (GDMT) compared to GDMT alone, after MI in the English National Health Service (NHS).
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!