Chief Scientist Office Scotland and British Heart Foundation.
Machine learning methods offer great promise for fast and accurate detection and prognostication of coronavirus disease 2019 (COVID-19) from standard-of-care chest radiographs (CXR) and chest computed tomography (CT) images. Many articles have been published in 2020 describing new machine learning-based models for both of these tasks, but it is unclear which are of potential clinical utility. In this systematic review, we consider all published papers and preprints, for the period from 1 January 2020 to 3 October 2020, which describe new machine learning models for the diagnosis or prognosis of COVID-19 from CXR or CT images. All manuscripts uploaded to bioRxiv, medRxiv and arXiv along with all entries in EMBASE and MEDLINE in this timeframe are considered. Our search identified 2,212 studies, of which 415 were included after initial screening and, after quality screening, 62 studies were included in this systematic review. Our review finds that none of the models identified are of potential clinical use due to methodological flaws and/or underlying biases. This is a major weakness, given the urgency with which validated COVID-19 models are needed. To address this, we give many recommendations which, if followed, will solve these issues and lead to higher-quality model development and well-documented manuscripts.
Inflammation is a determinant of atherosclerotic plaque rupture, the event leading to most myocardial infarctions and strokes. Although conventional imaging techniques identify the site and severity of luminal stenosis, the inflammatory status of the plaque is not addressed. Positron emission tomography imaging of atherosclerosis using the metabolic marker fluorodeoxyglucose allows quantification of arterial inflammation across multiple vessels. This review sets out the background and current and potential future applications of this emerging biomarker of cardiovascular risk, along with its limitations.
Background-Atherosclerotic plaque rupture is usually a consequence of inflammatory cell activity within the plaque.Current imaging techniques provide anatomic data but no indication of plaque inflammation. The current "gold standard" imaging technique for atherosclerosis is x-ray contrast angiography, which provides high-resolution definition of the site and severity of luminal stenoses, but no information about plaque inflammation.There is a need to quantify plaque inflammation to predict the risk of plaque rupture and to monitor the effects of atheroma-modifying therapies. This is important because recent experimental and clinical studies strongly suggest that hepatic hydroxymethyl glutaryl coenzyme A reductase inhibitors (statins) promote plaque stability by decreasing plaque macrophage content and activity without substantially reducing plaque size and therefore angiographic appearance. 4 [ 18 F]-fluorodeoxyglucose ( 18 FDG) is a glucose analogue that is taken up by cells in proportion to their metabolic activity. 5 We tested the hypothesis that plaque inflammation could be visualized and quantified non-invasively using 18 FDG-PET in patients with symptomatic carotid artery disease. Methods Patient RecruitmentWe recruited 8 patients who had experienced a recent carotidterritory transient ischemic attack and had an internal carotid artery stenosis of at least 70%. Patients were excluded if they had either carotid artery occlusion or diabetes. The study protocol was approved by the local ethics committee and the UK Administration of Radioactive Substances Advisory Committee. All patients gave written informed consent. PET ProtocolPET was carried out using a GE Advance PET scanner (GE Medical Systems). We administered 370 MBq 18 FDG intravenously over 60 seconds. PET images (as 4ϫ5 minute frames) were acquired in 3D mode, at 190 (Ϯ6) minutes after 18 FDG administration. This timepoint was chosen after preliminary dynamic studies indicated that late imaging provided optimal contrast between the 18 FDG concentration in plaque and the main background region, namely blood.A stiff cervical collar was worn to minimize patient movement. PET images were reconstructed using the 3D reprojection algorithm, 6 with corrections applied for attenuation, dead time, scatter, and random coincidences. Rigid body co-registration with CT was performed, using a combination of fiducial markers and internal anatomical landmarks (spinal cord and muscles of the jaw and neck). This resulted in co-registration typically to within 1 mm in each dimension around the stenosis. To estimate plaque 18 FDG concentration, three-dimensional volumes of interest (VOI) were drawn CT ProtocolUsing a GE Hispeed Advantage CT scanner (GE Medical Systems), helical contrast CT angiograms were acquired from skull base to 3 cm below the level of the carotid bifurcation. Plaque HistologyAfter imaging, carotid endarterectomy samples from all 8 patients imaged were fixed and stained with hematoxylin and eosin. Immunohistochemistry was performed using anti-macr...
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.