Erik L. Ridley[email protected]MRIGadolinium levels increase sharply in Tokyo riversThe amount of gadolinium found in rivers around Tokyo has risen sharply over the last two decades, in line with a rapid proliferation of MRI scanners and an increasingly aging population that receives more contrast-enhanced exams, according to research published in the May issue of Marine Pollution Bulletin.May 27, 2020PACS/VNAAt-home PACS workstations enable social distancingRadiology departments can rapidly transition to mostly remote interpretations by radiologists at home during the COVID-19 pandemic, but they will need to navigate a number of difficult challenges along the way, according to a clinical perspective published online May 21 in the American Journal of Roentgenology.May 21, 2020CTCan machine-learning models predict IR outcomes?Machine-learning algorithms can utilize nonimaging data such as patient demographics and prior medical history to predict outcomes from interventional radiology (IR) procedures, according to research published online May 4 in the Journal of Vascular and Interventional Radiology.May 21, 2020CTAI can detect, quantify traumatic brain injury on CTAn artificial intelligence (AI) algorithm was able to help accurately detect traumatic brain injury (TBI) on head CT exams, as well as assess the type of injury, quantify lesion burden, and measure lesion progression, U.K. researchers reported in an article published online May 14 in Lancet Digital Health.May 19, 2020AIAI can differentiate normal, abnormal chest x-raysArtificial intelligence (AI) algorithms can differentiate normal and abnormal chest radiographs with an accuracy on par with experienced radiologists, enabling triage of these studies for priority review, according to research published online May 14 in npj Digital Medicine.May 18, 2020Advanced VisualizationAI-based image reconstruction poses challengesThe use of deep learning to enhance image reconstruction has been considered to be a key application for artificial intelligence (AI) in radiology. A multinational team of researchers is warning, however, that the technology is prone to instability issues that could potentially even lead to a wrong diagnosis.May 14, 2020CTNvidia unveils new CT AI models for COVID-19Graphics processing unit technology developer Nvidia has introduced two new artificial intelligence (AI) models trained to provide lung segmentation and detection of COVID-19 on CT exams. The company is making these models available to researchers to facilitate the development of new predictive AI algorithms.May 14, 2020AIFree AI software can help triage COVID-19 on x-rayA free commercial artificial intelligence (AI) software application can perform comparably to radiologists in triaging suspected COVID-19 cases on chest radiographs, according to research published online May 8 in Radiology.May 12, 2020MRIBowel abnormalities found in COVID-19 patientsAbdominal imaging of COVID-19 patients has shown that bowel abnormalities, including ischemia, are common findings in these cases, according to research published online May 11 in Radiology. Cholestasis is also frequently present.May 11, 2020AIAI may predict COVID-19 progression on chest x-raysAn artificial intelligence (AI) algorithm can predict how COVID-19 cases will progress based on analysis of baseline chest x-rays, offering potential to help in deciding how to triage these patients, according to a study posted online May 5 as a preprint on medRxiv.org.May 11, 2020Previous PagePage 59 of 389Next PageTop StoriesCT'Habitat' AI model shows promise for stratifying lung nodule disease risk on LDCTThis type of model has an edge on its 2D and radiomics counterparts, researchers reported.MRICE MRI-based radiomics model captures DEB TACE-induced tumor changesUltrasoundPOCUS performs well in assessing pathologic venous congestionCTMachine learning plus CT helps assess severity of COPDUltrasoundActive thyroid surveillance effective, beneficial for older patients
