AI Blog

Impact of machine-learning CT-derived fractional flow reserve for the diagnosis and management of coronary artery disease in the randomized CRESCENT trials

European Radiology August 2020

In this observational cohort study, the authors aimed to determine the potential impact of machine learning (ML) CT-derived fractional flow reserve (CT-FFR) on the diagnostic efficiency and effectiveness of coronary CT angiography (CCTA) in patients with obstructive coronary artery disease (CAD). It was found that the implementation of on-site CT-FFR may change management and help to improve diagnostic efficiency and

AI abstracts from ECR 2019: analysis of topics and compliance with the STARD for abstracts checklist

Daniel Pinto dos Santos August 2020

New machine learning techniques, especially deep neural networks, hold the promise of revolutionizing many aspects of radiology and have gained immense public and professional attention over the last few years. This has led to a sharp increase in publications, the founding of new journals, and FDA approval for new diagnostic algorithms. With this increased scientific output, we wanted to take

Diagnostic accuracy and potential covariates for machine learning to identify IDH mutations in glioma patients: evidence from a meta-analysis

European Radiology August 2020

The goal of this study was to assess the diagnostic accuracy of machine learning in the prediction of isocitrate dehydrogenase (IDH) mutations, particularly in patients with glioma, as well as to identify potential covariates that may have an influence on the diagnostic performance of machine learning. The authors were able to show that machine learning demonstrated excellent diagnostic performance in

AI for reading screening mammograms: the need for circumspection

Philippe Autier July 2020

AI is viewed as an emerging technology for reading screening mammograms. However, most studies done so far have adopted retrospective designs that cannot fully appreciate the added value and limitations of AI technologies (Autier et al, Eur Radiol 2020, Apr 21). For instance, these studies cannot inform on numbers and results of biopsies that would have been done following a

Deep learning for the determination of myometrial invasion depth and automatic lesion identification in endometrial cancer MR imaging

He Zhang July 2020

Endometrial cancer (EC) has the highest rate of malignancy in women in the entire world, including China, which has the largest population. Accurately staging EC prior to an invasive procedure still poses a challenge for clinicians. In the present study, we used more than five hundred EC patients’ MR images to train the computer to establish a deep learning diagnostic

Can training data help radiologists to open deep learning black box?

Marina Codari July 2020

Deep learning has recently pervaded the radiology field, reaching promising results that have encouraged both scientists and entrepreneurs to apply these models to improve patient care. However, “with great power there must also come — great responsibility” [1]! In most cases, the complexity of deep learning models forces their users, and sometimes also their developers, to treat them as black

Looking outside the box: inspector robots, machine learning helping to catalogue history, and sanitizing work spaces without humans

ESR July 2020

This week in artificial intelligence (AI) news, we take a look at systems being utilized for quality control in factories while some workers are in quarantine, cataloguing print media over the past 200 years using machine learning technology, and robotics in Boston helping local organizations to sanitize their workplaces during the COVID-19 pandemic. The rise of the COVID-19 pandemic has

Automated classification of solid renal masses on contrast-enhanced computed tomography images using convolutional neural network with decision fusion

European Radiology July 2020

The purpose of this study was to develop a deep learning-based method for the automated classification of renal cell carcinoma (RCC) from benign solid renal masses using contrast-enhanced computed tomography (CECT) images. The authors determined that a semi-automated majority voting convolutional neural network (CNN) based methodology enabled the accurate classification of RCC from benign neoplasms among solid renal masses on

Development and validation of machine learning prediction model based on computed tomography angiography–derived hemodynamics for rupture status of intracranial aneurysms: a Chinese multicenter study

Guo Zhong Chen June 2020

Decisions regarding the optimal management of unruptured intracranial aneurysms (UIAs) depend on a comprehensive comparison of the risks between aneurysm rupture and interventional treatment. The accurate prediction for UIA rupture risk is important for clinicians and patients. Our study further proves that the hemodynamic parameters can improve prediction performance for rupture status of UIAs. Moreover, the AUC of model integrating

Looking outside the box: facial recognition to enforce wearing masks, robotics saving coral reefs, and virtual partners during quarantine

ESR June 2020

This week in artificial intelligence (AI) news, we take a look at facial recognition technology being used to monitor citizens and whether or not they are following best health practices during the COVID-19 pandemic, the potential of robotics and AI to help save the disappearing coral reefs, and an augmented/virtual reality app to help solve the loneliness crisis. In the

Welcome to the blog on Artificial Intelligence of
the European Society of Radiology

Latest posts