AI Blog

COVID-19 open access imaging datasets

ESR May 2020

The European Institute for Biomedical Imaging Research (EIBIR) has recently launched an overview of COVID-19 imaging datasets. Imaging databases and registries are essential for diagnosis in radiology, as well as for the development of artificial intelligence tools for machine-based diagnosis. EIBIR compiled a list of open access COVID-19 repositories and datasets, which can be used for teaching, training and/or research.

Two mobile labs in Romania use XVision in fight against COVID-19

XVision May 2020

Romanian startup XVision is putting its artificial intelligence (AI) solution to use in the fight against COVID-19. Their medical platform, which uses AI to analyse lung radiographs, has become an important part of mobile laboratories set up outside of hospitals in Bucharest and Timisoara. The goal of the software is to be used to identify patients with lung injuries that

Artificial intelligence for detecting small FDG-positive lung nodules in digital PET/CT

European Radiology May 2020

The authors of this study aimed to determine the diagnostic performance of a deep learning algorithm for the automated detection of small 18F-FDG-avid pulmonary nodules in positron emission tomography (PET) scans. Their findings suggest that these machine learning algorithms may be able to aid in the detection of small 18F-FDG-avid pulmonary nodules in clinical PET/CT scans, with artificial intelligence (AI)

First CE-marked image AI solution for chest CT in COVID-19

icometrix April 2020

A group of hospitals (Vrije Universiteit Brussel, UZ Brussel, KU Leuven, UZ Leuven, and UZ Antwerpen), together with icometrix and other organizations, have joined forces in a global initiative to leverage artificial intelligence (AI) in the fight against COVID-19. The multinational collaboration resulted in the development of an AI algorithm, icolung, which received CE-marking for clinical use in Europe. The

Radiomics allows for detection of benign and malignant histopathology in patients with metastatic testicular germ cell tumors prior to post-chemotherapy retroperitoneal Iymph node dissection

Bettina Baeßler April 2020

Among solid tumors, testicular germ cell tumors (TGCT) are the most common entity in men below the age of 40, and they are very likely to metastasize. The so-far unsolved clinical problem for metastasized TGCTs is that as many as 40-50% of patients are overtreated by post-chemotherapy lymph node dissection since the resected lymph nodes show a viable tumor in

Attitudes and perceptions of UK medical students towards artificial intelligence and radiology: a multicentre survey

Daniel Poon April 2020

Our study surveyed 484 medical students from 17 medical schools on their views towards AI. We also explored the current state of AI education in the UK. The majority of students in our cohort felt that medical schools are poorly preparing them in the critical use of novel digital tools underpinned by AI. We feel this is unsurprising given the

Looking outside the box: how AI is being used against COVID-19, fighting bias in writing, and virtual assistants going to work in the UK

ESR April 2020

This week in artificial intelligence (AI) news, we take a look at AI apps being utilized to fight COVID-19 in GCC countries, how technology is trying to eliminate unconscious bias in writing, and Google’s Duplex AI assistant’s mission to contact restaurants and businesses all over the United Kingdom. Countries making up the Gulf Cooperation Council (GCC) have implemented some of

Test-retest reproducibility of a deep learning–based automatic detection algorithm for the chest radiograph

European Radiology April 2020

The authors of this retrospective study performed test-retest reproducibility analyses for a deep learning-based automatic detection algorithm (DLAD) using two stationary chest radiographs with short-term intervals, in order to analyze influential factors on test-retest variations. The test, which included patients with pulmonary nodules resected in 2017, showed that DLAD was robust to the test-retest variation. Key points The deep learning–based

Accurate prediction of responses to transarterial chemoembolization for patients with hepatocellular carcinoma by using artificial intelligence in contrast-enhanced ultrasound

European Radiology April 2020

The aim of this study was to establish and validate an artificial intelligence-based radiomics strategy in order to predict personalized responses to hepatocellular carcinoma (HCC) to first transarterial chemoembolization (TACE) by analyzing contrast-enhanced ultrasound (CEUS) cines quantitatively. This was done using 130 HCC patients, showing that a deep learning-based radiomics method can effectively utilize CEUS, resulting in accurate and personalized

Deep learning workflow in radiology: how to get started

An Tang March 2020

In the past decade, deep learning architectures, which essentially consist of neural networks with numerous layers, have emerged as a dominant class of machine learning algorithms. Owing to the availability of larger datasets in radiology and access to high-performance graphical processing units, deep learning has provided state-of-the-art performance for various computer vision tasks such as lesion detection, segmentation, classification, monitoring,

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

Latest posts