European Congress of Radiology 2020
July 15 - 19, 2020, Austria Center Vienna, Wien, Austria
Visit us at Booth #G03 on the First Level - Expo Gallery!
The ECR 2020 may have been postponed until July 15th, but there is no reason you can't stay up to date on the latest research in radiology. Learn more about the latest developments in our diagnostic support solutions. Want to know more about STATdx and RADPrimer? Contact us here for more information.
ECR 2020 article collection
View our special collection of articles published in Elsevier’s radiology, radiography, nuclear medicine and medical physics journals. All articles in the collection are free to access online until July 15th 2020.
Natural language is ubiquitous in the workflow of medical imaging. Radiologists create and consume free text in their daily work, some of which can be amenable to enhancements through automatic processing. Recent advancements in deep learning and “artificial intelligence” have had a significant positive impact on natural language processing (NLP). This article discusses the history of how researchers have extracted data and encoded natural language information for analytical processing, starting from NLP's humble origins in hand-curated, linguistic rules. The evolution of medical NLP including vectorization, word embedding, classification, as well as its use in automated speech recognition, are also explored. Finally, the article will discuss the role of machine learning and neural networks in the context of significant, if incremental, improvements in NLP.
Ultrasound contrast agents have been used for decades in Europe and Asia for cardiac and abdominal imaging and are now being more commonly utilized in the United States for radiology applications. Our article reviews the basics of contrast-enhanced ultrasound including how the contrast agent works, advantages and disadvantages, as well as pearls and pitfalls to help the radiologist efficiently integrate this technology into day-to-day clinical practice. We also discuss the diagnosis of focal hepatic lesions as well as off-label applications such as evaluation of renal masses.
Although pioneering, most of the evidence is of a low level, having been obtained retrospectively and in single centres. Studies applying ML to build neuro-oncology monitoring biomarker models have yet to show an overall advantage over those using traditional statistical methods. Development and validation of ML models applied to neuro-oncology require large, well-annotated datasets, and therefore multidisciplinary and multi-centre collaborations are necessary.
Diagnostic and Interventional Imaging
Annotated normal CT data of the abdomen for deep learning: Challenges and strategies for implementation
A reliable data collection/annotation process for abdominal structures was developed. This process can be used to generate large datasets appropriate for deep learning.
European Journal of Radiology
Artificial intelligence is a hot topic in medical imaging. The development of deep learning methods and in particular the use of convolutional neural networks (CNNs), have led to substantial performance gain over the classic machine learning techniques. Multiple usages are currently being evaluated, especially for thoracic imaging, such as such as lung nodule evaluation, tuberculosis or pneumonia detection or quantification of diffuse lung diseases. Chest radiography is a near perfect domain for the development of deep learning algorithms for automatic interpretation, requiring large annotated datasets, in view of the high number of procedures and increasing data availability. Current algorithms are able to detect up to 14 common anomalies, when present as isolated findings. Chest computed tomography is another major field of application for artificial intelligence, especially in the perspective of large scale lung cancer screening. It is important for radiologists to apprehend, contribute actively and lead this new era of radiology powered by artificial intelligence. Such a perspective requires understanding new terms and concepts associated with machine learning. The objective of this paper is to provide useful definitions for understanding the methods used and their possibilities, and report current and future developments for thoracic imaging. Prospective validation of AI tools will be required before reaching routine clinical implementation.
European Journal of Radiology Open
Comparative analysis between synthetic mammography reconstructed from digital breast tomosynthesis and full-field digital mammography for breast cancer detection and visibility
Diagnostic performances of 2DSM and FFDM images were comparable for detecting breast cancers, and it is possible that 2DSM may eliminate the need for additional FFDM during DBT-based imaging due to advances in image reconstruction methods.
Journal of the American College of Radiology
Our results demonstrate performance inconsistency across the data sets and models, indicating that the high performance of deep learning models on one data set cannot be readily transferred to unseen external data sets, and these models need further assessment and validation before being applied in clinical practice.
Journal of Neuroradiology
New OFSEP recommendations for MRI assessment of multiple sclerosis patients: special consideration for gadolinium deposition and frequent acquisitions
New multiple sclerosis (MS) disease-modifying therapies (DMTs), which exert beneficial effects through prevention of relapse, limitation of disability progression, and improvement of patients’ quality of life, have recently emerged. Nonetheless, these DMTs are not without associated complications (severe adverse events like. progressive multifocal leukoencephalopathy). Patient follow-up requires regular clinical evaluations and close monitoring with magnetic resonance imaging (MRI). Detection of new T2 lesions and potential brain atrophy measurements contribute to the evaluation of treatment effectiveness. Current MRI protocols for MS recommend the acquisition of an annual gadolinium (Gd) enhanced MRI, resulting in administration of high volume of contrast agents over time and Gd accumulation in the brain.
Journal of Vascular and Interventional Radiology
Safety of Therapeutic Anticoagulation with Low-Molecular-Weight Heparin or Unfractionated Heparin Infusion during Catheter-Directed Thrombolysis for Acute Pulmonary Embolism
To examine the safety of therapeutic-dose anticoagulation during catheter-directed thrombolysis (CDT) for acute pulmonary embolism (PE).
Size-specific dose estimations for pediatric chest, abdomen/pelvis and head CT scans with the use of GATE
The purpose of this study is to create an organ dose database for pediatric individuals undergoing chest, abdomen/pelvis, and head computed tomography (CT) examinations, and to report the differences in absorbed organ doses, when anatomical differences exist for pediatric patients.
Interventional radiology (IR) has come of age and is a core and innovative specialty within modern medicine. It has also served as a fulcrum for change in many allied sciences. The pace of change has challenged modern health structures and close intra- and inter-disciplinary collaboration has been fundamental to our progress. Within radiology units there is a requirement for a diverse multi-stakeholder contribution that successfully delivers IR care; including but not limited to radiology and radiography working in a seamless collaboration. As the cornerstone of modern IR, it is timely that the Cardiovascular and Interventional Radiological Society of Europe (CIRSE) and the European Federation of Radiographer Societies (EFRS) issue a consensus statement that reflects our members' shared perspective on safe, high quality care and our future direction.