AI Blog

Communicating with patients in the age of online portals

Christoph Becker December 2022

Future generations of patients are very likely to get more involved in decisions regarding their healthcare according to the motto “nothing about me without me”. The deployment of electronic patient portals increasingly allows patients throughout Europe to consult and share their medical data, including radiology reports and images, securely and timely online. Technical solutions and rules for releasing reports and

Considerations for AI clinical impact in oncologic imaging

Luis Martí-Bonmatí November 2022

Artificial Intelligence for Health Imaging (AI4HI) is a network of 5 large EU-funded research projects (Chaimeleon, EuCanImage, INCISIVE, ProCancer-I, PRIMAGE), consisting of more than 120 institutions from 20 countries. This network is currently collecting images from more than 91,000 patients with different types of cancer and is working on artificial intelligence (AI) solutions that will be trained and validated on

Deep Learning–driven classification of external DICOM studies for PACS archiving

European Radiology November 2022

The authors of this study used a deep learning-based approach, MOdality Mapping and Orchestration (MOMO), to deal with potential issues that are caused when patients switch hospitals throughout the course of their treatment. These changes result in the staff at the new hospital, consisting of dedicated medical-technical personnel, being tasked with the processing and archiving of external DICOM studies. This

AI for radiological paediatric fracture assessment

Susan Shelmerdine November 2022

Fractures in children are common, sometimes subtle and can signify underlying child abuse. They present unique challenges, given the different appearances of the growing skeleton at different ages. In this systematic review, the authors reviewed the available literature on the use of AI for paediatric fracture detection. Additional Key points: Few articles (n=9) were available for review regarding paediatric fracture

The role of generative adversarial networks in brain MRI

Hazrat Ali, Zubair Shah November 2022

Magnetic Resonance Imaging (MRI) is a widely used medical imaging technology that is non-intrusive and considered safe for humans and can generate different modalities of an image, as well as provide valuable insights into a specific disease. The frequent sequences of MRI are T1-weighted and T2- weighted scans. The popularity of artificial intelligence (AI) for brain MRI is on the

Survey of ESR members looks at radiologists’ practical experience with AI

Christoph Becker October 2022

To obtain an impression of the current practical clinical experience of radiologists from different European countries with artificial intelligence (AI)-powered tools, the European Society of Radiology (ESR) conducted a survey among its members. Out of a total of 690 respondents, there were 276 radiologists from 229 institutions in 32 countries who responded that they had practical clinical experience with an

AI system for detecting COVID-19 on chest radiographs in symptomatic patients

European Radiology October 2022

Due to the challenges associated with differentiating COVID-19 from the number of respiratory infections that can appear on chest radiographs (CXR), the authors of this study developed and validated an AI system for COVID-19 detection on presenting CXR. This was achieved by training a deep learning model on nearly 170,000 CXRs, and was subsequently validated on a large international test

MRI-based radiomics to predict response in locally advanced rectal cancer

European Radiology Experimental October 2022

The study aimed to implement and externally validate an MRI-based radiomics pipeline in order to predict the response to treatment of locally advanced rectal cancer (LARC), while also investigating the impact of manual and automatic segmentations on said radiomics models. The authors were able to show that radiomics models can help clinicians in the prediction of tumor response to chemoradiotherapy

Radiologists with and without deep learning–based computer-aided diagnosis

Shoji Kido October 2022

When radiologists encounter pulmonary nodules/masses in computed tomography (CT) images, they diagnose malignancy based on lesion characteristics (e.g., spiculation and calcification). However, accurate characterization requires careful observation and can be difficult, especially for inexperienced radiologists. In addition, the assessments may vary among radiologists, resulting in the low reproductivity of findings. We investigated if commercially-available deep learning (DL)-based computer-aided diagnosis (CAD)

Differentiating lesions presenting as calcifications with AI

European Radiology October 2022

The authors of this study aimed to evaluate how artificial intelligence computer-aided detection (AI-CAD) differentiates lesions presenting as calcifications, subsequently comparing its performance to that of an experienced breast radiologist. The authors discovered that AI-CAD showed similar diagnostic performances to the radiologists regarding calcifications detected in mammography. Key points Among calcifications with same morphology or BI-RADS assessment, those with positive

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

Latest posts