Dear Enterprise Imaging Insider,
As the global radiology community continues to explore the potential role of diagnostic imaging in fighting the COVID-19 pandemic, a number of efforts are underway in Europe to develop an evidence base, facilitate education, and even drive the development of software to help detect, assess, and monitor this devastating disease.
In the U.K., for example, the British Society of Thoracic Imaging has launched a new COVID-19 imaging repository and database. This timely initiative aims to quickly disseminate clinical and diagnostic advice to healthcare staff. In addition, the European Society of Radiology recently held a webinar on the clinical presentation of COVID-19 respiratory failure. Dr. Nicola Sverzellati of the academic hospital of Parma in Italy shared his institution's experience in managing the pandemic.
Meanwhile, a European campaign is also underway to develop a deep learning-based model for automated detection and quantification of lung involvement of COVID-19 on chest CT. So far, approximately 30 partners have indicated their willingness to share data and to support the plan to train the algorithm.
A team of researchers from six institutions recently shared a list of best practices for radiology departments in handling COVID-19 cases and to help protect hospital staff and patients. U.K. experts also urged radiology departments to actively prepare for the crisis.
In other enterprise imaging news, Arun Gill of market intelligence firm Signify Research reported that artificial intelligence offers a significant opportunity for teleradiology vendors. Several barriers still need to be overcome, however.
Also, stay tuned for a feature we'll be publishing on 7 April on software developer Smart Reporting, the winner of the Best New Radiology Vendor award in the 2020 EuroMinnies. Editor-in-Chief Philip Ward spoke with radiologist and CEO Prof. Dr. Wieland Sommer on a wide range of topics, including adaptations made by the company in the era of COVID-19.
If you have any tips or suggestions for topics you'd like to see covered in the Enterprise Imaging Community, please feel free to drop me a line.
![A normal mammogram confirmed by three-year radiologic follow-up illustrates reader-marked regions of interest (ROIs) during (A) unaided (round 1) and (B) artificial intelligence (AI)–assisted (round 2) reading. Each colored dot represents an ROI for recall by a human reader. Readers could mark more than one ROI per case, represented by multiple dots of the same color. During AI-assisted reading, the AI system displayed three visible prompts: two with suspicion of malignancy scores of 35% (left mediolateral oblique [L MLO] and craniocaudal [L CC]) and one with a suspicion of malignancy score of 10% (right craniocaudal [R CC]), shown as polygonal overlays. Without AI, six of 10 readers (60%) marked a false-positive ROI. With AI assistance, this fell to two of 10 (20%). R MLO = right mediolateral oblique.](https://img.auntminnieeurope.com/mindful/smg/workspaces/default/uploads/2026/07/2026-07-14-radiology-mammogram-ai-auto-bias.H0bYO8QlWs.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
