Dear AuntMinnieEurope Member,
Artificial intelligence (AI) is showing great potential as an effective way of replacing a reader in a double-reading breast cancer screening program. That was one of the take-home messages of a research presentation session at ECR 2021 that featured talks from mammography pioneers in Germany, the Netherlands, and France.
A special report on this groundbreaking session is this week's top story. You can read more in the Women's Imaging Community.
Another standout session at the virtual congress was about the first decade of PET/MRI. Around 110 of these scanners have been installed worldwide, of which more than half are located in Europe. How are these systems being used? What are the prospects for the future? Go to the Molecular Imaging Community for some answers.
Global comparisons of radiologists' salaries are rare, so it was no surprise that Tuesday's article on this topic proved very popular. The survey found that Norway has the highest-paid radiologists in Europe, but Dr. Audun Berstad from Oslo has questioned this analysis. Most Norwegian radiologists earn 80,000-100,000 pounds (93,446-116,807 euros) and salaries are state-regulated and the private market is limited, he wrote in our Forums section.
Hospitals and factories could do a better job of recycling their materials, including gadolinium-based contrast agents, according to the authors of a new Swiss study of wastewater plants. They detected high concentrations of gadolinium and other elements. Find out more in the MRI Community.
Last but not least, some AI research from Lausanne, Switzerland, caught our eye. The group looked at the issues you should consider when buying software for radiology, and they've come up with a list of 10 questions that purchasers should ask.
![Overview of the study design. (A) The fully automated deep learning framework was developed to estimate body composition (BC) (defined as subcutaneous adipose tissue [SAT] in liters; visceral adipose tissue [VAT] in liters; skeletal muscle [SM] in liters; SM fat fraction [SMFF] as a percentage; and intramuscular adipose tissue [IMAT] in deciliters) from MRI. The fully automated framework comprised one model (model 1) to quantify different BC measures (SAT, VAT, SM, SMFF, and IMAT) as three-dimensional (3D) measures from whole-body MRI scans. The second model (model 2) was trained to identify standardized anatomic landmarks along the craniocaudal body axis (z coordinate field), which allowed for subdividing the whole-body measures into different subregions typically examined on clinical routine MRI scans (chest, abdomen, and pelvis). (B) BC was quantified from whole-body MRI in over 66,000 individuals from two large population-based cohort studies, the UK Biobank (UKB) (36,317 individuals) and the German National Cohort (NAKO) (30,291 individuals). Bar graphs show age distribution by sex and cohort. BMI = body mass index. (C) After the performance assessment of the fully automated framework, the change in BC measures, distributions, and profiles across age decades were investigated. Age-, sex-, and height-adjusted body composition reference curves were calculated and made publicly available in a web-based z-score calculator (https://circ-ml.github.io).](https://img.auntminnieeurope.com/mindful/smg/workspaces/default/uploads/2026/05/body-comp.XgAjTfPj1W.jpg?auto=format%2Ccompress&dpr=2&fit=crop&h=167&q=70&w=250)
