Dear AuntMinnieEurope Member,
Spare a thought for the 15 radiology trainees at Westmead Hospital in Sydney. Just when they require stability and expert supervision, they face an uncertain future after the radiology department lost its training accreditation.
This might happen elsewhere in the months and years ahead. Training schemes across the globe are under intense pressure as a result of the pandemic, and the increasing emphasis on radiology workload and volume is creating extra tension and difficulties.
Further evidence of Dr. László Tabár's remarkable longevity and vision came to light this week, when we posted an interview with him about breast artificial intelligence (AI). He acknowledges the great potential of AI, but he also has some reservations. Find out more in the Women's Imaging Community.
Like many of us, Dr. Giles Maskell has loved the action from the Tokyo Olympics, and he's wondering whether a radiology Olympics might be feasible. In a light-hearted column, he proposes several possible events, including speed reporting, cherry-picking, and the surgical conversation.
After three exhausting weeks in the polyclinic, chief radiologist Dr. Yukihisa Saida and his team must be enjoying some rest and relaxation before the start of the Paralympics on 24 August. Soon after Sunday's closing ceremony, he spoke to us again about the imaging of the Games. Learn more in the MRI Community.
Last but not least, a new study in the British Journal of Cancer caught our attention. Chinese authors have used deep learning to identify hepatocellular carcinoma on liver CT exams with a level of accuracy comparable to radiologists.
![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)
