Will Morton[email protected]Digital X-RayLLMs excel at scoliosis detection on spine x-raysFor scoliosis detection, Grok 4 led with 94.2% accuracy.May 7, 2026Molecular ImagingPSMA-PET linked to higher use of systemic therapiesARPI therapy was initiated in 15.6% of PSMA-PET patients versus 7.7% of bone scan patients.May 7, 2026InterventionalRadiation segmentectomy can be optimized before liver transplantAs of 2023, yttrium 90 (Y-90) radioembolization has become the most frequently used local-regional therapy in the U.S. for bridging patients with HCC to liver transplant.May 5, 2026Radiation Oncology/TherapyWill upright radiotherapy become a new standard?Multiple commercial upright systems have entered the market in recent years.May 4, 2026Molecular ImagingNET tracers first widened, then closed imaging access gapGa-68 DOTATATE/DOTATOC captured 33.8% market share in its 2017 debut and reached 90.9% by 2020.April 30, 2026Molecular ImagingLu-177 PSMA-SPECT/CT predicts survival in mCRPCLu-177 PSMA-617 SPECT/CT total tumor volume complete response at six weeks associated with overall survival.April 29, 2026AIChildren ‘almost invisible’ in public imaging datasetsAmong 135 datasets with usable age data, children accounted for just 6,026 of 512,608 patients (under 2%).April 27, 2026Molecular ImagingChatGPT matches nuclear medicine experts on FDG-PET/CT scansModels excelled on cases with well-defined metabolic patterns, such as in typical cases of Alzheimer's disease, yet were less accurate on complex cases.April 24, 2026Practice ManagementMusculoskeletal strain affects majority of radiologistsMusculoskeletal strain represents the single largest category of workplace injury in radiology.April 23, 2026InterventionalGAE benefits may just be ‘placebo effect’Patients who received either genicular artery embolization (GAE) or a sham procedure experienced equal pain improvements.April 22, 2026Page 1 of 52Next PageTop StoriesDigital X-RayLLMs excel at scoliosis detection on spine x-raysFor scoliosis detection, Grok 4 led with 94.2% accuracy.HomeExpanding opportunities for interventional radiology practiceCTWelding fumes linked to distinct lung CT changes, functionMolecular ImagingPSMA-PET linked to higher use of systemic therapiesSponsor ContentTurning Innovation into Everyday Efficiency
![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.auntminnie.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)
