🩺 At #CIRSE2026, experts debated whether drug-coated devices should remain routine in leg artery treatment -and what the SWEDEPAD findings could change. #InterventionalRadiology #PeripheralArteryDisease www.auntminnieeurope.com/clinical-new...

At #CIRSE2026, a session put that thinking into practice: specialists created new vascular and biliary pathways, targeted elusive lymphatic leaks and used unconventional access to treat patients with few remaining options. 🩺 👉 Read the full story buff.ly/IrIUDs8

🫁 The discussion on local treatment of lung tumours at #CIRSE2026 centred on patient selection, percutaneous ablation for lung-tissue preservation and same-session biopsy, and the complementary roles of SBRT, ablation and CT-guided brachytherapy. www.auntminnieeurope.com/clinical-new...

An iterative training approach, the expert-guided annotation loop, for efficient reference standard medical image segmentation https://doi.org/10.1148/ryai.250200 @muellerrom.bsky.social #CIRSE2026 #IRad #CVRad #radiology

An algorithmic framework was developed to identify and quantify shortcut learning and bias driven by exposure parameters in chest radiographs, revealing hidden sources of bias in medical artificial intelligence. https://doi.org/10.1148/ryai.250731 #CIRSE2026 #IRad #CVRad #radiology

Benchmarking of AI and Radiologists for Indeterminate Lung Nodule Malignancy Risk Estimation on Screening CT: The LUNA25 Challenge https://doi.org/10.1148/ryai.260179 #CIRSE2026 #IRad #CVRad #radiology

An iterative training approach, the expert-guided annotation loop, for efficient reference standard medical image segmentation https://doi.org/10.1148/ryai.250200 @muellerrom.bsky.social #CIRSE2026 #IRad #CVRad #radiology

An algorithmic framework was developed to identify and quantify shortcut learning and bias driven by exposure parameters in chest radiographs, revealing hidden sources of bias in medical artificial intelligence. https://doi.org/10.1148/ryai.250731 #CIRSE2026 #IRad #CVRad #radiology

Benchmarking of AI and Radiologists for Indeterminate Lung Nodule Malignancy Risk Estimation on Screening CT: The LUNA25 Challenge https://doi.org/10.1148/ryai.260179 #CIRSE2026 #IRad #CVRad #radiology

An expert-guided annotation loop reduced expert annotation time and enabled estimated cost savings while producing high-quality reference standard CT and MRI segmentations https://doi.org/10.1148/ryai.250200 @muellerrom.bsky.social #CIRSE2026 #IRad #CVRad #radiology

Deep learning models trained on CXRs may exploit exposure parameters as shortcut features; exposure-regimen audits may flag high-risk conditions before clinical deployment https://doi.org/10.1148/ryai.250731 #CIRSE2026 #IRad #CVRad #radiology

Results of the LUNA25 Challenge: AI outperforms radiologists in estimating malignancy risk on indeterminate lung nodules on LDCT https://doi.org/10.1148/ryai.260179 #CIRSE2026 #IRad #CVRad #radiology

Impact on Cost and Expert Time of Data-Efficient Deep Learning for Medical Image Segmentation https://doi.org/10.1148/ryai.250200 @muellerrom.bsky.social #CIRSE2026 #IRad #CVRad #radiology

Impact of Exposure Parameters on Deep Learning Models in Chest Radiography and Implications for Deployment https://doi.org/10.1148/ryai.250731 #CIRSE2026 #IRad #CVRad #radiology