The 2026 Chinese lung cancer guideline adds AI and opportunistic screening in low-dose CT, expands molecular testing, and updates treatment regimens for NSCLC, including perioperative, consolidation immunotherapy, and targeted therapy for EGFR, ALK, KRAS, HER2, and MET alteratio…
On 76 test cases, the AI framework achieved Cobb angle MAE 2.4°, Lenke curve type accuracy 0.895, and reduced review time from 8.2 to 1.5 min/case.
PSAD remained below 0.11 ng/mL² across all ages in 1037 healthy German men, contrasting with continuously rising PSA. 95th percentile reference: PV 51.39 mL, PSA 2.79 ng/mL, PSAD 0.071 ng/mL².
A multiphase CT angiography spot sign identified high-risk intracerebral hemorrhage: hematoma expansion occurred in 25/51 (49%) phase-1, 13/28 (46%) phase-2, and 4/9 (44%) phase-3 spots versus 12/71 (17%) with no spot sign.
FDA issues discussion paper on GenAI medical devices
NewVue partners with Strategic Radiology on workflow platform access
Survey: Network disruptions routinely hit imaging workflows
AI fracture detection device validated across three European hospitals
FDA is seeking public comment through Oct. 19 on how to regulate generative AI in medical devices, including risk assessment, premarket evaluation, and postmarket safety monitoring. Radiologist Rick Abramson now leads the Digital Health Center of Excellence.
<![CDATA[Beyond Detection: AI that Evolves Radiology]]>
Rayence launches portable x-ray systems
<![CDATA[Clinical AI Beyond Detection: Extending Radiology’s Impact Across the Care Pathway]]>
Cardiac Masses: Tumors and Mimics
Beyond the Scan: Understanding What Prevents Patients From Coming Back
On wrist MR arthrography, fluid at the distal ulna without contrast leak through the TFCC indicates a high-grade partial tear of the foveal attachment; contrast leak would indicate a complete tear. This is why a primary DRUJ injection is valuable for assessing this area.
Why you must correlate your sequences. This radiocarpal arthrogram shows an intact TFCC surface.
RE Foundation Fuels Research
YOLOv8 and YOLOv11 achieved near-perfect sex classification from hand-wrist radiographs of 1,800 individuals aged 8-18, with F1-scores of 0.99 and 0.98 and AUCs of 0.99 and 0.98; YOLOv5 performed poorly (F1 0.69, AUC 0.61).
Letter to the Editor: Mechanistic and methodological perspectives on genicular artery embolization for knee osteoarthritis.
AI shows promise for making ultrasound more efficient and consistent in Gulf healthcare systems, but real-world implementation demands region-specific validation across diverse equipment and training.
AI tools may detect or predict interval breast cancers earlier, potentially lowering missed cancers in screening mammography and improving program effectiveness, according to a new review.
DL-LVCS on cardiac MRI achieved AUC 0.887, sensitivity 85.9%, specificity 79.2% for acute myocarditis with preserved EF, surpassing conventional feature tracking (AUC 0.806, sensitivity 67.2%).
Among 3,608 neuro-oncology studies, 65% used TCGA, 14% SEER, 13% BraTS; <1% assessed functional outcomes, 90% relied on single dataset, external validation rare.
Prompting the future: artificial intelligence in pediatric radiology.
Transvaginal embolization of residual pelvic varices reduced pain: median VAS at rest 4→1, activity 7→1, dyspareunia 8→2 (all p<0.001) at 12 months; CIVIQ-14 59.5→19. In 32 women after prior transvenous embolization. One asymptomatic glue embolus to lung, resolved.
Commentary on 'Safety and Effectiveness of Liquid Embolics for Prostate Artery Embolization: A Systematic Review and Meta-Analysis.' Are we there yet?
AI-guided risk-adapted follow-up after de-intensified treatment for stage II nasopharyngeal carcinoma reduced follow-up visits for >90% of failure-free patients (no more than six visits over five years), with external AUC 0.986 and high sensitivity.
Suicidal thoughts and behaviors are tied to disrupted prefrontal-limbic-subcortical circuitry and reduced global brain network integration on MRI; connectome profiles may act as individual 'fingerprints' to guide personalized risk assessment.
An open-weight LLM (LLaMA 3.1) extracted structured data from 947 Dutch brain MRI reports. Zero-shot accuracy: 0.90-0.96 for atrophy scores, 0.93 for microbleed detection. Few-shot prompting boosted microbleed count extraction to 0.92 accuracy. Text similarity for lesion locatio…
Diagnostic yield: a missing quality metric in medical imaging.
Cohort Profile Update: the Rotterdam Periconceptional Cohort-biomarkers, lifestyle intervention, and artificial intelligence.
Combining DL features from thoracolumbar X-rays with clinical factors improved 2-year fracture prediction (AUC 0.774) vs clinical model alone, with net reclassification improvement 0.241 in validation.
