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.
CT Interpretation in the Artificial Intelligence Age: Turning Efficiency into Better Patient Care.
Beyond Burnout in Radiology: A Call to Action in the AI Era.
The ACR is developing pediatric-specific guidance for incidental imaging findings, noting adult guidelines may not fit children; interim strategy offered for managing these findings safely.
A hybrid convolutional neural network (CNN)-transformer mammography model reached 85.5% accuracy and 79.6% macro F1 on VinDrMammo three-class classification, with lesion-focused evidence matching annotated abnormalities and fewer parameters than comparators.
Automated BoneXpert bone age was more accurate than single human readers (mean absolute error 4.8 vs 6.5 months) and had fewer >1.8-year errors (0.7% vs 3.4%) in 1,285 pediatric hand radiographs. Reader variability was higher under age 12 (standard deviation 8.7 vs 4.2 months).
Prostate-specific membrane antigen (PSMA) PET/CT: PSMA Reporting and Data System v2.0 outperformed bone uptake metastatic probability (BUMP) for focal bone uptake (sensitivity 98% vs 74%; specificity 96% vs 80%). BUMP AUROC 0.812 (95% CI 0.636-0.931) in 130 patients/412 lesions.
Fully automated AI-based CT analysis for TAVI planning had excellent agreement with semi-automated measurements (ICC>0.95), but would have changed prosthesis size selection in 21% of patients versus 14% with standard software, underscoring the need for expert interpretation.
A five-country analysis of radiography curriculum documents found communication addressed in all, but explicit listening behaviours uncommon; only Australia’s capability standards explicitly defined listening.
In a 4-year pediatric radiology eConsult pilot, 257 consults were submitted (mean 6.8/month). All 26 provider survey respondents were satisfied (Likert ≥4), and 80.8% reported impact on clinical decision-making.
A US geospatial analysis found highly unequal SPECT-CT access (Gini 0.327). Between-group inequality was significant by race and population (p≤0.004), not income or sex. Local racial impact varied widely: from -7.82 to +9.37 miles/% White, highlighting regional disparities.
Flow diversion for 11 children with 15 pediatric posterior circulation aneurysms: all procedures technically successful, no procedure-related permanent neurologic morbidity or mortality, and residual opacification in 6.7% of aneurysms at median 47 months follow-up.
Spectroscopists propose a harmonized minimum-standard single-voxel proton MRS approach for children with neurodevelopmental delays, aiming to reduce misdiagnosis in cerebral creatine deficiency syndromes and standardize data for clinical trials.
As medical AI moves into clinical practice, polarized debate obscures real needs. A balanced, evidence-based focus on clinical validation, human-AI interaction, bias, trust, and education will be key to success.
AI in cardiac CT now automates calcium scoring, stenosis detection, plaque quantification, CT-FFR, and perfusion analysis, with performances comparable to invasive standards; however, prospective validation remains lacking.
From Water Imaging to Tissue State Imaging: What Multiplexed MRI Adds to Quantitative MRI.
In a study of 80 patients, women with cognitive decline and lower education showed preserved cortical thickness despite higher p-tau/Aβ42 ratio (p=0.026) and thicker frontal cortex (p=0.049). Education moderated the biomarker-thickness link (p<0.05 for all regions), suggesting M…
Opposite brain network dynamics on resting-state fMRI distinguish Parkinson's disease from progressive supranuclear palsy, with machine learning achieving moderate accuracy. External validation needed.
AI on coronary CTA in 1009 NSTE-ACS patients: 99% NPV for in-hospital heart failure; high AI likelihood group (17%) had a 5.39-fold risk (95% CI 2.32-12.50) of index HF, and 2.56-fold risk after discharge.
Deceptive Eloquence in AI-assisted Thoracic Radiology.
Falling Fruit Sign: Pelvic Splenosis Supplied by the Celiac Trunk.
Sharpening the PET Amyloid Signal with MRI.
Bringing Inflammation's Microvasculature into View: Super-Resolution US in Crohn Disease Activity-Early Career Perspective.
Closing the Gap in Femoral-Neck Fracture Detection: AI Assistance with Pelvic and Hip Radiographs.
MRI-guided amyloid PET reconstruction improved interreader agreement (Fleiss κ 0.91 vs 0.79) and specificity (99.2% vs 91.6%), reducing false positives from 8.1% to 0.8% vs OSEM in a retrospective study of 120 patients.
Deep learning model OccuNet detected femoral-neck fractures on hip/pelvic radiographs with 97.5% sensitivity, 98.8% specificity, AUC 0.99. It raised reader sensitivity and cut reading time: radiologists 93.7% to 97.2%, emergency physicians 84.3% to 95.6%, time -14.9% and -18.9%.
Super-resolution contrast-enhanced US (SRCEUS) differentiated moderate/severe from remission/mild Crohn disease with AUC 0.92, sensitivity 94.1%, and specificity 95.0% in a prospective study of 54 patients. Performance exceeded conventional CEUS (AUC 0.78, P=.03).
Black-White Racial Differences at Breast MRI.
A Progressive Shift in Procedural Sedation: Is It Time to Embrace Ketamine in Interventional Radiology?
Assuring Transparency of AI Software after Deployment
Comprehensive multimodal model achieved AUC 0.86 for baseline cerebral microhemorrhage detection in ADNI; minimal clinical-only model still reached AUC 0.72, supporting resource-limited screening.