Top this week

most clinically relevant
Chest / ThoracicAI / InformaticsGuidelineTrainee

Chinese Medical Association updates lung cancer diagnosis and treatment guideline for 2026

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…

Zhonghua zhong liu za zhi [Chinese journal of oncology]

Latest

4699 stories
GeneralNews

Radiology wins $1B in surprise-billing arbitration awards

Radiology secured about $1.03 billion in No Surprises Act arbitration awards from 2023 to 2025, as providers won 85% of 2025 disputes and total costs hit $22.4 billion, per a Georgetown analysis.

Radiology Business
GeneralNews

Diagnostic errors dominate 71% of radiology malpractice claims, review finds

Diagnostic errors accounted for 71% of radiology malpractice claims vs 28% in other specialties, per a new Radiology review. Post-2010, mean payments rose to $344,197, and severe patient outcomes made high payments nearly 9 times more likely. Outpatient cases (51%) and severe ou…

Radiology Business
Neuro / Head & NeckAI / InformaticsResearch

AI-simplified neuroradiology reports preferred by patients in randomized trial

In a randomized trial of 100 adults, an AI-simplified neuroradiology report received significantly higher communication ratings than a conventional report (Cohen's d 1.31-2.10, all p<0.001). Qualitative comments favored clearer explanations.

Insights into imaging
Chest / ThoracicAI / InformaticsNews

Comment: AI-CT Lung Nodule Review Lacks Search Strategy, Overstates Predictive Performance

A comment on a review linking AI-derived CT features of lung ground-glass nodules to driver genes notes missing search methods, selective accuracy reporting (AUC 0.64 to >0.95), and framing that overstates AI's performance given a referenced systematic review's mean AUC of ~0.64.

Journal of cancer research and clinical oncology
Neuro / Head & NeckAI / InformaticsResearch

Hybrid CNN-GRU model improves estimation of respiratory and heart rate variations from resting-state BOLD fMRI across the lifespan

A 1D-CNN+GRU deep learning model reduced error in respiratory and heart rate variation estimates from resting-state BOLD fMRI by 7–10% (MAE, MSE, DTW) versus established baselines. Evaluated on three HCP cohorts spanning ages 5–100 years, the model leveraged 630 brain regions an…

Imaging neuroscience (Cambridge, Mass.)
Chest / ThoracicAI / InformaticsResearch

Semantic fluency doesn't guarantee factual accuracy in RadVLM chest X-ray reports

A radiology vision-language model (RadVLM) generated easier-to-read chest X-ray impressions, but readability weakly correlated with factual accuracy (association coefficient 0.154; 95% CI 0.124-0.183), so a fluent report could hide incorrect findings.

Frontiers in digital health
CardiacAI / InformaticsResearch

CT-Derived Left Atrial Wall Thickness Does Not Correlate with Bipolar Voltage in AF

CT-derived left atrial wall thickness (mean 1.45 mm) did not correlate with bipolar voltage (r=-0.018) in 60 AF patients. Persistent AF had larger left atrial volume (119 vs 102 mL, p=0.024) and a trend toward thicker walls, suggesting complementary structural info.

Journal of clinical medicine
NewerPage 33 of 157Older