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.
In 104 patients, fluorodeoxyglucose PET radiomics using a 5-mm peritumoral region predicted tumor spread through air spaces with AUC 0.79, outperforming tumor-only (0.70) and 10-mm peritumoral (0.74) models; SUVmax, SUVmean, and SUVpeak did not differ.
Machine learning models using transcriptome and neuroimaging data predicted cerebral small vessel disease (average F1=0.93) and dementia (F1=0.73) in 91 patients. Differentially distributed neuroimaging features included white matter hyperintensity severity and CSVD burden.
An NLP-assisted quality control system identified significant differences in radiology report error rates by physician grade, location, and time of day. ARIMA modeling predicted a declining trend over 3 months (error rates 0.036, 0.031, 0.029).
Automated CT body composition via TotalSegmentator predicted overall survival in 357 cancer patients on immunotherapy. Volumetric muscle-to-bone ratio had c-index 0.616; combining all tissue density and quantity reached 0.621. Five-year mortality was 84% (95% CI 80-88%).
AI-measured pericardial effusion volume on pre-TAVI CT had no independent association with long-term mortality (HR 1.00, 95% CI 0.996–1.01; p=0.842). Effusion was common (58.7%) but larger ones rare (5.1%), and linked to atrial fibrillation and pulmonary hypertension.
A DCE-CT nomogram integrating intratumoral heterogeneity and body fat predicted vessels encapsulating tumor clusters (VETC) in hepatocellular carcinoma with AUC 0.847 (internal) and 0.814 (external) in 360 patients; higher scores also linked to shorter recurrence-free survival.
In a retrospective study of 169 patients, an integrated MRI radiomics and clinical random forest model predicted early hepatocellular carcinoma (HCC) recurrence after radiofrequency ablation (RFA) with a test AUC of 0.909 (sensitivity 83.3%, specificity 90.9%).
An MRI radiomics model using ADC, DSC, T1CE, and FLAIR distinguished tumor from treatment effects in post-treatment glioblastoma (AUC 0.887, sensitivity 75.0%, specificity 92.3%), but it requires external validation.
Integrating quantitative SPECT/CT metrics into a machine-learning model improved differentiation of spinal tuberculosis from pyogenic spondylitis, adding 0.110 to AUC (95% CI 0.054–0.172) over conventional data.
FDA cleared Lower Limb AI (LLAI) from AI Planning Logic via 510(k), an AI-based software tool for lower extremity radiograph analysis.
CT for breast radiotherapy detects ischemic heart disease risk
Evolving Contrast Equation: Clinical Performance and Supply Considerations in Modern Radiology
Azra AI, 4DMedical enter partnership
MWA may have long-term benefits for renal cell cancer patients
CureMetrix secures FDA clearance for cmAngio 2.0
Epic adds one-click diagnostic image exchange
<![CDATA[FDA Clears Updated AI Mammography Software for Breast Arterial Calcification Detection]]>
Radiation-related cancer mortality higher for U.S. flight crew
<![CDATA[Could Risk-Stratified MRI Surveillance Supplant Semiannual Ultrasound Exams in Patients with Cirrhosis?]]>
Retroperitoneal fibrosis
What's the abnormality on this abdominal CT?
<![CDATA[Perspectives on Peer Review, Medicolegal Cases and Judgment in Radiology]]>
Phantom Testing: Mammography (Revised 08-17-2026)
This educational video reviews CT features of benign polypoid gastric masses, focusing on diagnostic pearls, common pitfalls, and the differential diagnosis.
Multi-view AI output variability as a teaching resource in a micro-course for thyroid TI-RADS interpretation among ultrasound residents: a randomized controlled trial
University of Southern California researchers 3D-print flexible MRI coils for infant hearts in under 10 minutes for $30 each, yielding roughly four times the contrast of standard commercial sensors.
Computational CT analysis, including artificial intelligence, enables automated volumetric quantification and pattern classification of interstitial lung disease on high-resolution CT, offering an objective alternative to visual scoring for patients with inflammatory rheumatic d…
Can AI safely triage abbreviated breast MRI? Bridging efficiency and diagnostic confidence.
