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.
Noncontrast CT-based unimodal imaging AI detected anterior circulation large vessel occlusion with sensitivity 0.78 (95% credible interval 0.68-0.86) and specificity 0.88, versus expert readers' sensitivity 0.62 and similar specificity; low-certainty retrospective evidence.
SIR Foundation research consensus panel calls for standardized acute DVT intervention endpoints: biologically informed patient selection, anatomic/physiologic metrics, validated severity tools, longitudinal biomarkers, and economic/QoL measures to advance precision and reduce po…
A scoping review of 19 recent patents shows AI-based X-ray diagnostics for osteoporosis are advancing with deep learning for bone density estimation, fracture risk prediction, and image preprocessing, but lack clinical validation and interpretability.
A deep learning model using venous-phase CT images predicted high vs low Ki-67 expression in renal cell carcinoma with accuracy 0.814 (sensitivity 0.889, specificity 0.667) in a clinical validation set of 27 patients.
Editorial: The future of oncology: digital twins and precision cancer care.
Radiologists rely on communication, empathy, teamwork, adaptability, and leadership to build patient trust and collaborate. As artificial intelligence (AI) automates repetitive imaging tasks, human judgment, ethics, empathy, and leadership become central to radiologists' value.
<![CDATA[New Study Shows Substantial Decline in CT Radiation Dosing for Adults Over the Past Decade]]>
CT radiation doses have fallen sharply over past decade
Arizona law now permits equipment-based radiation shielding instead of lead aprons in interventional radiology and cardiac cath labs, citing orthopedic strain. Signed Jun 19; House vote 50-2, Senate 29-0.
Carotid web causing embolic stroke in a young adult
Podcast: Testing the effectiveness of today's MR safety standard of care
<![CDATA[Can AI-Enabled Intratumoral CT Threshold Segmentation Help Predict Visceral Pleural Invasion in Lung Cancer Patients?]]>
‘SI DOC LIZA MAY BREAST CANCER’ Internet personality Dr. Willie Ong, who is battling stage 4 sarcoma, revealed on social media that his wife, Dr. Anna Liza Ramoso-Ong, was recently diagnosed with breast cancer. In a vlog posted Tuesday, the couple sh
Diagnostic Performance of the International Academy of Cytology Yokohama System for Reporting Breast Fine-Needle Aspirates: A Cytology-Histopathology Correlation Study From Central India
Takeaways from the ACR-RBMA Practice Leadership Forum
MIPS and QCDR Measures, Specifications and Submission Overview
Interpreting Performance Report Fields
Curium is in advanced talks to buy Lantheus for $7 billion, potentially combining two major players in diagnostic radiopharmaceuticals such as the PET tracer Pylarify. No final decision has been reached.
ACR projects CT angiography of the chest (CPT 71275) will increase 149% to $83.09 under the proposed 2027 Medicare fee schedule, while other codes like CT upper extremity without dye face cuts (-15%). The conversion factor drops 1.68% to $32.84.
Siemens Healthineers and Vanderbilt Health announced an $87M multi-year partnership to standardize imaging and radiation oncology equipment, integrate AI, and support workforce development across Nashville-based sites.
In a study of 540 adults, six calcaneal angles measured on radiographs were not suitable for sex prediction. Key angles like Böhler and Gissane varied with age, while calcaneal compression differed between sexes. These population-specific reference values may aid clinical diagno…
An automated MRI-based AI framework staged pubertal olecranon bone age with internal accuracies of 94.12% (girls) and 93.75% (boys); external validation at a second centre achieved 86.67% (girls) and 90.48% (boys), with mean absolute errors of 0.233 and 0.095 years.
Artificial intelligence for interstitial lung disease pattern recognition on high-resolution computed tomography: A step forward for general radiologists.
A combined prospective and retrospective motion-correction approach (SAMER) for 2D TSE MRI reduced normalized root mean squared error in 90% of moderate-to-severe motion cases and significantly decreased overall reconstruction error across 274 simulated clinical inpatient trajec…
Long-term PM2.5 and PM10 exposure correlated with higher pericoronary fat attenuation index on CCTA: each IQR increase in PM2.5 raised right coronary artery FAI by 7.57 HU. Associations strongest in hypertension, diabetes, and smokers.
Artificial intelligence in radiology.
In a retrospective study of 120 patients, electrocautery tract closure after percutaneous core needle biopsy resulted in no major bleeding, transfusions, or procedure-related deaths at 30 days, with four small intraprocedural hematomas that did not progress.
A letter in World Journal of Radiology warns deep learning models for spontaneous ICH may mistake basal ganglia calcifications for hematoma heterogeneity and chronic lacunar infarcts for perihematomal edema, inflating false positives. Radiologist-verified quantitative radiomics…
A nomogram based on smoking, metabolic status, BMI, age, and sex predicts cardiopulmonary abnormalities on LDCT with AUC 0.833 (95% CI 0.787-0.879) in validation, outperforming age/sex alone (AUC 0.647).
Combining CT radiomics with alpha-fetoprotein and total bilirubin yielded an AUC of 0.948 for predicting glypican-3 expression in hepatocellular carcinoma, up from 0.862 with radiomics alone.
