Deep Learning Framework Automates Lenke Classification on Multi-View Spine Radiographs
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.
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…
Osteoporosis screening with DXA declined 35.4% among Medicare beneficiaries from 2005 (7,255 per 100,000) to 2023 (4,690 per 100,000), with steeper drops in minority and deprived groups. Use rose 58% in those with highest comorbidities.
ACR-backed Senate Bill Targets Medicare Payment Volatility
<![CDATA[Thirteen Takeaways on BI-RADS v2025 Changes for Mammography, Ultrasound and Breast MRI Reporting]]>
Facebook Live: Cancer Screening in CT
Medicine is better viewed as avoiding unforced errors than chasing rare diagnoses, especially in radiology where images are permanent. Search patterns build consistency and reduce mistakes.
A multisociety coalition released a radiation safety toolkit for interventional fluoroscopy, aiming to curb occupational health crisis. Survey found nearly 60% of clinicians reported orthopedic injuries from lead aprons, and 1 in 5 reduced caseload or took leave.
OhioHealth is investing $10.2 million to double CT scanner capacity at its Bradley Cancer Center in Circleville, Ohio, adding a second scanner to the only facility offering CT in Pickaway County. The two-year project also adds five infusion spaces and expands pharmacy services.
Shining a Spotlight on Sustainability in Radiology
Exam Requirements: Pediatric Ultrasound (Revised 8-6-2026)
Vexev raises $6M for vascular imaging platform
Lantheus reports increased Q2 revenue following Curium deal
Unfortunately, the MRIQuestions.com forum became unmanageable due to spam attacks. I recommend an alternative resource: www.imagingQA.com - Who's Online
Report turnaround times for imaging rose 27% from 2023 to 2024, reaching 0.251 days—a 177% increase over 10 years, per Medicare claims data. Growth decelerated from 60% in 2023, but the workforce may be at maximum capacity.
46-year-old pregnant woman with hypotension, hemoglobin drop after MVA revisited
<![CDATA[Can Brain MRI Help Predict Spinal Cord Stimulation Response for Treating Urinary Incontinence in Stroke Survivors?]]>
AI model using multi-view 2D echo (no Doppler) classified LVOT obstruction (>20 mm Hg) in hypertrophic cardiomyopathy with external validation AUC 0.84. Enables scalable, cost-effective screening.
Cerebrovascular reactivity can be estimated from resting-state BOLD fMRI without a breath-hold or gas challenge. The reconstruction method achieved a mean spatial correlation of 0.61 with hypercapnic CVR maps (0.72 in high respiratory variability).
Critical dialogue: Interstitial lung abnormalities: an evolving concept.
In a meta-analysis of 30 test datasets (67,266 non-contrast CTs), U-Net deep learning models had higher sensitivity (0.916) and precision (0.983) for subdural hematoma detection vs other architectures. However, only 4 U-Net datasets were pooled vs 22 for CNN, so conclusions are…
Correction: Diagnostic accuracy of deep learning vs. human raters for detecting osteoporotic vertebral compression fractures in routine CT scans.
Bibliometric analysis of CT use in human identification shows growing scientific output since 2015, with most studies assessing age and sex; Japan leads in citation impact. No significant link found between journal impact factor and citations.
A deep learning model detected simulated external root resorption with 100% accuracy on periapical radiographs and up to 97.92% on CBCT. Performance dropped to 73.96% with three-dimensional reconstruction, especially in treated teeth.
Optical tissue sensing during vacuum-assisted breast biopsy distinguished malignant from healthy tissue with 86% accuracy, 91% sensitivity, 82% specificity in ex vivo study of 40 mastectomy specimens.
In 183 patients with chronic limb-threatening ischemia, a Small Artery Disease (SAD) score ≥1 on lateral foot DSA increased risk of major adverse limb events (HR 2.22, p=0.011) and death (HR 2.06, p=0.025), but not wound healing or amputation.
Delayed Inferior Thyroid Artery Pseudoaneurysm and Arteriovenous Fistula after Microwave Ablation of a Benign Thyroid Nodule.
Percutaneous Gun-sight Reentry from an Occluded Femoral-Popliteal Bypass Stump to the Native Superficial Femoral Artery for Limb Salvage.
LLMs significantly improved radiology report readability (P<0.05), with DeepSeek-R1 performing best, but all models showed inherent output instability and information omission. Optimized structured prompts reduced model variance and improved translational accuracy, particularly…
A prospective, 21-site, two-vendor study (FAST-CMR) will evaluate a free-running, non-ECG-gated cardiac MRI framework (5D FISS-FRF) in 300 patients with cardiac disease, comparing LVEF precision to conventional cine.