QSM shows greater lateral centromedian nucleus contrast than WMn and MP2RAGE, achieving a median CNR of 2.9 for medial pulvinar and 1.6 for ventral lateral thalamus, but lower SNR.
In 600 patients with unilateral chronic subdural hematoma, bilateral middle meningeal artery embolization had 0% index-admission surgical rescue vs 9.5% for unilateral (p=0.99), with no overall retreatment difference.
Low-intensity focused ultrasound (LIFU) noninvasively modulates neuronal activity in millimeter-sized brain regions, offering a transient alternative to ablative HIFU. AJNR review covers technical background, clinical applications, and safety.
Transcranial MR-guided HIFU is established for movement disorders; neuroradiologist involvement varies. Emerging LIFU offers neuromodulation and blood-brain barrier disruption, but protocols are uncertain. CT/MR imaging is critical for targeting and outcomes.
CAPTYN, a Blood-Based Machine-Learning Model Predicting Clinical Benefit of Atezolizumab-Bevacizumab in Hepatocellular Carcinoma: Validation in the IMbrave150 Trial.
Can explainable artificial intelligence classify asthma and COPD from xenon-129 ventilation magnetic resonance imaging?
Study Shows Enhanced Diagnosis of Coronary Artery Stenosis with Photon-Counting CTA
Fujifilm’s 'Aspire to be Fearless' campaign brings 3D mammography to women across the country.
CAD helps improve 2D synthetic mammography performance
POSITION Job Opening in LOCATION
Integrating engineered biomaterials with deep learning-driven molecular imaging promises non-invasive monitoring and prediction of cancer immunotherapy response, but clinical translation faces hurdles like probe synthesis, tissue penetration, and model generalizability.
Can you figure out what this renal mass is? #radiology #foamrad #ultrasound #ctscan #urology
This week's top radiology content covers adjunctive CT bone reading software for breast cancer, new research on tightness of high-convexity sulci on brain MRI, and molecular imaging insights from recent studies.
A deep learning model estimated pediatric age from pelvic radiographs with a mean absolute error of 0.394 years internally and 0.513 years externally; accuracy within 1 year was 0.937 and 0.927, respectively.
Deep-learning virtual dynamic contrast-enhanced (DCE) breast MRI reached 92% sensitivity vs 96% for standard gadolinium-enhanced DCE, with accuracy 76% vs 77% and no significant differences in BI-RADS or background enhancement in a 592-exam study.
A multimodal MRI deep learning model achieved an AUC of 0.82 (95% CI 0.73–0.91) and NPV of 96% for preoperative prediction of meningioma bone invasion in external testing, improving over conventional radiomics (AUC +0.155, p=0.035).
An artificial intelligence (AI)-derived panoramic score was independently associated with diabetes, hypertension, hyperlipidemia, osteoporosis, and ischemic heart disease in 26,550 radiographs; adjusted AUC 0.74–0.80.
A multimodal deep learning model combining pre- and post-treatment CT/MRI with clinical notes predicted 90-day modified Rankin Scale after stroke thrombectomy with AUC 0.9147 (noncontrast CT) and 0.9479 (MRI), outperforming single-modality baselines.
A deep learning model with generalized linear model feature residualization (PMDN) classified Alzheimer disease on brain MRI with balanced accuracy 0.71 and near-zero age bias; post hoc isotonic or Bayesian binning calibration reached max calibration error 0.21–0.24.
Phyllodes tumors of the breast show significant imaging overlap with fibroadenomas. Core needle biopsy is key but limited by tumor heterogeneity. Surgical excision with negative margins remains the mainstay; local recurrence risk hinges on histologic grade and margin status. Eme…
U-Net model automatically measured hallux valgus angle (MAE 2.118°, ICC 0.961) and intermetatarsal angle (MAE 0.966°, ICC 0.919) on foot radiographs, with high agreement vs experts in temporal validation (n=100).
Capitol Imaging Services acquires Impression Imaging
Beta Technologies tested its electric Alia CX300 aircraft on 20-42 min Utah routes to see if it can deliver short-lived radiopharmaceuticals like FDG (half-life ~110 min), aiming to expand nuclear imaging access for patients farther from production sites.
VR boosts accuracy, confidence for evaluating abdominal neuroblastoma
GE HealthCare’s John Jaeckle wins AdvaMed Imaging Röntgen Award
FDA clears SimBioSys's breast cancer risk software
In a prospective study, 68Ga-HER2 PET/CT after two cycles predicted pathologic complete response (pCR): 85% pCR when uptake dropped ≥61% vs 38% if less.
AI Certificate Program Builds Practical AI Expertise
