ASFNR clinical state-of-practice: For posterior circulation large vessel occlusion stroke, use noncontrast CT to exclude hemorrhage, CT angiography to identify occlusion, and MRI with DWI as reference standard. Imaging scores like PC-ASPECTS help select patients for thrombectomy.
The ACR Appropriateness Criteria 2026 update provides imaging guidelines for suspected or confirmed diffuse lung disease, covering initial evaluation, acute exacerbation, and surveillance.
New expert consensus framework for symptomatic B3 breast lesions: assess concordance, lower excision threshold for discordant/palpable lesions, conservative management for concordant non-atypical lesions, and risk-based surveillance for atypia.
ACR Appropriateness Criteria for indolent lung cancer: For patients with slow-growing subsolid nodules or atypical cysts where surveillance is chosen over intervention, imaging follow-up aims to detect changes that alter management, with modality selection guided by accuracy and…
A foundation model-powered trimodal AI combining MRI, pathology, and clinical data predicted platinum resistance in high-grade serous ovarian cancer, achieving AUCs up to 0.790 in external validation—outperforming late fusion.
In a randomized trial of 36 medical imaging students, those taught with 3D-printed scoliosis models and AI software scored higher on theoretical knowledge (91.01 vs 82.49) and imaging case analysis (90.24 vs 80.61) than those receiving traditional lectures (p<0.001).
A successful deployment of medical artificial intelligence (AI) in radiology requires a structured process: start with clear goals, then plan, prepare, implement in phases, and continuously monitor performance using key performance indicators and user feedback.
Seeing Beyond the Image: Should Ethics Be Included in Radiology Curricula?
Photon-counting detector CT angiography successfully localized spinal arteriovenous fistulas in all eight patients, with 0.2 mm low-energy threshold reconstructions providing the best visualization. Confirmed at surgery or DSA.
ASL MR perfusion is a contrast-free technique that may help assess penumbra and collaterals in acute stroke patients with contrast contraindications, but the ASFNR says multicenter validation and standardized protocols are required before routine integration into endovascular th…
Primary iliac vein stenting reduced pain (7.7 to 1.4, p=0.01) and pelvic reflux in 69.4% of women with hemodynamically significant nonthrombotic iliac vein lesions and ovarian vein reflux. For non-significant stenosis, ovarian vein embolization/resection alone was effective.
A deep learning model classified pancreas lesions on portal-venous CT as normal, benign, or malignant, achieving an area under the curve (AUC) of 0.84 for all lesions and 0.97 for malignant lesions specifically in an external test set of 166 patients.
A combined model integrating DWI-based habitat analysis and Transformer deep learning predicted progesterone receptor expression in meningiomas with AUC 0.910 (training) and 0.902 (external test), outperforming the clinical model.
Patients with coronary microvascular dysfunction had an older PhenoAge (61 vs 52 years) and dysregulated triacylglycerol lipids. Adding lipid species to clinical factors improved prediction (AUC 0.94 vs 0.86).
FDA cleared Cubresa BrainPET, a dedicated brain positron emission tomography (PET) insert for MRI systems, via 510(k) pathway. The device is intended for functional brain imaging.
Carl Zeiss Meditec obtained FDA 510(k) clearance for ZEISS CLINIC 360, a radiology software platform classified under product code NFJ.
Facial nerve preservation during skull base, otologic, and parotid surgery requires individualized, anatomy-driven approach integrating diffusion tensor imaging tractography, intraoperative monitoring, and AI predictive models to optimize outcomes.
CT-based 2.5D deep learning model predicted response to immunotherapy+chemo after EGFR-TKI resistance: AUCs 0.885 (training), 0.819, 0.863 (validation cohorts). Prospective validation needed. (n=490)
In a study of 567 patients, integrating hip CT radiomics with clinical data via a GradientBoosting Nomogram model yielded the highest validation accuracy (0.849) and AUC (0.911) for opportunistic osteoporosis screening, outperforming 2D and 3D deep learning models alone.
GE HealthCare and Catholic Health signed a 10-year, approximately $500 million partnership to modernize radiology across 40 clinical sites. The plan includes roughly 1,300 new imaging systems and AI/cloud upgrades, expanding access to advanced MRI, CT, PET, and contrast-enhanced…
Pitt names new radiology department chair
Varian highlights Fast-02 proton Flash therapy trial results.
Radiology dominates thirty years of FDA AI device approvals
SDMS names new 2026 board, committee members
GEHC, Catholic Health announce $500M imaging Care Alliance
ASRT Museum and Archives launches self-guided video tour
Societies applaud introduction of Patients First Act
Facebook Live: Case Conference July '26
Using AI Could Help Patients Understand Radiology Reports
Bipartisan lawmakers introduced the Patients First Act to tie Medicare physician reimbursement to inflation and ease burdens for independent practices, with provisions to streamline the stalled imaging appropriate use criteria (AUC) program. The move follows a new CMS fee schedu…
QCDR for MIPS Reporting Startup Guide
How to Have a Successful State Lobby Day
Awareness and Attitudes of Radiology Staff Toward Artificial Intelligence in Medical Imaging Diagnosis: A Systematic Review
