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 deep learning-based pipeline automates organ and tumor segmentation and quantitative analysis for longitudinal preclinical PET-CT studies, reducing manual variability. Demonstrated in a murine case study from acquisition to uptake curve extraction. Performance metrics vs. manu…
MobileMamba-UNet, a lightweight hybrid model, outperformed prior deep learning methods for low-dose CT reconstruction on Mayo datasets, delivering better image quality with lower memory use and faster inference (retrospective testing).
An AI-generated left anterior descending (LAD) artery region surrogate showed strong correlation with manual contours for maximum dose (R²=0.93) and V10Gy (R²=0.81) in lung SBRT. Mean heart dose was a poor predictor of LAD dose (R²≈0.4). Retrospective, single-center.
Automated CT-DCG analysis segmented the bony nasolacrimal duct (Dice 0.79) and classified lacrimal sac size with 84.7% agreement vs experts (κ=0.76) in a retrospective study of 151 PANDO patients.
On an in-house liver cancer radiotherapy dataset, FS-Mamba achieved 92.68% DSC and a clinician score of 4.69/5, while being 4.5× smaller and 6.5× faster than TotalSegmentator (20.6M params).
Retrospective study of 1,000 NCCTs: CNN for early ischemic stroke had 91% sens, 89% spec (AUC 91%). On 30 cases, missed 2 strokes vs radiologist’s 0 (p=0.21). Web tool built, not externally validated.
A dual-domain projection GAN (DDPGAN) enhanced accelerated brain MRA to surpass standard scans, achieving PSNR 31.98 dB at 10× compressed sensing acceleration in a prospective study of 64 patients.
Photoacoustic microscopy distinguished angiogenesis-type from vessel-co-option-type colorectal liver metastases in mice. Vessel-co-option metastases showed no significant response to bevacizumab (treated vs untreated vessel density: p=0.56), while angiogenesis-type metastases ha…
Synergistic calibration & PD-FDK reconstruction improved PSNR (28.99→32.72 dB) and RMSE (0.036→0.023) in dual-arm robotic CBCT phantoms. Single-system; not yet clinically validated.
Meta-analysis of 3 AI studies (2743 lateral cephalograms): pooled sensitivity 87%, specificity 91%, AUC 0.94. Single-center, no external validation—estimates are exploratory.
A study evaluates the impact of AI-assisted teaching on radiology resident training, but the abstract does not provide specific effectiveness metrics or sample size details.
An AI system for hip dysplasia screening on pelvic radiographs achieved sensitivity 96%, specificity 92%, and AUC 0.94, outperforming orthopaedic residents (F-measure 0.96 vs 0.60–0.81). Trained on a limited dataset (40 patients), it requires external validation before clinical…
Australia’s National Lung Cancer Screening Program (July 2025) recommends low-dose CT for high-risk individuals aged 50–70 with a smoking history, incorporating risk-based eligibility, nodule management protocol, and smoking cessation support.
In vitro, multiphase CCTA velocimetry (VBMPI) achieved <4% mean error in coronary flow velocity quantification across stenosis severities. In 5 patients, velocity ratio showed promise for stenosis characterization and ischemia detection (preliminary, not yet clinically validated…
MAMMOMAT B.brilliant with Tomosynthesis Option — Siemens Medical Solutions USA, Inc.
Hammock Sign of Anomalous Origin of Coronary Artery.
The Risks and Benefits of Synthetic Medical Images.
A best-practice review consolidates society guidelines for liver US shear-wave elastography into actionable steps to ease clinical deployment, covering patient selection, acquisition, reliability assessment, and common pitfalls.
Understanding Automation Bias in Imaging AI: An Early Career Perspective.
First human radiographs acquired in space show on-orbit digital radiography is feasible. In-flight image quality was comparable to preflight (mean overall quality 4.86 vs 5.0, P>.99), but central radiograph positioning was worse (4.07 vs 4.95, P=.02).
Robotic-assisted 90Y Transarterial Radioembolization for Treatment of Hepatocellular Carcinoma: Initial Experience.
From Oceans to Orbit: Radiography at the Threshold of a New Human Environment.
AI influences visual search in mammography.
Data Need a Home: Introducing the Dataset Section in EJRAI
Artificial Intelligence–Based Computer-Aided Detection in Breast Cancer Diagnosis: Variation by Breast Density, Imaging Feature, and Tumor Characteristics
Towards Efficient AI Solutions: Optimizing Large Language Models to Extract Information about Kidney Tumors from Radiology Reports
In a survey of 234 dental trainees and radiologists, radiology residents were more cautious about present AI (β=-2.41 vs students) but showed greater near-future acceptance (change β=+1.95); all groups rated future AI capabilities higher than current (p<0.001).
Gemini achieved highest mean total scores for radiolucent (11.49) and mixed (9.01) jaw lesions on panoramic radiographs, ChatGPT for radiopaque (10.93), while Copilot scored lowest; significant differences across LLMs (p<0.05).
In high myopia, resting-state fMRI shows stronger within-hemisphere autonomy in the right lingual gyrus but weaker interhemispheric synergy between bilateral fusiform gyri. These altered brain areas strongly match serotonin/dopamine receptor maps. A classifier using interhemisph…
Internally validated multimodal CT radiomics and inflammatory marker model achieved AUC 0.931 (sensitivity 0.957, specificity 0.782) for preoperative parotid mass risk stratification in 490 patients. Exploratory: AUC 0.952 vs MSRSGC 0.712.