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…
AI-assisted CXR interpretation significantly improved traumatic pneumothorax detection for emergency physicians (diagnostic accuracy OR 2.37, p<0.001). Non-specialists benefitted more than specialists, with a significant AI-by-experience interaction (p=0.010). Specificity was un…
A dynamic curriculum learning framework for spatiotemporal encoding outperformed existing methods on six brain imaging tasks including Alzheimer's and tumor classification.
Radiology was a high-density domain in 368 AI-in-healthcare systematic reviews; 68% of data from imaging, electronic health records, labs; ethical concerns in 78.5% (rising 2021–2025).
Fully automated AI-based coronary artery calcification quantification on low-dose CT for lung cancer screening showed excellent agreement with semi-automated scoring (ICC 0.96) and high sensitivity (0.97) for excluding CAC, without extra reading time.
Tau PET tracer flags early Alzheimer risk in healthy older adults
Ultrasound's evolution spans from ancient Greek acoustics to today's >$50B market, with key milestones like the 1880 piezoelectric effect and the 1940s birth of medical imaging.
Provect AI wins FDA clearance for 3D imaging software
Why Future Radiologists Want to Make Their Own Schedules | RSNA Unscripted with Roger Yang, MD
Women's Imaging MinnieCast, Episode 13: Partial breast irradiation in the spotlight
<![CDATA[Rethinking Our Approach to Acquisitions of Coronary Computed Tomography Angiography (CCTA) Scans]]>
A profile of a vascular employer in Southern Kentucky.
The American College of Radiology warns that proposed federal grant rules changes could disrupt radiology research, increase compliance burdens, and risk losing scientists to other countries. Over 54,000 comments submitted.
The University of Pittsburgh announced Maureen P. Kohi, MD, as its new radiology chair effective Oct. 12. An interventional radiologist, she joins from UNC Chapel Hill where she served as chair and led growth in clinical care, research, and enterprise imaging.
MIPS CMS Submission Overview
GRID Form Submission Status Report
ACR Raises Concerns About OMB’s Federal Grant Rule Proposal
Registration is open for the 2026 MIPS Value Pathway (MVP).
<![CDATA[SCCT: Assessing the Impact of AI Detection of Coronary Plaque on Chest CT Scans and Notification of Treating Physicians ]]>
In early Alzheimer's disease, greater neuroinflammation was linked to reduced glymphatic function and higher tau burden; total indirect effect on cognition was -0.165 (95% CI -0.266 to -0.105) in ADNI and -0.143 in a replication cohort.
Reply to the Letter to the Editor: Lung cancer screening in Asian populations: from radiological convergence to mechanistic heterogeneity.
Letter to the Editor: Patient education support is not equivalent to informed consent adequacy: reflections on the role of large language models in radiology.
Fairness in healthcare AI is not a one-time check but a continuous responsibility spanning the entire lifecycle—from problem formulation to postdeployment monitoring. Clinicians must recognize biases like shortcut learning, distribution shift, and automation bias, and demand sub…
Adding contrast-enhanced ultrasound (CEUS) to conventional US improved AUC from 0.699 to 0.780 for differentiating benign from malignant TI-RADS 4-5 thyroid nodules in a retrospective, propensity-matched surgical cohort. Absence of filling defects was linked to malignancy.
In a prospective study, standard-dose CT during PET/CT significantly increased chromosomal aberrations (p=0.016), while reduced-dose CT and FDG injection did not. CT effective dose was independently associated with aberration frequency, supporting protocol optimization.
No qualitative or quantitative MRI features were significantly associated with tumor behavior in desmoid-type fibromatosis during active surveillance in a 24-patient study, suggesting limited standalone predictive value.
A fusion model using MRI deep learning, radiomics, and clinical features predicted placenta accreta spectrum; test set AUCs were 0.949 (intraoperative criteria) and 0.936 (histopathologic criteria).
A transformer deep learning model analyzing non-contrast chest CT achieved external test AUCs of 0.89 (0.84-0.94) and 0.89 (0.82-0.95) for identifying children with refractory Mycoplasma pneumoniae pneumonia, outperforming a clinical model (p<0.001).
AI measured major curve angle with MAE 2.7° (r=0.99) and detected implants with MAE 0.18 per image (r=0.99) in multi-institutional external validation of 4585 scoliosis radiographs.
LightGBM model integrating MRI, mammography & ultrasound features predicted sentinel lymph node status after neoadjuvant chemotherapy in early breast cancer with AUCs of 0.95, 0.93 & 0.91 in internal, external test 1 & external 2 cohorts.
CT radiomics model predicts spread through air spaces (STAS) grade in lung adenocarcinoma; STAS grade II independently linked to worse recurrence-free survival (P=0.037). Random forest detected STAS with AUC 0.886 internally and 0.779 externally, aiding surgical decisions.
