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…
Leadership skills for radiologists are learnable through a framework emphasizing self-awareness, adaptable styles, team diversity, structured onboarding, and mentorship. A new Canadian Association of Radiologists course distills these into interactive education for busy radiolog…
Deep Learning Improves Sensitivity to Change in Sinus Computed Tomography: Evidence From Two Randomized Controlled Trials.
In breast ultrasound classification, Gaussian noise reduced a custom CNN's accuracy by 36.1% at 5 dB SNR, and Poisson noise reduced Inception V3 by 35.2%. Noise-matched training boosted accuracy up to 56.5% at 5 dB, underscoring the need for noise-robust evaluation.
In 166 cognitively unimpaired older adults, higher temporal lobe [18F]PI-2620 tau PET binding was associated with higher plasma p-tau217 (β=0.22), worse episodic memory (β=-0.36), female sex, and APOE4 carrier status. These brain and blood markers explained ~30% of memory varian…
Two board-certified radiologists reviewing public chest X-ray datasets found significant label disagreement. Cross-dataset testing of AI models revealed sharp drops in external performance (AUPRC and F1 scores) versus internal tests, and a source-classification model could ident…
Adding coronary CTA-based CAD-RADS score and CT-derived fractional flow reserve gradient (ΔFFRCT) to the CAR-OLT score improved prediction of 1-year major adverse cardiac events after liver transplantation (AUC 0.793 vs. 0.668, P=0.044) in a dual-center study of 395 recipients.
Editorial for "Impact of Different Degrees of Liver Iron Concentration on MRI Feature Assessment and LI-RADS v2018 Category Assignment for Hepatocellular Carcinoma".
In a study of 201 head CT pairs, an automated registration and subtraction tool (NeuroAlign CT) cut read time (71 vs 98 sec, p<0.0001) and improved accuracy for detecting worsening intracranial hemorrhage (92.7% vs 80.0%, p=0.046) among three neuroradiologists.
Phase I study of Yttrium-90 radioembolization plus DEBIRI for colorectal liver metastases: maximum tolerated dose was 80 Gy, with considerable toxicity and limited response (RECIST ORR 9%).
A new collimation index (CI) tracked in 7579 fluoroscopic procedures over 13 months showed that educational feedback improved weekly average CI for complex cases from 0.155 to 0.227. Aggressive collimation varied substantially by procedure type and operator, especially in comple…
A PatchGAN-discriminator boosted semi-supervised U-Net to a Dice of 86.12 for carotid plaque ultrasound segmentation with only 30% labeled data, vs. 84.22 for standard semi-supervised U-Net (970 images).
CFD pressure gradients achieved 95% diagnostic accuracy for iliac stenosis in a 34-study scoping review. High wall shear stress and oscillatory shear index predicted plaque vulnerability and restenosis in carotid and peripheral artery disease.
In 55 HNSCC patients, a CT radiomics pipeline with feature selection and window contrast augmentation achieved AUC 0.831 for distinguishing vital from non-vital persistent cervical nodes after chemoradiotherapy, an 8.2% relative gain, but differences were not statistically signi…
DL and CFD-based CT-FFR show similar high diagnostic performance for detecting hemodynamically significant stenosis, with AUCs of 0.90 (95% CI 0.88-0.93) and 0.89 (95% CI 0.86-0.92).
A new framework proposes that radiology AI should shift from plug-and-play to institution-calibrated stewardship, requiring local validation, monitoring, and multidisciplinary governance to ensure ongoing accuracy, relevance, equity, and utility.
A multimodal early-fusion random forest model combining admission CT and clinical data (excluding anti-MDA5 antibodies) predicted 90-day respiratory failure in dermatomyositis-associated interstitial lung disease (DM-ILD), achieving AUC 0.967 in internal testing.
Radiology Researchers Navigate NIH Funding and Policy Changes
ACR Hails ROOT Act Inclusion in House Medicare Reform Bill
When an AI tool incorrectly suggested a mammogram was normal, radiologists' median sensitivity fell from 71% to 39%, per a Radiology study. Eye-tracking showed less scrutiny of those exams, highlighting automation bias.
AdvanCell raises $315M for targeted alpha therapy
MRI could replace DRE for prostate cancer staging
<![CDATA[Mammogram Interpretation and AI Automation Bias: What New Research Reveals]]>
IPR ’26 Case of the Day: Nail–patella syndrome
Portable X-Ray Technology Marks Milestone in Space Healthcare
Evaluating the Role of Automated Breast Ultrasound in Dense Breast Screening
Retire at the Top of Your Game. #radiology
Harvard Medical Faculty Physicians at Beth Israel Deaconess Medical Center, Inc. (HMFP) Employer Profile
<![CDATA[Breast Imaging in Focus: Can Automated Breast Ultrasound Have an Impact in Screening for Women with Dense Breasts?]]>
How to Show Filename Extensions
How to Convert an Excel File to a .TXT File
