The ACR has issued its 2026 update to Appropriateness Criteria for myelopathy, providing evidence-based imaging guidance for acute, chronic, and vascular causes of spinal cord dysfunction to help differentiate extrinsic from intrinsic pathology.
In 82,957 women with negative screening mammograms (Kaiser Permanente cohort), combining Mirai AI, a 313-SNP polygenic score, and BCSCv3 clinical risk reached C-index 0.70 (95% CI 0.69–0.71) vs 0.66, 0.62, and 0.61 for each alone — supporting integrated risk-stratified screening.
After venous sinus stenting for pulsatile tinnitus, temporal bone remodeling occurred in 73.1% of patients with follow-up CT (38/52). Remodeling was significantly more likely with a diverticulum vs isolated wall dehiscence (85.7% vs 47.1%; adjusted OR 8.08, 95% CI 1.31-49.73), a…
Across >3 million multicenter emergency department encounters, overall ED neuroimaging utilization doubled from 2016 to 2025. Head CT without contrast remained dominant, but CT perfusion use rose >5-fold over the same period, signaling a marked shift in acute stroke workup inten…
In 283 anterior circulation LVO stroke patients, adding the Perfusion Collateral Impairment Score (PCIS) to standard collateral scores improved 90-day poor-outcome prediction (COVES+PCIS aOR 1.53, 95% CI 1.17–2.01), but PCIS alone did not outperform comparators after correction.
Curium and Lantheus won a patent dispute concerning lutetium-177 dotatate products, used for neuroendocrine tumor imaging and therapy. The ruling could impact availability and competition in the radiopharmaceutical market.
A $9 million grant will fund training for early-career scientists in cerebral amyloid angiopathy (CAA), a small vessel disease that causes lobar intracerebral hemorrhage and cognitive decline (exact figure not reported in source).
The American Society of Radiologic Technologists has created two scholarships in memory of members who made significant contributions to medical imaging and radiation therapy education and advancement.
FDA has cleared RadNet's AI module for detecting breast arterial calcification (BAC) on mammography — a marker of cardiovascular risk. In clinical testing, sensitivity was 90% and specificity 88% across varying breast densities.
A new meta-analysis examines fibroblast activation protein inhibitor (FAPI) PET/CT for detecting peritoneal metastases, suggesting diagnostic performance advantages over conventional imaging — though exact pooled sensitivity/specificity figures were not reported in the source ex…
Photon-counting CT may offer faster, cleaner differentiation of hemorrhage from contrast staining after mechanical thrombectomy — a clinically critical distinction — but supporting numbers not reported in source.
This item is a philosophical blog post quoting Annie Dillard and Thomas Merton on intentional living. It contains no radiology findings, imaging data, clinical results, or practice-relevant information for a radiology audience.
Generative AI firm Midjourney is investing over $74M to launch a whole-body ultrasound screening business — a move radiologists are publicly criticizing for lack of clinical evidence supporting its marketing claims.
The proportion of radiologists performing any IR-related work fell from 70% in 2008 to 50% by 2023, per new JVIR research — suggesting IR is consolidating into a smaller, more specialized subset of the workforce.
The U.S. Senate has passed a radiologist-supported bill aimed at boosting lung cancer research, prompted in part by a puzzling increase in cases among nonsmoking women even as overall lung cancer rates decline.
A retrospective study found vision-language models (VLMs) performed on par with LLMs for labeling incidental breast findings on CT reports, achieving similar accuracy without substantial performance gaps (exact figures not reported in source).
CTisus hosts a live case conference for June 2026, walking through multiple unknown CT cases with expert commentary. Designed for radiologists and trainees, the session offers practical teaching points on body CT interpretation, differential diagnoses, and pearls for daily pract…
European radiology
European radiology
European radiology
BACKGROUND: Axillary lymph node metastasis (ALNM) is a critical prognostic factor in breast cancer. While sentinel lymph node biopsy remains the gold standard, conventional imaging relies on operator expertise with variable diagnostic accuracy. This meta-analysis evaluates the...
European radiology
OBJECTIVES: In moderately advanced (T2-T3) glottic cancer, eligibility for organ-preserving surgery is limited by tumor extension into certain high-risk areas within the larynx that can be identified on preoperative imaging and serve as predictive factors for poorer outcomes....
OBJECTIVES: To evaluate whether GPT-4.1 and Llama 3.3 70B, large language models (LLMs) assessed in zero-shot, baseline configurations, detect and categorize clinically consequential errors across types that range from pattern-based to reasoning-dependent. MATERIALS AND METHOD...
OBJECTIVES: Standardizing magnetic resonance enterography (MRE)-defined transmural healing (TH) remains challenging in Crohn's disease (CD) despite its prognostic superiority. We aimed to evaluate seven conventional MRE-defined TH criteria and develop a machine-learning-optimi...
European radiology
PURPOSE: To compare rupture-related signals captured by automatically extracted computed tomography angiography (CTA) morphologic features and threshold-based computed tomography perfusion (CTP) metrics in large unruptured intracranial aneurysms (UIAs), and to explore a parsim...
BACKGROUND: Thymomas are primarily assessed using chest computed tomography (CT); however, this method has inherent limitations such as an overlap between the semantic features of thymomas presenting as localized lesions and other histological subtypes. Therefore, this study a...
Lens epithelial cells (LECs) have a critical role in nutrient transport, ion balance, and the synthesis of essential molecules required to preserve the lens's transparency. We hypothesize that lens epithelial cell density (LECD) may be correlated with the formation and severit...
A major barrier to clinical adoption of artificial intelligence (AI) for brain tumor monitoring is the lack of calibrated uncertainty in automated segmentation, limiting clinician trust. We developed a deep learning framework that generates uncertainty estimates for meningioma...
PCWG4 revises prostate cancer trial design: integrates PSMA PET/CT for eligibility and response, redefines radiographic progression, and introduces 'no longer clinically benefitting' to guide treatment continuation beyond standard endpoints.
A 2023 survey of 3,919 Chinese hospitals found wide variability in prostate MRI practice: only 58.7% included high b-value diffusion-weighted imaging, and 55.3% still used unstructured reports — signaling major PI-RADS standardization gaps nationally.
Systematic review of ultrasound teaching methods finds blended learning (classroom + online) and simulation-based training improve both cognitive and practical skills in medical students more than traditional instruction alone. No single dominant pedagogy identified; flipped cla…
A JACR perspective argues that AI-assisted 'vibe coding' — generating functional code from natural-language prompts without deep programming knowledge — is redefining the expertise required to conduct radiology research, with implications for how the field trains and evaluates i…
