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…
In 2,652 CT exams (4.1% fracture prevalence), Aidoc AI detected acute cervical spine fractures with sensitivity 89.1% vs 94.5% for radiologists; combined sensitivity/specificity favored radiologists (p=0.02). Single-center retrospective study.
Multicenter retrospective: LightGBM model predicts post-TJA hypoproteinemia (external AUC 0.855). Age, erythrocyte sedimentation rate, surgery time, serum calcium, and anesthesia method were key predictors. Not yet prospectively validated.
A systematic review of 27 studies shows Med-VQA has shifted from text-only classifiers to generative vision-language models. Frameworks using chain-of-thought reasoning and retrieval-augmented generation improve interpretability, but lack standardized clinical benchmarks and rea…
In a retrospective cohort of 283 patients, an XGBoost model using MRI-based pelvic depth, tumor-to-peritoneal reflection distance, and gender achieved AUC 0.809 (95% CI 0.757–0.862) for predicting laparoscopic TME difficulty, outperforming logistic regression (AUC 0.623).
FUAS monotherapy for adenomyosis: pooled dysmenorrhea remission 79% (95% CI 75-83%), major adverse events 0.3%, but long-term recurrence 45% in meta-analysis of 27 studies (13,307 pts).
A fusion model (2.5D deep learning + habitat-radiomics + clinical features) differentiated lipid-poor adrenal adenomas from metastases with an external test AUC of 0.886 (multicenter, 390 patients, retrospective).
Multimodal MRI-clinical fusion model predicted 90-day stroke functional outcome with AUC 0.885 (sensitivity 92%, specificity 76%) on internal test (n=50); external validation (n=37) showed similar trends. Retrospective, not yet externally validated in multicenter setting.
A global survey of 103 stroke providers found that while 88% manage pediatric AIS, only 65% offer both IV thrombolysis and thrombectomy. CT/CTA was most common first-line imaging (34%), but perfusion and AI tools were underutilized.
MIT researchers have introduced a new augmented reality (AR) system designed to assist clinicians in interpreting ultrasound images. No clinical performance data or validation details were reported in this announcement.
CTisus continues its Facebook Live series sharing key takeaways from Johns Hopkins' 2025-2026 Radiology Speaker Series, distilling insights for practicing radiologists and trainees.
On ankle MRI, chronic periosteal sleeve avulsion of the flexor retinaculum is easily missed on coronal views alone. The axial sequence clearly demonstrates the retinaculum wrapping around the medial malleolus tip instead of inserting sharply, with associated chronic scar plate a…
Eurorad teaching case illustrates the imaging findings of an intra-abdominal testis presenting years after orchiopexy, a rare postoperative complication.
This item is a literary/cultural essay about deception in society, routed from a general blog. It contains no radiology, imaging, or clinical content and does not meet RadPigeon editorial scope.
Interactive image-based review details the radiologic spectrum of lung adenocarcinoma, from preinvasive lesions to invasive subtypes, on CT and PET/CT. (Descriptive educational piece; exact performance statistics not applicable).
The American College of Radiology advises radiology practices to immediately review CMS Q3 National Correct Coding Initiative (NCCI) edits, as quarterly updates directly affect billing compliance and claim denials for diagnostic imaging.
ACR urges Congress to fund NIH All of Us program, collecting diverse health data including imaging for precision medicine.
FDA officials outlined programs to streamline regulatory review for radiology AI tools at the ACR DSI Summit, aiming to accelerate safe innovation (specific initiatives not detailed in source).
The federal administrative fee for initiating No Surprises Act independent dispute resolution cases has been lowered, reducing costs for radiologists challenging out-of-network payer reimbursements (exact new fee not reported in source).
Subtle Medical's deep-learning CT enhancement software received FDA clearance. The algorithm denoises and sharpens CT images, potentially allowing lower-dose acquisitions without sacrificing diagnostic quality. (Exact performance figures not reported in source.)
DeepHealth debuts AI-Enhanced Reporting Pro, a tool designed to integrate artificial intelligence into radiology reporting to streamline workflow (specific capabilities and performance metrics not detailed in source).
The RSNA details the ABR alternate certification pathway, a route for experienced radiologists to become board certified without completing a traditional residency. The article outlines eligibility criteria, the application process, and implications for the radiology workforce.
SNMMI has awarded $530,000 in Mars Shot grants to support cutting-edge nuclear medicine and molecular imaging research projects.
Among men with equivocal or non-suspicious prostate MRI, PSMA PET/CT reduced the biopsy rate by nearly 50% compared to standard workup, according to a new study.
Three commercial mammography AI algorithms produced elevated cancer scores as far as 10 years before clinical diagnosis in a Swedish study (Radiology), with signal strength increasing closer to diagnosis — suggesting AI may detect long-horizon mammographic risk. Exact AUC/sensit…
FDA 510(k) clearance granted to Hitachi High-Tech Corp. for the PROBEAT-CR under product code LHN. Specific indications and predicate device not detailed in available source data.
FDA 510(k) clearance granted to Mighty Oak Medical for Acorn 3D Software (AC-SEG-4009) and Acorn 3DP Model (AC-101-XX), a spine segmentation and 3D-printed anatomical model system intended to support surgical planning.
FDA 510(k) clearance granted to Changzhou Boen Zhongding Medical Technology (China) for a dental X-ray system under product code OAS. No clinical performance data reported in clearance notice.
ACR BI-RADS v2025 — the first year-versioned edition — drops 'focus' and 'developing asymmetry,' adds ultrasound 'non-mass,' standardizes Category 4 subdivisions across modalities, and reframes mammographic density around masking risk rather than volume.
A retrospective study (n=390) found a wavelet-spectrum multi-channel deep learning model could spare 26% of biopsies in BI-RADS 4a+ breast lesions while keeping missed malignancy at 1.8% — a ~2% accuracy gain over B-mode alone. Not yet externally validated.
A narrative review finds urologists and trainees show strong willingness to engage with sustainability initiatives, but formal curricula are nearly absent. Most existing efforts are brief and elective; evidence linking training to behavioral or environmental outcomes remains lim…
