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…
An AuntMinnie MinnieCast episode reviews where ABUS (automated breast ultrasound) stands today, discussing clinical adoption, evidence gaps for dense breasts, and its place relative to handheld ultrasound and mammography. No new data are reported.
The FDA has cleared new functionalities for DeepHealth’s AI-powered breast imaging suite. (Exact features not disclosed in the announcement.)
An AI-powered brain tumor segmentation tool has been cleared by the FDA, marking a key step for the manufacturer's expansion into North America. The clearance covers automated tumor delineation on imaging; specific performance metrics or predicate device details were not disclos…
A new independent report from Signify Research examines why Voice AI pilots for specialty patient access stall, available free. Published via PR Newswire and Artera, the report highlights adoption barriers without offering quantitative data.
Mount Sinai Medical Center has listed an employer profile on the ACR Career Center.
The American College of Radiology has launched a new login portal for the Journal of the American College of Radiology (JACR), transitioning authentication to jacr-auth.acr.org. The change affects how members access journal content; members should update bookmarks and login cred…
A breast imaging radiology position in Arizona metro offers a $75,000 sign-on bonus and a fellowship stipend, per an ACR Career Center listing.
The American College of Radiology (ACR) has released a summary outlining how the Medicare Payment Advisory Commission's (MedPAC) June 2026 report could affect radiology reimbursement and practice, though exact financial figures are not yet publicly available.
ACR Chief Research Officer Dr. Etta Pisano highlighted the College's AI initiatives and strengthened international collaborations, underscoring radiology's role in shaping artificial intelligence in medicine.
On MRI, LI-RADS LR-5 had higher PPV for HCC than KLCA-NCC definite HCC (93.9% vs 91.7%, p<0.001); on CT, PPVs were equal (92.9%). Corresponding probability categories should not be used interchangeably.
In a 100-question radiology MCQ test, Gemini 2.5 Pro achieved 90% accuracy, with Claude 4.5 Sonnet at 86%. All LLMs and 3rd-year residents outperformed juniors. No performance gap between Turkish and English (P=1.000). Claude showed best temporal reliability (κ=0.872).
In a 92-patient prospective STEMI cohort, an AI-driven coronary CTA model predicted 1-year MACE (AUC 0.876) significantly better than the GRACE score (AUC 0.742, p=0.012). Key predictors included total plaque volume >400 mm3, low-attenuation plaque, and LV end-diastolic volume c…
An AI system detected clavicle fractures on AP radiographs with 95.8% sensitivity, 98.9% specificity, and AUC 0.95—performance comparable to an experienced orthopedic surgeon in a single-center retrospective study of 367 exams. Second-plane view results were similarly high.
A Random Forest model using obesity composite indices achieved an AUC of 0.895 (0.864–0.926) for identifying kidney stone history in patients with both diabetes and hypertension. Roundness fat mass and lipid accumulation product were the strongest predictors. Validation was on a…
CT-based radiomics with an SVM classifier predicted high PD-L1 expression (≥50%) in NSCLC with AUC 0.83 (IQR 0.63-0.92) in a small retrospective study of 55 patients. Clinical data did not improve performance; texture features were most informative. Not yet externally validated.
Preoperative cone-beam breast CT (CE-CBBCT) radiomics predicted high Ki-67 in breast cancer (AUC 0.885 at 14% cut-off; 0.831 at 30% cut-off, external test cohort). Adding deep learning did not significantly improve performance. The radiomics score for Ki-67 ≥30% independently pr…
Integrated phenotyping of 69 patients with idiopathic pleuroparenchymal fibroelastosis (PPFE) using quantitative CT and clinical markers identified two reproducible clusters. The severe fibrotic phenotype carried an 8.6-fold higher mortality risk (95%CI 1.06-70.4). A four-variab…
In 258 dental exam questions, AI models varied: Gemini led factual recall (p=0.048), but no model excelled in analytical reasoning (p=0.032). AI aids education, not yet reliable for clinical decisions in oral radiology.
A new dataset of 30 human lumbar vertebrae registers clinical CT with micro-CT (105 μm) to help develop super-resolution methods for visualizing trabecular bone microarchitecture, invisible on routine CT.
Several FDA-approved drugs like metformin and doxycycline show anticancer effects but poor tumor selectivity. Nanocarrier delivery enhances tumor accumulation, bioavailability, and enables combination therapy, but clinical translation faces regulatory hurdles. (Review; no origin…
A domain-adaptation method (RegAlign) substantially reduced cross-group performance gaps in MRI-based dementia classification between Non-Hispanic White and Hispanic White populations in a multi-site study, while standard models showed significant bias when tested across racial…
First-pass reperfusion (mTICI 2c-3) after a single device pass was achieved in 46% (94/204) of acute stroke thrombectomy patients. An explainable ML model (Random Forest) predicted FPE from collateral status, systolic BP, hypertension, age with best accuracy/specificity/F1; AdaB…
A digital twin (DT) framework reduced online adaptive proton-therapy reoptimization time to 5.52±2.94 min vs 17.66±7.93 min for clinical workflows (p not given), while achieving comparable plan quality scores (164.01 vs 161.23) and DIL/CTV V100 coverage >99% in prostate SBRT wit…
A dual-embedding neural network that integrates patient-specific hemodynamic boundary conditions with coronary geometry achieved AUC 0.90 for FFR prediction vs. invasive FFR in a proof-of-concept study of 288 patients; inference is real-time but not yet externally validated.
On 27 radiology questions, DeepSeek-R1 scored higher than ChatGPT-o1 (mean 4.51 vs 3.73 on a 5-point scale, P<.001). When ChatGPT-o1 answered image-based questions, residents rated it lower than its own text answers, particularly for factual accuracy (mean 2.75). Both models sho…
Seven of 12 LLMs achieved human-level accuracy (96.2%) extracting binary structured data from ILD clinic notes—at seconds per note and under US $10.50 per patient. Multiclass ILD classification accuracy dipped to 88–91%, demonstrating feasibility but reduced reliability for comp…
A study on deep learning-accelerated MRI for back pain, claiming faster scans and better quality, has been retracted by La Radiologia medica. No reason given in retraction note.
In a retrospective study of 166 hypervascular LI-RADS 3 observations <2 cm without ancillary features, only 3.0% (95% CI 0–6.1%) progressed to HCC at 1 year, far lower than the ~one-third rate often cited for the overall LR-3 category.
In a meta-analysis of 11,326 patients, intracranial atherosclerotic disease (ICAD) LVO was associated with lower odds of successful reperfusion after endovascular treatment (OR 0.46, 95%CI 0.31–0.70), but functional independence and mortality did not differ from non-ICAD LVO. Sy…
Technical considerations for NBCA sac packing of true visceral artery aneurysms are discussed, aiming to advance the method. No efficacy or safety outcomes were reported in the source snippet.
