On 76 test cases, the AI framework achieved Cobb angle MAE 2.4°, Lenke curve type accuracy 0.895, and reduced review time from 8.2 to 1.5 min/case.
PSAD remained below 0.11 ng/mL² across all ages in 1037 healthy German men, contrasting with continuously rising PSA. 95th percentile reference: PV 51.39 mL, PSA 2.79 ng/mL, PSAD 0.071 ng/mL².
Noncontrast CT-based unimodal imaging AI detected anterior circulation large vessel occlusion with sensitivity 0.78 (95% credible interval 0.68-0.86) and specificity 0.88, versus expert readers' sensitivity 0.62 and similar specificity; low-certainty retrospective evidence.
SIR Foundation research consensus panel calls for standardized acute DVT intervention endpoints: biologically informed patient selection, anatomic/physiologic metrics, validated severity tools, longitudinal biomarkers, and economic/QoL measures to advance precision and reduce po…
In a phantom study, a 30-40% data extraction percentage for data-driven gating combined with deep learning PET reconstruction (AiCE-i) yielded optimal balance between image noise and respiratory motion effects.
Gemini 3.0 achieved mean Dice 0.935 for zero-shot STS segmentation (radiologist inter-rater Dice 0.949). Tumor size from masks had ICC 0.976 vs 0.922 for direct LLM estimate (p=0.027), with bias -0.5 mm vs -5.0 mm. Segmentation-derived measurements are more reliable.
Imaging evaluation of liver metastases is evolving from purely morphologic assessment to biologically informed techniques. Advanced imaging, radiomics, and artificial intelligence can assess tumor biological heterogeneity, guide therapy, and predict outcomes.
Pairing hip X-ray or MRI with radiology text descriptions boosted multimodal LLMs' detection of femoral head osteonecrosis: AUC 0.91 vs 0.55 for image-only, and staging reliability ICC 0.97 vs 0.51. Multi-image input offered no benefit.
Applying conformal prediction to vision-language model report drafting for chest X-rays, high-confidence outputs showed significantly better agreement with radiologist impressions (P<0.001) and higher classification AUROC (P<0.05).
CT radiomics-based SVM model predicted early treatment response in advanced NSCLC, with AUC 0.90 (95% CI 0.82-0.97) for chemo-immunotherapy and 0.84 (95% CI 0.73-0.95) for immunotherapy, externally validated.
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.
French radiology is advancing with innovations in dual-energy and photon-counting CT, AI for cancer diagnosis, and interventional radiology, enhancing diagnostic accuracy and patient outcomes.
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…
Multidisciplinary guideline recommends pre- and post-reduction imaging, biomechanical reduction first, 1-week immobilization, and surgery for age <40, contact sports, or bone loss (low GRADE evidence).
Letter to the Editor: Concordance of vibration-controlled transient elastography and magnetic resonance elastography for fibrosis staging in patients with metabolic dysfunction-associated steatotic liver disease.
Letter to the Editor: Autonomous robotic thrombectomy should be considered a near-term frontier for AI-enabled interventional radiology.
Current AI scribe assessments focus on initial note drafts, but signed clinical notes are dynamic—errors can compound as content is copied, coded, and re-ingested by downstream tools. Safety must be measured by tracking these cascading effects across the patient record.
From Model Accuracy to Patient Benefit: Rethinking Evaluation of Radiology AI.
Specialization, Structural Range, and Redeployability in Radiology Careers.
Rethinking Interventional Radiology Night Call: Impact of Two Call Models on Physician Wellness, Academic Missions and Clinical Productivity.
Heparin Resistance During Iliocaval Thrombectomy in a Hypercoagulable Patient.
For knee OA, weight loss, exercise, and education remain core interventions for preserving joint healthspan. Genicular artery embolization may help in synovitis-dominant cases but lacks consistent sham-controlled evidence.
In a pilot study of 30 children with neuroblastoma, T2-weighted MRI radiomics with XGBoost achieved an AUC of 0.88 for distinguishing high-risk from low/intermediate-risk tumors, suggesting potential as a noninvasive imaging biomarker.
A deep learning model using longitudinal CT radiomics predicted rib fracture risk after stereotactic body radiotherapy in NSCLC patients, achieving an AUC of 0.792 on validation. The model-predicted high-risk group had a hazard ratio of 10.82 compared to the low-risk group.
The ACR Appropriateness Criteria 2026 update provides imaging guidelines for suspected or confirmed diffuse lung disease, covering initial evaluation, acute exacerbation, and surveillance.
EndoFusion, an unpaired multi-modal AI framework, detected endometriosis signs (POD obliteration, bowel nodules) on TVUS and MRI with average AUC 0.827 (95% CI 0.790–0.861).
Deep learning (DL)-based reconstruction of multi-shot breast DWI significantly improved SNR, CNR, lesion conspicuity, and reduced acquisition time by 29% vs. standard rs-EPI, with gains confirmed in a separate validation cohort, supporting clinical integration.
80 kVp coronary CT angiography with deep learning reconstruction reduced radiation dose from 4.46 to 2.85 mSv and contrast dose from 43.64 to 34.62 mL in overweight patients while improving image quality.
Correction: Reliability and diagnostic performance of an automated MRI-based classifier compared with radiologists in Alzheimer's disease.
A DCE-MRI radiomics model using gradient boosting decision tree (GBDT) and feature selection showed high predictive performance for breast cancer molecular subtyping.
FDA cleared via 510(k) the EM-TECH Passive Ultrasound Probe Strap (product code ITX) from EM-TECH Solutions, a radiology device.
FDA cleared Lucida Medical's Prostate Core, a radiological image processing software (product code QIH), via the 510(k) pathway. The clearance supports the device's use in prostate imaging analysis.
Multimodal image fusion combines anatomical computed tomography/magnetic resonance imaging with functional positron emission tomography/single-photon emission computed tomography to improve analysis and treatment planning; review covers six method families and future trends.
Response to "Consideration of Statin Therapy in the Interpretation of Artificial Intelligence-Derived Coronary Artery Calcium Density".