GeneralNewsBrief
Testing Overview: Nuclear Medicine and PET (10-20-2026)
Testing Overview: Nuclear Medicine and PET (10-20-2026)
American College of Radiology (ACR)via Google News
Latest
5678 storiesNuclear / MolecularGeneralNews
Capitol Imaging acquires 4 South Florida centers, adds molecular imaging
Capitol Imaging Services acquires Impression Imaging's four outpatient centers in South Florida, expanding into molecular imaging and theranostics. Radiologist co-founder Michael Fagien, MD becomes Chief Medical Officer of molecular imaging to guide expansion.
Radiology Business
GeneralNews
Radiology Partners turns to high-yield bonds for Everlight Radiology acquisition
Radiology Partners sold high-yield bonds yielding 10% to fund its acquisition of Everlight Radiology amid a weak lending market, the company confirmed.
Radiology Business
BreastNewsBrief
Koning Vera breast CT system gets Health Canada license
Koning gets Health Canada license for Vera breast CT system
AuntMinnievia Google News
Nuclear / MolecularAI / InformaticsResearch
AI-Guided Design Yields TROP-2-Targeting Peptide PET Tracer With Nanomolar Affinity
AI-designed peptide PET tracer [68Ga]Ga-DOTA-TR23 shows nanomolar affinity (KD=26.8 nM) for TROP-2, with rapid, specific tumor uptake and high contrast in pancreatic, prostate, and thyroid cancer mouse models.
Bioconjugate chemistry
Neuro / Head & NeckAI / InformaticsResearch
End-to-End Multiagent AI System Outperforms Initial Reads for Glioma BT-RADS Scoring
In a retrospective study of 492 posttreatment glioma MRI exams, an automated AI system achieved 76.0% accuracy for Brain Tumor Reporting and Data System (BT-RADS) scoring, compared with 57.5% for initial assessments (absolute improvement +18.5 percentage points, P<.001).
Radiology. Artificial intelligence
GeneralAI / InformaticsResearch
TRAM-AI Checklist for Verifying Usable Medical Imaging Datasets in AI Development
A 14-item TRAM-AI checklist for verifying medical imaging dataset accessibility for AI was developed via Delphi consensus. In pilot testing of 10 datasets, compliance was 10% for archive validation and 30% for partition keys, highlighting gaps in functional usability.
Radiology. Artificial intelligence
CardiacChest / ThoracicAI / InformaticsResearch
Deep learning on chest radiographs detects reduced ejection fraction, may cut echo volume
A deep learning model detected LVEF ≤40% on chest X-rays with AUC 0.92-0.97 in checkup cohorts, enriching baseline prevalence 37-87-fold, and could reduce echocardiography volume up to 85% without missing cases.
Radiology. Artificial intelligence
GeneralResearchBrief
Variance Decomposition: Understanding What Drives Between-State Variability.
Variance Decomposition: Understanding What Drives Between-State Variability.
AJR. American journal of roentgenology
GeneralResearchBrief
Litigation on Obstetric Ultrasound Reporting Offers Lessons for Radiologists.
Litigation on Obstetric Ultrasound Reporting Offers Lessons for Radiologists.
AJR. American journal of roentgenology
GeneralEducationBriefTrainee
How to Navigate Data and Research Ethics.
How to Navigate Data and Research Ethics.
AJR. American journal of roentgenology
GeneralNewsBrief
The Artificial Intelligence (AI) Arms Race: When Hospital and Insurer Bureaucrats Equipped With AI Make Healthcare More
The Artificial Intelligence (AI) Arms Race: When Hospital and Insurer Bureaucrats Equipped With AI Make Healthcare More Expensive for Patients.
AJR. American journal of roentgenology
GeneralNewsBrief
ESR Bridges: high-risk steatotic liver disease: new developments in non-invasive tests and treatment-a multidisciplinary
ESR Bridges: high-risk steatotic liver disease: new developments in non-invasive tests and treatment-a multidisciplinary view.
European radiology
Musculoskeletal (MSK)AI / InformaticsResearch
Automated MRI Muscle Fat Fraction Correlates with Disease Severity and Functional Decline in CMT1A
Automated MRI muscle fat fraction quantification in CMT1A correlates with disease severity and functional impairment, with anterior compartment FF showing moderate correlations with stair climb time (r=0.68) and 6-min walk distance (r=-0.66).
Muscle & nerve
Chest / ThoracicEducationTrainee
Lung-RADS: Current Updates and Future Directions for Lung Cancer Screening Reporting
ACR Lung-RADS continues to evolve, with latest updates addressing volumetric vs. diameter measurement, sub-solid nodule management, Category 0 for infectious findings, and a new Atlas. Future directions include AI integration and risk-based approaches to refine lung cancer scree…
Cancer imaging : the official publication of the International Cancer Imaging Society
GeneralAI / InformaticsResearch
Existing Clinical CT Data Infrastructure Partially Supports an Operational Radiology Ontology
48.1% of 156 CT workflow data properties were directly available in structured form in clinical data systems; 33.3% required standardization, 11.5% were not readily available, indicating partial support for an operational radiology ontology.
Journal of imaging informatics in medicine
Neuro / Head & NeckAI / InformaticsResearch
Systematic Review: Fairness Reporting Lacking in Studies of Commercial Stroke CT AI Tools
Only one of thirteen studies on regulator-cleared AI for acute stroke CT reported subgroup performance, showing lower PPV for female vs male (67.3% vs 72.7%, p=0.02) and Black vs non-Black patients (66.7% vs 73.2%, p=0.005).
Academic radiology
Chest / ThoracicAI / InformaticsResearch
Combined CXR Radiomics and Clinical Model Screens for Preserved Ratio Impaired Spirometry
A combined chest X-ray radiomics and clinical model identified preserved ratio impaired spirometry (PRISm) with AUC 0.759 (95% CI 0.658–0.854) in external validation, outperforming radiomics-alone (AUC 0.618) and clinical-alone (AUC 0.655) models (p<0.001).
Academic radiology
BreastAI / InformaticsResearch
Multiparametric MRI deep learning radiomics model predicts axillary pCR after neoadjuvant chemo in breast cancer.
A multiparametric MRI deep learning radiomics model predicted axillary pathological complete response in cN+ breast cancer after neoadjuvant chemo with AUC 0.949 (training, 95% CI 0.912-0.986) and 0.932 (validation, 95% CI 0.867-0.998). Could help select patients for axillary de…
Magnetic resonance imaging
Neuro / Head & NeckPediatricAI / InformaticsResearch
FeTal-SAM: Atlas-prompted Segment Anything Model for fetal brain MRI achieves flexible segmentation without retraining
FeTal-SAM adapted SAM with atlas-based prompts for fetal brain MRI segmentation. On two datasets, Dice scores matched dataset-specific baselines for well-contrasted structures (cortical plate, cerebellum) but were lower for subtle structures like hippocampus. The method segments…
NeuroImage
GeneralAI / InformaticsResearchBrief
Optimizing learning for control of human-machine interfaces.
Optimizing learning for control of human-machine interfaces.
Neuron
BreastAI / InformaticsEducationTrainee
AI and Gamification Tools for Precision Breast Imaging Education
AI large language models and gamified learning tools show promise for personalizing breast imaging training and boosting engagement, potentially addressing knowledge gaps from limited workstation teaching and differing case exposure among trainees.
Journal of breast imaging
GeneralAI / InformaticsResearchBrief
Vision-Enabled Large Language Models in Mammography: From Benchmarking to Clinical Accountability.
Vision-Enabled Large Language Models in Mammography: From Benchmarking to Clinical Accountability.
Journal of breast imaging
Musculoskeletal (MSK)AI / InformaticsResearchTrainee
DL-accelerated shoulder MRI cuts scan time 38.7% but may underdetect bursitis and supraspinatus tears
Sonic DL reduced nominal acquisition time by 38.7% (6:15 vs 10:12 min:s) vs AIR Recon DL in shoulder MRI, but subacromial/subdeltoid bursitis and supraspinatus tears were detected less often (P=0.049, P=0.006) in a pilot of 30 patients.
Skeletal radiology
Body / AbdominalResearchTrainee
Synthetic MRI T1/T2 and ADC combination yields higher AUC than PI-RADS v2.1 for zone-specific prostate cancer detection
In 141 prostate MRI lesions, a model combining synthetic MRI T1, T2, and ADC showed AUC 0.947 in the peripheral zone and 0.961 in the transition zone, vs PI-RADS v2.1 AUC 0.799 and 0.803 (P=0.002, P=0.013).
International urology and nephrology
GeneralResearchBrief
AI-Enhanced CTA Triage Improves Detection of Intracranial Vessel Occlusions in Routine Clinical Workflow.
AI-Enhanced CTA Triage Improves Detection of Intracranial Vessel Occlusions in Routine Clinical Workflow.
Journal of the American College of Radiology : JACR
GeneralNewsBrief
Can MRI-Based AI Have an Impact in Reducing Unnecessary Prostate Biopsies?
Can MRI-Based AI Have an Impact in Reducing Unnecessary Prostate Biopsies?
Diagnostic Imagingvia Google News +1 more
Body / AbdominalAI / InformaticsNewsTrainee
AI Software Cuts Unnecessary Prostate Biopsies by 18.9% for PI-RADS 3 Lesions on MRI
AI software reclassified PI-RADS 3 prostate MRI lesions with 98.4% sensitivity, yielding an 18.9% reduction in unnecessary biopsies. Lesion-level sensitivity was lower (78.8% vs 88.8% for PI-RADS), supporting its role as a decision aid for radiologists.
Diagnostic Imaging
GeneralNewsBrief
AuntMinnie.com Women's Imaging Insider
AuntMinnie.com Women's Imaging Insider
AuntMinnievia Google News
GeneralNewsBrief
Brainomix highlights CT study using e-Lung software
Brainomix highlights CT study using e-Lung software
AuntMinnievia Google News