Bilateral Dynamic CT Uses Contralateral Wrist to Diagnose Scapholunate Injury
Using the patient's healthy wrist as an internal control eliminates the need for external reference sets in 4D computed tomography.
Multi-Echo T2* MRI Identifies Neonatal Hemochromatosis via Extrahepatic Iron Patterns
Pancreatic and thyroid siderosis on MRI distinguishes neonatal hemochromatosis from other liver failure causes with 92.3% accuracy.
AI Detects Occult Pancreatic Cancer 15 Months Before Radiologists on CT
A validated radiomics model identifies subvisual signatures of pancreatic ductal adenocarcinoma with 73% sensitivity at a 475-day lead time.
Retinal Imaging AI Screens for Six Systemic Metabolic and Endocrine Diseases
A multitask framework identifies diabetes, hypertension, and osteoporosis from fundus photos, showing high negative predictive value in primary care.
Spectral CT Reconstructions Improve Acute Bowel Ischemia Detection
Adding iodine maps and monoenergetic images to portal venous CT increases diagnostic accuracy from 73% to 86% across scanner platforms.
Ultrasound-Derived Fat Fraction Accurately Grades Steatosis in Chronic Liver Disease
A multicenter study shows ultrasound-derived fat fraction provides high diagnostic accuracy across diverse etiologies and fibrosis stages.
Artificial Intelligence Matches Physician Committees in Adjudicating Cardiovascular Trial Endpoints
An automated system shows high agreement with human experts in identifying major adverse cardiovascular events in a large clinical trial.
Explainable AI Identifies Cortical Asymmetry to Detect Major Depression
A deep learning model using fNIRS data achieves 81% accuracy by mapping hemodynamic imbalances in the dorsolateral prefrontal cortex.
Photon-Counting CT Matches V/Q SPECT for CTEPH Perfusion Mapping
A retrospective study shows high quantitative concordance between photon-counting CT and scintigraphy for lobar lung perfusion assessment.
Normalization Choice Impacts Molecular Rejection Diagnosis in Kidney Transplants
Standardized data processing maintains high diagnostic accuracy for antibody and T cell-mediated rejection in allograft biopsies.
Training-Free AI Framework Automates Radiographic Morphometry Across Multiple Joints
A generalist landmark matching model achieves measurement accuracy comparable to radiologists without requiring anatomy-specific datasets.
[89Zr]girentuximab PET Identifies Any Renal Malignancy with 98% Positive Predictive Value
A secondary analysis of the ZIRCON trial indicates the CAIX-targeted tracer detects non-clear cell subtypes with high clinical accuracy.