A smartphone image–centered deep learning model showed promise for intraoperative diagnosis and grading of clinical stage IA lung adenocarcinoma, but grade-specific limitations and lack of outcomes data mean the tool remains investigational.
Attenuation imaging increased with visually graded steatosis severity in pediatric patients, but findings were not validated against MRI-PDFF or biopsy.
Radiologists assigned to receive step-by-step explanations from a large language model achieved higher diagnostic accuracy in a randomized vignette study, while differential-diagnosis outputs may have increased inappropriate reliance on incorrect model suggestions.