Get Started
Home
Topics
Search
Library
Research questionHow can vision-language models reliably report clinically meaningful changes between serial CT scans?Clinical interpretation often depends on how disease changes between studies, but models focused on individual CT scans may miss or misstate those interval changes.
AI
Computer Vision
Evaluation & Benchmarks
Health
Image & Video Processing
Multimodal Models
Latest papersRecent research connected to this question, newest first.CT-$Δ$Bench: A Benchmark for Longitudinal 3D Medical Imaging Difference Reporting with Vision-Language ModelsThe source describes CT-ΔBench with patient-level splits, change-aware evaluation metrics, physician validation of synthesized references and extracted events, and comparisons between direct paired-CT reasoning and two-stage textual differencing. It also includes DeltaMed as a baseline; the abstract does not provide performance results or establish clinical deployment capability.research paper · Sep 4, 2026
Related questions
How can automated brain-MRI reporting compare longitudinal studies to describe subtle, distributed interval changes?How can longitudinal MRI models forecast neurodegenerative progression without confusing stable anatomy or noise with disease change?How can mammography vision-language models make reliable zero-shot predictions from high-resolution images and homogeneous reports?How can vision-language models interpret whole-body PET/CT by grounding metabolic and anatomical findings?