Preprint
Aug 2026
Resolution Meets Reduction: Efficient Visual Context for 3D Radiology Report Generation
Vision-language models offer a promising path toward automating radiology report generation, but applying them to full 3D CT volumes poses substantial computational challenges. Modern foundation vision encoders (VEs) can produce tens of thousands of vision tokens per scan, making the visual sequence passed to the large...
Jonathan Suprijadi, Raphael Stock, Moritz Langenberg et al.
· 1 citation