AI RESEARCH
Unleashing Video Language Models for Fine-grained HRCT Report Generation
arXiv CS.CV
•
ArXi:2603.12469v1 Announce Type: new Generating precise diagnostic reports from High-Resolution Computed Tomography (HRCT) is critical for clinical workflow, yet it remains a formidable challenge due to the high pathological diversity and spatial sparsity within 3D volumes. While Video Language Models (VideoLMs) have nstrated remarkable spatio-temporal reasoning in general domains, their adaptability to domain-specific, high-volume medical interpretation remains underexplored.