PET-F2I: A Comprehensive Benchmark and Parameter-Efficient Fine-Tuning of LLMs for PET/CT Report Impression Generation

ArXi:2603.10560v1 Announce Type: new PET/CT imaging is pivotal in oncology and nuclear medicine, yet summarizing complex findings into precise diagnostic impressions is labor-intensive. While LLMs have shown promise in medical text generation, their capability in the highly specialized domain of PET/CT remains underexplored. We