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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Liu, Yuchen, Zhang, Wenbo, Peng, Liling, Zhang, Yichi, Fu, Yu, Guo, Xin, Qu, Chao, Qi, Yuan, Xue, Le
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915853757317120
author Liu, Yuchen
Zhang, Wenbo
Peng, Liling
Zhang, Yichi
Fu, Yu
Guo, Xin
Qu, Chao
Qi, Yuan
Xue, Le
author_facet Liu, Yuchen
Zhang, Wenbo
Peng, Liling
Zhang, Yichi
Fu, Yu
Guo, Xin
Qu, Chao
Qi, Yuan
Xue, Le
contents 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 introduce PET-F2I-41K (PET Findings-to-Impression Benchmark), a large-scale benchmark for PET/CT impression generation using LLMs, constructed from over 41k real-world reports. Using PET-F2I-41K, we conduct a comprehensive evaluation of 27 models across proprietary frontier LLMs, open-source generalist models, and medical-domain LLMs, and we develop a domain-adapted 7B model (PET-F2I-7B) fine-tuned from Qwen2.5-7B-Instruct via LoRA. Beyond standard NLG metrics (e.g., BLEU-4, ROUGE-L, BERTScore), we propose three clinically grounded metrics - Entity Coverage Rate (ECR), Uncovered Entity Rate (UER), and Factual Consistency Rate (FCR) - to assess diagnostic completeness and factual reliability. Experiments reveal that neither frontier nor medical-domain LLMs perform adequately in zero-shot settings. In contrast, PET-F2I-7B achieves substantial gains (e.g., 0.708 BLEU-4) and a 3.0x improvement in entity coverage over the strongest baseline, while offering advantages in cost, latency, and privacy. Beyond this modeling contribution, PET-F2I-41K establishes a standardized evaluation framework to accelerate the development of reliable and clinically deployable reporting systems for PET/CT.
format Preprint
id arxiv_https___arxiv_org_abs_2603_10560
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle PET-F2I: A Comprehensive Benchmark and Parameter-Efficient Fine-Tuning of LLMs for PET/CT Report Impression Generation
Liu, Yuchen
Zhang, Wenbo
Peng, Liling
Zhang, Yichi
Fu, Yu
Guo, Xin
Qu, Chao
Qi, Yuan
Xue, Le
Computer Vision and Pattern Recognition
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 introduce PET-F2I-41K (PET Findings-to-Impression Benchmark), a large-scale benchmark for PET/CT impression generation using LLMs, constructed from over 41k real-world reports. Using PET-F2I-41K, we conduct a comprehensive evaluation of 27 models across proprietary frontier LLMs, open-source generalist models, and medical-domain LLMs, and we develop a domain-adapted 7B model (PET-F2I-7B) fine-tuned from Qwen2.5-7B-Instruct via LoRA. Beyond standard NLG metrics (e.g., BLEU-4, ROUGE-L, BERTScore), we propose three clinically grounded metrics - Entity Coverage Rate (ECR), Uncovered Entity Rate (UER), and Factual Consistency Rate (FCR) - to assess diagnostic completeness and factual reliability. Experiments reveal that neither frontier nor medical-domain LLMs perform adequately in zero-shot settings. In contrast, PET-F2I-7B achieves substantial gains (e.g., 0.708 BLEU-4) and a 3.0x improvement in entity coverage over the strongest baseline, while offering advantages in cost, latency, and privacy. Beyond this modeling contribution, PET-F2I-41K establishes a standardized evaluation framework to accelerate the development of reliable and clinically deployable reporting systems for PET/CT.
title PET-F2I: A Comprehensive Benchmark and Parameter-Efficient Fine-Tuning of LLMs for PET/CT Report Impression Generation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2603.10560