Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911180982845440 |
|---|---|
| author | Sun, Chengbo Leong, Hui Yi Li, Lei |
| author_facet | Sun, Chengbo Leong, Hui Yi Li, Lei |
| contents | The manual creation of the "Impression" section in radiology reports is a primary driver of radiologist burnout. To address this challenge, we propose a coarse-to-fine framework that leverages open-source large language models (LLMs) to automatically generate and personalize impressions from clinical findings. The system first produces a draft impression and then refines it using machine learning and reinforcement learning from human feedback (RLHF) to align with individual radiologists' styles while ensuring factual accuracy. We fine-tune LLaMA and Mistral models on a large dataset of reports from the University of Chicago Medicine. Our approach is designed to significantly reduce administrative workload and improve reporting efficiency while maintaining high standards of clinical precision. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_15845 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports Sun, Chengbo Leong, Hui Yi Li, Lei Computation and Language Artificial Intelligence The manual creation of the "Impression" section in radiology reports is a primary driver of radiologist burnout. To address this challenge, we propose a coarse-to-fine framework that leverages open-source large language models (LLMs) to automatically generate and personalize impressions from clinical findings. The system first produces a draft impression and then refines it using machine learning and reinforcement learning from human feedback (RLHF) to align with individual radiologists' styles while ensuring factual accuracy. We fine-tune LLaMA and Mistral models on a large dataset of reports from the University of Chicago Medicine. Our approach is designed to significantly reduce administrative workload and improve reporting efficiency while maintaining high standards of clinical precision. |
| title | Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2508.15845 |