Coarse-to-Fine Personalized LLM Impressions for Streamlined Radiology Reports

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Chengbo, Leong, Hui Yi, Li, Lei
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