相关实验视频

Updated: Jul 14, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

使用维库纳保护隐私的大型语言模型用于标记放射学报告的可行性

Pritam Mukherjee¹, Benjamin Hou¹, Ricardo B Lanfredi¹

¹From the Imaging Biomarkers and Computer-Aided Diagnosis Laboratory, Department of Radiology and Imaging Sciences, National Institutes of Health Clinical Center, Bldg 10, Room 1C224D, 10 Center Dr, Bethesda, MD 20892-1182.

|October 10, 2023

概括

一个本地运行的大型语言模型 (LLM),Vicuna,在标记胸部X光学报告中显示了中等到实质性的协议,对13个发现进行了标记,证明了对隐私意识分析的可行性.

科学领域:

医疗成像中的人工智能
放射学自然语言处理用于放射学.

背景情况:

由于患者隐私问题,像ChatGPT这样的大型语言模型 (LLM) 不适合放射学报告.
当地部署LLM是必要的,以解决医疗数据的隐私限制.
维库纳-13B为当地在医疗保健领域的LLM应用提供了潜在的替代方案.

研究的目的:

评估使用Vicuna-13B LLM用于标记胸部X光学报告的可行性.
评估Vicuna-13B在确定X光学报告中的13个具体发现方面的表现.
为了比较Vicuna-13B的标签准确度与已建立的自动标签者和人类放射科医生.

主要方法:

来自MIMIC-CXR和NIH数据集的胸部放射学报告被追溯分析.
维库纳-13B被采用单步和多步提示策略来识别13个放射性发现.
使用Fleiss κ与CheXpert和CheXbert标签剂进行了评估,AUC用于放射科医生注释的子集的性能评估.

主要成果:

使用多步骤提示策略的Vicuna-13B在两个数据集中与CheXpert和CheXbert取得了中等到实质性的协议 (κ中位数为0.520.64).
该模型的性能与现有的标签器相比 (中位数AUC为0.84) 在11个发现中的9个结果中表现相似.
在随机的超参数设置下评估了中期协议,以确保可靠性.

结论:

法学士Vicuna-13B证明了胸部X光学报告的标签可行性,与既有方法达成中等到实质性的协议.
这项研究作为一种概念验证,用于在放射性报告分析中使用本地部署的LLM.
维库纳-13B显示出对医疗成像报告的隐私保护自动化分析的承诺.

更多相关视频

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

相关概念视频

Radiological Investigation I: X-ray and CT

Radiological Investigation I: X-ray and CT

Radiological investigations, including X-rays and computed tomography (CT) scans, are critical for diagnosing and evaluating various medical conditions. These imaging techniques provide valuable insights into the body's internal structures, aiding in the detection of abnormalities, assessment of disease progression, and development of treatment strategies. This article delves into two primary radiological investigations, chest X-rays and CT scans, outlining their purpose, procedures, and...

Computed Tomography

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...