相关实验视频

Updated: Jun 18, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

在神经放射学病例中评估大型语言模型的诊断准确性,使用来自JAMA神经学和JAMA临床挑战的图像输入

Ahmed Albaqshi¹, Ji Su Ko^1,2, Chong Hyun Suh³

¹Department of Radiology and Research Institute of Radiology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.

Scientific reports

|November 27, 2025

概括

大型语言模型 (LLM) 显示出强大的文本诊断技能,但在复杂的放射图像解释方面遇到了困难. 克劳德3.5在准确度方面领先,表现相当于第一年学员.

科学领域:

人工智能在医学中的应用
医学成像分析医学成像分析
神经学诊断神经学诊断

背景情况:

大型语言模型 (LLM) 越来越多地被用于医学应用.
评估LLM诊断性能,特别是在复杂的医学成像中,至关重要.
神经学放射学提出了具有挑战性的病例,需要细微的解释.

研究的目的:

评估六个领先的LLM (GPT-4v,GPT-4o,Gemini 1.5 Pro,Gemini 1.5 Flash,Claude 3.0,Claude 3.5) 在复杂的神经学放射病例上的诊断准确度.
为了比较LLM的表现与人类专家 (神经放射学家,研究员,初级教师).
评估LLM在独立解释医疗图像与附带文本方面的能力.

主要方法:

使用了来自JAMA神经学和JAMA (2015年5月至2024年4月) 的56个复杂的神经学放射病例.
案件以四种格式向LLM提交:原始文本/图像,重新表述的文本/图像,仅重复表述的文本和仅图像.
对三个神经放射学家进行了对比,并使用Fleiss' kappa对五次重复的一致性进行了评估.

主要成果:

克劳德3.5在原始图像和文本输入中实现了最高准确度 (80.4%).
修改文本和图像的LLM准确度在62.5%至76.8%之间.
法学士的表现与第一年学员 (71.4%) 相当,但表现优于初级教师 (51.8%) 和第二年学员 (48.2%).
在仅使用图像的任务中,LLM识别病理位置的准确性差异很大 (21.5%至63.1%).
所有测试的LLM都在重复中表现出很高的一致性 (Fleiss' kappa:0.860-1.000).

结论:

当提供临床文本时,LLM表现出强大的诊断性能,与早期职业生涯的医疗专业人员相比.
当前的LLM对复杂放射学图像的独立解释仍然有限,这凸显了需要改进图像分析能力的需要.
在人工智能驱动的图像分析中进一步的进步是必要的,以便将LLM无整合到临床放射学工作流程中.

关键词:

神经成像是一种神经成像.人工智能的人工智能是人工智能.计算机辅助的计算机辅助.深度学习是一种深度学习.图像解释图像解释

更多相关视频

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

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

相关概念视频

Imaging Studies I: CT and MRI

Imaging Studies I: CT and MRI

Introduction: MRI and CT scans are crucial advancements in medical imaging techniques, playing a vital role in diagnosing conditions related to the gastrointestinal (GI) system. Each scan serves distinct purposes, targets specific areas, and requires unique nursing duties.
Description of the Procedures
Computed Tomography (CT) scan:
Computed Tomography (CT) scans use X-ray technology to generate detailed images of bones, organs, and tissues. During the scan, the patient lies on a moving table...

Imaging Studies II: Positron Emission Tomography and Scintigraphy

Imaging Studies II: Positron Emission Tomography and Scintigraphy

Positron Emission Tomography (PET) is a medical imaging technique that provides crucial insights into the body's physiological functions at a molecular level. It is an indispensable resource for diagnosing, staging, and monitoring various illnesses, notably cancer, neurological disorders, and cardiovascular conditions.
Fundamental Principles of PET

Imaging Studies VII: Vascular Imaging

Imaging Studies VII: Vascular Imaging

DefinitionRenal angiography, also known as renal arteriography, is an imaging technique used to obtain a comprehensive view of blood flow and the vascular structure of blood vessels in the kidneys and surrounding areas.PurposeRenal angiography detects blood vessel abnormalities in the kidneys, such as aneurysms, stenosis, thrombosis, vascular tumors, and renal artery stenosis. It evaluates kidney function and guides interventional treatments like angioplasty or stent placement.Pre-Procedure...