从细分到解释:使用LLMs从MRI生成文本报告
Alberto G Valerio1, Katya Trufanova1, Salvatore de Benedictis1
1Department of Computer Science, University of Bari Aldo Moro, Bari, Italy.
Computer methods and programs in biomedicine
|July 9, 2025
概括
这项研究通过将语义细分与大型语言模型 (LLM) 结合起来,提高了医疗成像中的AI可解释性,以生成可靠,人类可读的诊断报告,提高临床医生的对AI的信心. 该代码是公开可用的可复制性.
科学领域:
- 医学成像和人工智能 医学成像和人工智能
- 在医疗保健中的自然语言处理.
背景情况:
- 医学成像中的深度学习模型缺乏透明度,阻碍临床医生对AI诊断的信任.
- 可解释性AI (XAI) 对于将AI整合到临床实践中并确保可靠的医疗保健结果至关重要.
研究的目的:
- 开发一种新的框架,以提高医疗成像中的AI可解释性.
- 从使用大型语言模型 (LLM) 的AI分析中生成全面的,人类可读的医疗报告.
主要方法:
- 语义细分模型与基于地图的映射和报告生成的LLM集成.
- 使用结构化的JSON和提示约束来确保事实准确性的反幻觉设计的实施.
- 验证关于脑瘤 (结质瘤) 和多发性硬化症病变检测任务的框架.
主要成果:
- 通过SegResNet模型实现了高细分精度.
- LLM (Gemma,Llama,Mistral) 在生成多样化和信息丰富的解释报告方面表现出有效性.
- 生成的报告被评估为词汇多样性,可读性,连贯性和信息覆盖.
结论:
- 拟议的方法显著提高了AI在医学成像中的透明度和可解释性.
- 该框架的通用性在不同的医学成像场景中得到了验证,增加了对AI应用程序的信任.
- 公共可用的代码和示例有助于在医疗保健中采用和进一步开发可解释的人工智能.
相关概念视频
01:24Magnetic Resonance Imaging
7.2K
Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...
7.2K
02:07Improving Translational Accuracy
2.7K
2.7K
01:21Imaging Studies for Cardiovascular System IV: CMRI
140
Cardiovascular magnetic resonance imaging, or CMRI, is a non-invasive diagnostic test that employs a magnetic field and radiofrequency waves to create precise images of the heart and arteries. It provides comprehensive information about cardiac anatomy, function, perfusion, and tissue characterization without ionizing radiation.IndicationsCMRI diagnoses various heart conditions, including tissue damage from heart attacks, ischemic heart disease, myocarditis, aortic issues (tears, aneurysms,...
140