相关实验视频

Updated: Aug 12, 2026

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Detection of Architectural Distortion in Prior Mammograms via Analysis of Oriented Patterns

Published on: August 30, 2013

对大型语言模型的潜力,陷和局限性进行初步调查,用于乳房图解读

Filippo Pesapane¹, Luca Nicosia², Anna Rotili²

¹Breast Imaging Division, Radiology Department, IEO European Institute of Oncology IRCCS, Milan, Italy. filippo.pesapane@ieo.it.

Discover oncology

|February 24, 2025

概括

像GPT-4这样的大型语言模型在解释乳房影像方面表现出有限的能力,在识别投影,微化和质量方面准确度低. 进一步开发和监管人工智能对于医疗成像安全临床使用至关重要.

科学领域:

医疗成像医学成像
人工智能的人工智能
放射学放射学是一门学科.

背景情况:

大型语言模型 (LLM) 越来越多地被用于医学应用.
乳房显微镜仍然是乳腺癌查的关键工具.

研究的目的:

评估GPT-4对乳房图像的解释能力.
评估LLMs在识别乳房镜检测结果的准确性,在没有临床背景的情况下.

主要方法:

通过GPT-4分析了120张乳房图像 (60张带有发现,60张没有发现).
该LLM仅基于图像数据生成报告.
性能指标包括精度,灵敏度和特异性,用于识别投影,微化和质量.

主要成果:

在53.3%的病例中,GPT-4发现了乳房影像预测.
对解释结果的敏感性和特异性分别为50.0%和37.5%.
该研究指出了大量的错误阳性,错误阴性和幻觉的情况.

结论:

GPT-4在乳房影像中展示了胚胎的解释能力,突出了目前的局限性.
潜在的风险,包括不准确性和幻觉,需要谨慎.
专门的培训,验证和监管对于临床乳房镜中的AI工具至关重要.

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

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

Typical Model Studies

Typical Model Studies

Fluid mechanics model studies often utilize scaled-down systems to predict fluid behavior in full-scale environments, such as river flows, dam spillways, and structures interacting with open surfaces. Maintaining Froude number similarity in river models is crucial, as it replicates surface flow features like wave patterns and velocities.