RELICT-NI:合成神经成像中的复制品检测 - - 一项关于非对比CT和飞行时间MRA的研究
Orhun Utku Aydin1, Alexander Koch2, Adam Hilbert2
1CLAIM - Charité Lab for AI in Medicine, Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität zu Berlin, Charitéplatz 1, 101117, Berlin, Germany. orhun-utku.aydin@charite.de.
Neuroinformatics
|November 10, 2025
概括
RELICT-NI是一种用于检测复制合成神经成像数据的新框架. 该工具有助于确保患者隐私,并支持医疗成像中深度学习模型的伦理发展.
科学领域:
- 医学成像和人工智能 医学成像和人工智能
- 神经成像数据合成和验证
- 深度学习模型的发展模式
背景情况:
- 合成神经成像数据可以增强深度学习模型,但由于潜在的数据记忆,患者隐私面临风险.
- 生成模型可能会无意中泄露敏感信息,限制合成数据的实用性和伦理应用.
研究的目的:
- 引入RELICT-NI (REpLIca deteCTion-NeuroImaging),这是一个用于识别合成神经成像数据集中的复制图像的新框架.
- 建立一种标准化的方法来验证合成神经成像数据,确保隐私并促进负责任的AI开发.
主要方法:
- RELICT-NI采用多方面的方法:图像层面分析,使用医疗基础模型进行特征层面分析,以及细分层面分析.
- 该框架在非对比头部CT (NCCT) 和飞行时间MR血管学 (TOF-MRA) 数据集上得到了验证.
- 专家视觉评分作为复制品识别的基础真理.
主要成果:
- RELICT-NI在检测复制品方面表现出高效率,图像级和特征级分析为NCCT数据集实现了完美平衡的准确性 (1.0).
- 对于TOF-MRA数据集,细分级别分析产生了最高的复制检测性能,平衡精度为0.79.
- 参考视觉评级确定了45/50 NCCT和5/50 TOF-MRA生成的图像作为复制品.
结论:
- 复制品检测是开发神经成像深度生成模型的一个重要但经常被忽视的步骤.
- RELICT-NI框架提供了一个标准化,用户友好的工具,以促进合成神经成像数据的伦理和严格验证.
- 这种方法支持神经成像数据的安全共享,并推动可靠的深度学习模型的开发.
相关概念视频
Magnetic Resonance Imaging
9.0K
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...
9.0K
Brain Imaging
651
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
651

![Studying Metabolic Brain Connectivity Using 2-Deoxy-2-[18F]Fluoro-D-Glucose Dynamic Positron Emission Tomography at the Single-subject Level](/_next/image?url=https%3A%2F%2Fcloudfront.jove.com%2FCDNSource%2Fteasers%2F67458.jpg&w=3840&q=50)
