可解释的人工智能对MRI分析的实用性:将模型预测与老化大脑的神经图像特征相关联
Simon M Hofmann1,2,3, Ole Goltermann1,4,5, Nico Scherf2,6
1Department of Neurology, Max Planck Institute for Human Cognitive and Brain Sciences, Leipzig, Germany.
Imaging neuroscience (Cambridge, Mass.)
|August 13, 2025
概括
可解释性AI (XAI) 将深度学习的大脑年龄预测与特定的老化大脑特征联系起来. 心室体积和皮层厚度与XAI相关性图表有很强的相关性,揭示了生物学见解.
科学领域:
- 神经成像是一种神经成像.
- 人工智能的人工智能
- 大脑衰老研究研究
背景情况:
- 深度学习模型可以准确地从MRI中预测大脑年龄,但缺乏解释能力.
- 可解释性AI (XAI) 识别了相关的大脑区域,但不是它们的生物含义.
- 弥合XAI和可解释的神经生物学特征之间的差距对于理解大脑衰老至关重要.
研究的目的:
- 将XAI在脑年龄预测模型中的基于voxel的贡献与老化大脑的人类可解释的结构特征联系起来.
- 为了调查哪些特定的老化大脑标志物对深度学习年龄预测最相关.
主要方法:
- 利用两组3D卷积神经网络 (3D-CNN) 在T1加权和流体减弱的反转恢复MRI数据上训练了1855名参与者 (18-82岁).
- 提取了基于XAI的参与者级别相关性地图,以确定年龄预测的重要voxels.
- 与区域灰色物质体积/厚度,周脉体空间 (PVS) 和白物质微分异构相关的XAI相关性地图.
主要成果:
- 所有测试的神经成像大脑衰老标志物,除了PVS,与XAI相关性地图有显著的相关性.
- 心室体积显示出与XAI相关性最强的相关性 (r=0.69).
- 时-皮皮层厚度/体积,小脑灰质体积和前-皮白质道与XAI相关性有很强的相关性.
结论:
- 结合深度学习和XAI可以揭示大脑衰老中的生物相关,多特征的关系.
- 这些模型包含了各种衰老过程,小脑比预期的更有影响.
- XAI有效地将模型预测与特定的神经生物学特征联系起来,增强对大脑衰老机制的理解.
更多相关视频
14:27Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
15.8K
09:38Generalized Psychophysiological Interaction PPI Analysis of Memory Related Connectivity in Individuals at Genetic Risk for Alzheimer's Disease
Published on: November 14, 2017
15.1K
相关概念视频
Magnetic Resonance Imaging
6.9K
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...
6.9K
Brain Imaging
313
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...
313
