区域注意力增强视觉转换器用于使用sMRI数据准确地分类阿尔茨海默病
Alireza Jomeiri1, Ahmad Habibizad Navin2, Mahboubeh Shamsi3
1Department of Computer Engineering, Qom Branch, Islamic Azad University, Qom, Iran.
Computers in biology and medicine
|September 13, 2025
概括
一个新的AI模型,区域注意力增强视觉转换器 (RAE-ViT),使用脑部扫描精确检测阿尔茨海默病 (AD). 这种先进的深度学习方法显示了早期和更可靠的AD诊断的希望.
科学领域:
- 人工智能的人工智能
- 神经成像是一种神经成像.
- 医学诊断 医学诊断 医学诊断
背景情况:
- 阿尔茨海默病 (AD) 诊断严重依赖于通过结构性MRI (sMRI) 检测大脑缩.
- 像CNN这样的传统深度学习模型在捕捉复杂的空间依赖性方面面临挑战,这对于从sMRI中准确地分类AD至关重要.
- 早期和精确的诊断对于及时干预和改善阿尔茨海默病患者的治疗结果至关重要.
研究的目的:
- 引入一种新的深度学习框架,即区域注意力增强视觉转换器 (RAE-ViT),用于使用sMRI数据增强AD分类.
- 通过有效地模拟大脑中的局部和全球结构模式,提高AD诊断的准确性和可靠性.
- 评估RAE-ViT与现有深度学习模型的性能,并评估其临床适用性.
主要方法:
- 开发了RAE-ViT,结合了区域注意力机制,专注于关键的大脑区域 (例如海马,心室).
- 利用分层自我注意力和多尺度特征提取来捕获sMRI扫描中的复杂的空间关系.
- 在来自阿尔茨海默病神经影像计划 (ADNI) 的各种数据集上训练并验证了模型,包括阿尔茨海默病,轻度认知障碍 (MCI) 和正常对照 (NC) 组的扫描.
主要成果:
- 在1152次sMRI扫描中,RAE-ViT实现了最先进的性能,精度为94.2%,灵敏度为91.8%,特异性为95.7%,AUC为0.96.
- 该模型的性能优于标准的视觉变压器 (89.5%准确率) 和基于CNN的模型,如ResNet-50 (87.8%准确率).
- 可解释的注意力图显示出与临床生物标志物 (海马0.89的迪斯得分,心室0.85) 的强烈对齐,该模型显示出对扫描器变化和噪声的稳定性.
结论:
- RAE-ViT代表了使用sMRI在AI驱动的阿尔茨海默病诊断方面的重大进步.
- 该模型的高精度,可解释性和稳定性表明,在早期AD检测中具有很强的临床应用潜力.
- 预先的多模式集成 (sMRI + PET) 进一步提高了诊断准确性,突出了结合成像模式以改善AD评估的潜力.
相关概念视频
Magnetic Resonance Imaging
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...
Brain Imaging
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 Stimulation (TMS).
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 Stimulation (TMS).


