用于阿尔茨海默病诊断的3D多模式多尺度端到端分类器
M Khojaste-Sarakhsi1, Seyedhamidreza Shahabi Haghighi1, S M T Fatemi Ghomi1
1Department of Industrial Engineering, Amirkabir University of Technology, Tehran, Iran.
Medical engineering & physics
|August 20, 2025
概括
这项研究引入了一个新的AI分类器,它结合了脑部扫描 (MRI,PET) 和认知得分,以准确诊断阿尔茨海默病 (AD) 和其早期阶段. 这种先进的模型通过同时分析多种数据类型和尺度来提高诊断准确性.
科学领域:
- 神经成像
- 人工智能
- 医疗诊断
背景情况:
- 阿尔茨海默病 (AD) 诊断依赖于整合各种数据类型,包括结构 (MRI) 和功能 (PET) 脑成像,认知评估 (MMSE) 和人口信息 (年龄).
- 目前的诊断模型往往难以有效地融合多模式数据,并捕捉疾病阶段之间的微妙差异,特别是稳定和渐进的轻度认知障碍 (MCI) 的区别.
研究的目的:
- 开发和验证一个新的3D多模式,多尺度,端到端分类器,用于增强阿尔茨海默病 (AD) 诊断.
- 将受试者分为四个不同的类别的准确性:正常控制 (NC),稳定轻度认知障碍 (sMCI),渐进轻度认知障碍 (pMCI) 和AD.
主要方法:
- 使用ResNet启发的架构,可训练的多尺度卷积缩放,用于处理集成的神经成像和临床数据.
- 实施了量身定制的数据融合策略 (MA_PC),将MRI与年龄和PET与MMSE并行分支进行处理,以优化互补信息.
- 使用阿尔茨海默病神经成像计划 (ADNI) 数据集进行实验,并进行五倍交叉验证和独立测试.
主要成果:
- 与现有的融合策略和预训练的3D ResNets相比,拟的MA_PC分类器实现了更高的性能.
- 4类分类 (NC,sMCI,pMCI,AD) 显示出明显优于3类方法 (NC,MCI,AD),有效地识别出细微的进展阶段.
- 该模型成功地整合了结构和功能性脑病理信息以提高诊断准确性.
结论:
- 先进的数据融合和多尺度分析对于提高阿尔茨海默病诊断的准确性至关重要.
- 开发的多模式卷积神经网络 (CNN) 显示了在神经退行性疾病诊断中推进医学成像研究和临床应用的巨大潜力.
- 能够区分sMCI和pMCI突显了该模型在捕获细微疾病轨迹方面的能力.
相关概念视频
Alzheimer's Disease: Overview
666
Alzheimer's Disease (AD) is a continually advancing neurodegenerative disorder, distinguished by escalating memory loss, cognitive dysfunction, and dementia. The disease unfolds in three stages: preclinical, mild cognitive impairment (MCI), and dementia. Its onset is insidious, and the progression gradual, with the cause not well explained by other disorders.
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
The clinical diagnosis of AD hinges on the presence of memory and other cognitive impairments. Biomarkers, such as changes in Aβ...
666
Alzheimer's Disease: Treatment
260
Alzheimer's Disease (AD), a neurodegenerative disorder, is pathologically identified by amyloid plaques and neurofibrillary tangles composed of tau protein. AD pharmacotherapy aims to manage cognitive symptoms, delay disease progression, and treat behavioral symptoms. The treatment is primarily symptomatic and palliative, with no definitive disease-modifying therapy available. Cholinesterase inhibitors, including donepezil (Aricept), rivastigmine (Exelon), and galantamine (Razadyne), are...
260


