Nie Yuanbi, Cui Qiushi, Li Wenyuan, Lü Yang, Deng Tianqing
School of Electrical Engineering, Chongqing University, Shapingba, Chongqing, 400044, China.
Department of Geriatrics, The First Affiliated Hospital of Chongqing Medical University, Youyi Road, Chongqing, 401122, China.
BMC Med Imaging. 2024 Dec 18;24(1):338. doi: 10.1186/s12880-024-01520-0.
Alzheimer's Disease is a neurodegenerative condition leading to irreversible and progressive brain damage, with possible features such as structural atrophy. Effective precision diagnosis is crucial for slowing disease progression and reducing the incidence rate and morbidity. Traditional computer-aided diagnostic methods using structural MRI data often focus on capturing such features but face challenges, like overfitting with 3D image analysis and insufficient feature capture with 2D slices, potentially missing multi-planar information, and the complementary nature of features across different orientations.
The study introduces MHAGuideNet, a classification method incorporating a guidance network utilizing multi-head attention. The model utilizes a pre-trained 3D convolutional neural network to direct the feature extraction of multi-planar 2D slices, specifically targeting the detection of features like structural atrophy. Additionally, a hybrid 2D slice-level network combining 2D CNN and 2D Swin Transformer is employed to capture the interrelations between the atrophy in different brain structures associated with Alzheimer's Disease.
The proposed MHAGuideNet is tested using two datasets: the ADNI and OASIS datasets. The model achieves an accuracy of 97.58%, specificity of 99.89%, F1 score of 93.98%, and AUC of 99.31% on the ADNI test dataset, demonstrating superior performance in distinguishing between Alzheimer's Disease and cognitively normal subjects. Furthermore, testing on the independent OASIA test dataset yields an accuracy of 96.02%, demonstrating the model's robust performance across different datasets.
MHAGuideNet shows great promise as an effective tool for the computer-aided diagnosis of Alzheimer's Disease. Within the guidance of information from the 3D pre-trained CNN, the ability to leverage multi-planar information and capture subtle brain changes, including the interrelations between different structural atrophies, underscores its potential for clinical application.
阿尔茨海默病是一种神经退行性疾病，会导致不可逆转的渐进性脑损伤，可能具有结构萎缩等特征。有效的精准诊断对于减缓疾病进展、降低发病率至关重要。传统的利用结构磁共振成像（MRI）数据的计算机辅助诊断方法通常专注于捕捉此类特征，但面临挑战，如三维图像分析中的过拟合以及二维切片特征捕捉不足，可能会遗漏多平面信息以及不同方向特征的互补性。
该研究引入了MHAGuideNet，这是一种结合利用多头注意力的引导网络的分类方法。该模型利用预训练的三维卷积神经网络来指导多平面二维切片的特征提取，特别针对结构萎缩等特征的检测。此外，还采用了结合二维卷积神经网络（CNN）和二维Swin Transformer的混合二维切片级网络来捕捉与阿尔茨海默病相关的不同脑结构萎缩之间的相互关系。
所提出的MHAGuideNet使用两个数据集进行测试：阿尔茨海默病神经成像倡议（ADNI）数据集和开放获取系列影像研究（OASIS）数据集。该模型在ADNI测试数据集上的准确率达到97.58%，特异性为99.89%，F1分数为93.98%，曲线下面积（AUC）为99.31%，在区分阿尔茨海默病和认知正常受试者方面表现出卓越性能。此外，在独立的OASIA测试数据集上进行测试的准确率为96.02%，表明该模型在不同数据集上具有稳健性能。
MHAGuideNet作为阿尔茨海默病计算机辅助诊断的有效工具显示出巨大潜力。在来自三维预训练CNN的信息指导下，利用多平面信息和捕捉细微脑变化（包括不同结构萎缩之间的相互关系）的能力突出了其临床应用潜力。
