Aghdam Maryam Akhavan, Bozdag Serdar, Saeed Fahad
Knight Foundation School of Computing and Information Sciences, Florida International University, Miami, FL, United States.
Department of Computer Science and Engineering, University of North Texas, Denton, TX, United States.
Proc IEEE Int Symp Biomed Imaging. 2024 May;2024. doi: 10.1109/isbi56570.2024.10635541. Epub 2024 Aug 22.
Alzheimer's disease (AD) is a neurodegenerative disorder, and timely diagnosis is crucial for early interventions. AD is known to have disruptive local and global brain neural connections that may be instrumental in understanding and extracting specific biomarkers. Existing machine-learning approaches are mostly based on convolutional neural network (CNN) and standard vision transformer (ViT) models, which may not sufficiently capture the multidimensional local and global patterns indicative of AD. Therefore, in this paper, we propose a novel approach called to classify AD and cognitively normal (CN) cases using pretrained pyramid vision transformer (PVT) and white matter (WM) of T1-weighted structural MRI (sMRI) data. Our approach combines the advantages of CNN and standard ViT to extract both local and global features indicative of AD from the WM coronal middle slices. We performed experiments on subjects with T1-weighed MPRAGE sMRI scans from the ADNI dataset. Our results demonstrate that the PVTAD achieves an average accuracy of 97.7% and an F1-score of 97.6%, outperforming the single and parallel CNN and standard ViT based on sMRI data for AD vs. CN classification. Our code is available at https://github.com/pcdslab/PVTAD.
阿尔茨海默病（AD）是一种神经退行性疾病，及时诊断对于早期干预至关重要。已知AD会破坏局部和整体的脑神经网络连接，这可能有助于理解和提取特定的生物标志物。现有的机器学习方法大多基于卷积神经网络（CNN）和标准视觉Transformer（ViT）模型，这些模型可能无法充分捕捉表明AD的多维局部和整体模式。因此，在本文中，我们提出了一种名为PVTAD的新方法，使用预训练的金字塔视觉Transformer（PVT）和T1加权结构磁共振成像（sMRI）数据的白质（WM）对AD和认知正常（CN）病例进行分类。我们的方法结合了CNN和标准ViT的优点，从WM冠状中间切片中提取表明AD的局部和整体特征。我们对来自阿尔茨海默病神经成像倡议（ADNI）数据集的T1加权MPRAGE sMRI扫描的受试者进行了实验。我们的结果表明，PVTAD在AD与CN分类中，基于sMRI数据的平均准确率达到97.7%，F1分数达到97.6%，优于基于sMRI数据的单个和并行CNN以及标准ViT。我们的代码可在https://github.com/pcdslab/PVTAD获取。
