Department of Mechanical Engineering of Khalifa University, Abu Dhabi, PO Box 127788, UAE.
Department of Electrical Engineering of Khalifa University, Abu Dhabi, PO Box 127788, UAE.
Sci Rep. 2024 Nov 12;14(1):27756. doi: 10.1038/s41598-024-76313-0.
Early detection and accurate diagnosis of brain morphological abnormalities are essential for the effective management and treatment of Alzheimer's disease (AD) and mild cognitive impairment (MCI). Structural magnetic resonance imaging (MRI) is a powerful support tool to aid in disease diagnosis and prediction. In this research study, we present an innovative approach to predict Alzheimer's disease (AD) and mild cognitive impairment (MCI) using MRI data, which integrates regional interest (ROI)-based methodology and deep learning within a comprehensible framework. The proposed method involves dividing the brain into 138 predetermined sections based on anatomical information. Next, we apply three-dimensional vision transformers (3D-ViTs) to each ROI individually, harnessing the power of deep learning. To improve prediction accuracy, we employ a deep belief network (DBN) as an ensemble learning model. Evaluating our approach on the baseline structural MRI dataset obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort, and comparing it against five other competing models, we demonstrate its performance across four binary classification tasks and a three-class classification test (AD vs MCI vs CN (Cognitively Normal)). The proposed system outperforms existing models and provides interpretable insights into the brain regions that significantly contribute to solving each classification problem. Our findings align with the existing body of literature and hold promise for guiding future research directions in this domain.
早期发现和准确诊断大脑形态异常对于阿尔茨海默病（AD）和轻度认知障碍（MCI）的有效管理和治疗至关重要。结构磁共振成像（MRI）是辅助疾病诊断和预测的有力工具。在这项研究中，我们提出了一种使用 MRI 数据预测阿尔茨海默病（AD）和轻度认知障碍（MCI）的创新方法，该方法将基于感兴趣区域（ROI）的方法和深度学习集成在一个可理解的框架内。该方法涉及根据解剖信息将大脑分为 138 个预定区域。接下来，我们将三维视觉转换器（3D-ViTs）应用于每个 ROI，利用深度学习的力量。为了提高预测准确性，我们使用深度置信网络（DBN）作为集成学习模型。我们在从阿尔茨海默病神经影像倡议（ADNI）队列获得的基线结构 MRI 数据集上评估了我们的方法，并将其与其他五个竞争模型进行了比较，结果表明，我们的方法在四个二分类任务和一个三分类测试（AD 与 MCI 与 CN（认知正常））中表现出色。该系统优于现有模型，并提供了对大脑区域的可解释见解，这些区域对解决每个分类问题具有重要贡献。我们的研究结果与现有文献一致，并为该领域的未来研究方向提供了指导。
