Alzheimer's Disease (AD) causes a continuous decline in memory, thinking, and judgment. Traditional diagnoses are usually based on clinical experience, which is limited by some realistic factors. In this paper, we focus on exploiting deep learning techniques to diagnose AD based on eye-tracking behaviors. Visual attention, as typical eye-tracking behavior, is of great clinical value to detect cognitive abnormalities in AD patients. To better analyze the differences in visual attention between AD patients and normals, we first conduct a 3D comprehensive visual task on a non-invasive eye-tracking system to collect visual attention heatmaps. We then propose a multi-layered comparison convolution neural network (MC-CNN) to distinguish the visual attention differences between AD patients and normals. In MC-CNN, the multi-layered representations of heatmaps are obtained by hierarchical convolution to better encode eye-movement behaviors, which are further integrated into a distance vector to benefit the comprehensive visual task. Extensive experimental results on the collected dataset demonstrate that MC-CNN achieves consistent validity in classifying AD patients and normals with eye-tracking data.

翻译：阿尔茨海默病（AD）会导致记忆力、思维能力和判断力持续衰退。传统诊断通常依赖临床经验，但受限于诸多现实因素。本文聚焦于利用深度学习技术，基于眼球追踪行为进行AD诊断。视觉注意作为典型的眼球追踪行为，对检测AD患者的认知异常具有重要临床价值。为更好分析AD患者与正常人在视觉注意上的差异，我们首先在无创眼球追踪系统上开展三维综合视觉任务，采集视觉注意热力图。随后提出多层比较卷积神经网络（MC-CNN），用于区分AD患者与正常人的视觉注意差异。在MC-CNN中，通过层次化卷积获取热力图的多层表征，以更好地编码眼动行为，这些表征进一步整合为距离向量以赋能综合视觉任务。在收集的数据集上的大量实验结果表明，MC-CNN在利用眼球追踪数据分类AD患者与正常人方面具有一致的有效性。