Interpretable Deep Temporal Structure Learning Model for Early Detection of Alzheimer's Disease

In Alzheimers research, Mild Cognitive Impairment (MCI) is an important intermediate stage between normal aging and Alzheimers disease. How to distinguish MCI samples that finally convert to AD from those do not is an essential problem in the prevention and diagnosis of Alzheimers. Traditional methods use various classification models to distinguish MCI converters from non-converters, while the performance is usually limited by the small number of available data. Moreover, previous methods only use the data at baseline time for training but ignore the longitudinal information at other time points along the disease progression. To tackle with these problems, we propose a novel deep learning framework that uncovers the temporal correlation structure of the longitudinal neuroimaing data in the disease progression. In the meantime, we formulate our new deep learning model in an interpretable style such that it provides insights on the important features Alzheimers research. We conduct extensive experiments on the ADNI cohort and outperform the related methods with significant margin.