RNN-Based Alzheimer's Disease Prediction from Prodromal Stage using Diffusion Tensor Imaging

Alzheimer's Disease is an irreversible, progressive brain disorder that slowly destroys cognitive abilities. In recent years, the relationship between the prodromal Mild Cognitive Impairment (MCI) stage and the Alzheimer's Disease (AD) stage has been extensively researched in hopes of finding a path towards early diagnosis. Early detection at the MCI stage can help determine appropriate treatment plans as well as assist in clinical trial enrollment as 32% of individuals with MCI will develop AD within 5 years. Computer vision studies leveraging Magnetic Resonance Imaging (sMRI, fMRI), Diffusion Tensor Imaging (DTI), and Positron Emission Tomography (PET) have led to encouraging results in classifying the different stages of AD. Studies around DTI specifically have shown that structural differences in white matter are prevalent between these stages. Rather than classification between stages, we propose a recurrent neural network model (RNN) based on the DTI modality for identifying the subset (32%) of individuals with Early Mild Cognitive Impairment (EMCI) that will develop AD. Our results are state-of-the-art and demonstrate high accuracy in determining which individuals will develop AD within the next 5-7 years. Additionally, we propose our augmentation methods for DTI data as well as our classification accuracy across the traditional AD stage categories.