Predicting Alzheimer's Disease with Deep Learning

 


   Note: An Official Proposal has not been Submitted to NACC.


   Lead Investigator:    Shivani Hegde
   Institution      :    Boston University
   E-Mail           :    svhegde@bu.edu
   Proposal ID      :    1746



   Proposal Description:
   This project's aim is to be able to apply a deep Convolutional Neural Network to an established Alzheimer's Disease dataset and train the neural network to be able to better predict the probability of a patient showing early signs of Alzheimer's Disease. I also want to answer questions like: are subjects with mild cognitive impairment misclassified as having mild Alzheimer?s disease dementia by the model? Were they faster to progress to dementia over time? I want the deep neural network to be able to automatically learn to identify imaging biomarkers that are predictive of Alzheimer's disease, and leverage them to achieve accurate early detection of the disease.