PhD Seminar: Early Detection of Alzheimer's Disease Using Deep Learning

Wednesday, April 17, 2019 11:30 am - 11:30 am EDT (GMT -04:00)

Candidate: Laura McCrackin

Title: Early Detection of Alzheimer's Disease Using Deep Learning

Date: April 17, 2019

Time: 11:30 AM

Place: EIT 3142

Supervisor(s): Crowley, Mark - Kulic, Dana

Abstract:

Using a combination of methods from image processing, signal processing and deep learning, we aim to develop a model to predict whether or not a patient will develop symptomatic Alzheimer's disease using Diffusion MRI (dMRI) imaging data. We first propose a 3D multichannel convolutional neural network (CNN) architecture to distinguish patients with Alzheimer's from normal controls, then propose an extension of our architecture to incorporate multiple scans from a patient’s history to improve classification accuracy and predict future prognosis. Finally, we discuss some of the inherent challenges in obtaining and utilizing this type of imaging data for deep learning applications, along with methods for performing data augmentation to add diversity and robustness to our unique and comparatively small dataset.