Faculty Advisor

Smith, Therese Mary

Abstract

Beta-amyloid plaques and tau neurofibrillary tangles (NFTs) are hallmark pathologies in Alzheimers disease. The amount of tau (known as the tau burden) is an important metric used to determine stages of Alzheimers disease. Recent work by Signaevsky, et. al. [1]has shown that convolutional neural networks can be used to determine accumulation of tangles in immunohistochemically stained tissue. The goal of this project is to compare the performance of several networks for the segmentation, quantification and classification of tau tangles and -amyloid plaques. The networks to be compared include U-Net, FCNet, SegNet and Mask-RCNN. The goal of this open-ended research is to evaluate the effectiveness of deep convolutional networks on classification of noisily labeled data.

Publisher

Worcester Polytechnic Institute

Date Accepted

2019-11-04

Major

Computer Science

Project Type

Major Qualifying Project

Accessibility

Unrestricted

Advisor Department

Computer Science

Share

COinS