Smith, Therese Mary
MIT Lincoln Laboratory
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. 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.
Worcester Polytechnic Institute
Major Qualifying Project
All authors have granted to WPI a nonexclusive royalty-free license to distribute copies of the work, subject to other agreements. Copyright is held by the author or authors, with all rights reserved, unless otherwise noted.