The time and cost of annotating ground-truth images and network training are major challenges to utilizing machine learning to automate the mining of volume electron microscopy data. In this work we present a less computationally intense pipeline to train a convolutional neural network aimed at rapid automated detection of intracellular structures in volume electron microscopy using a limited number of loosely annotated images. Find out more...
Visualizing SARS-COV-2 entry. Find out more...
Antibody broadly neutralizing SARS-COV-2 variants. Find out more...
Contact
Administrative Assistant: Catherine Swan
Email: Catherine.Swan [at] childrens.harvard.edu
Phone: 617.713.8889
