CEM500K, a large-scale heterogeneous unlabeled cellular electron microscopy image dataset for deep learning

Automated segmentation of cellular electron microscopy (EM) datasets remains a challenge. Supervised deep learning (DL) methods that rely on region-of-interest (ROI) annotations yield models that fail to generalize to unrelated datasets. Newer unsupervised DL algorithms require relevant pre-training...

Full description

Bibliographic Details

Published in:	eLife
Main Authors:	Ryan Conrad, Kedar Narayan
Format:	Article
Language:	English
Published:	eLife Sciences Publications Ltd 2021-04-01
Subjects:	electron microscopy deep learning segmentation vEM neural network image dataset
Online Access:	https://elifesciences.org/articles/65894