Improving Electron Micrograph Signal-to-Noise with an Atrous Convolutional Encoder-Decoder

07/30/2018

∙

by   Jeffrey M. Ede, et al.

∙

2

∙

share

We present an atrous convolutional encoder-decoder trained to denoise 512×512 crops from electron micrographs. It consists of a modified Xception backbone, atrous convoltional spatial pyramid pooling module and a multi-stage decoder. Our neural network was trained end-to-end to remove Poisson noise applied to low-dose (≪ 300 counts ppx) micrographs created from a new dataset of 17267 2048×2048 high-dose (> 2500 counts ppx) micrographs and then fine-tuned for ordinary doses (200-2500 counts ppx). Its performance is benchmarked against bilateral, non-local means, total variation, wavelet, Wiener and other restoration methods with their default parameters. Our network outperforms their best mean squared error and structural similarity index performances by 24.6 ordinary doses. In both cases, our network's mean squared error has the lowest variance. Source code and links to our new high-quality dataset and trained network have been made publicly available at https://github.com/Jeffrey-Ede/Electron-Micrograph-Denoiser