Learning to Restore ssTEM Image from Deformation and Corruption

Wei Huang, Chang Chen, Zhiwei Xiong, Yueyi Zhang, Dong Liu, Feng Wu

TL;DR: We propose a novel modeling strategy and a tailored deep learning framework to restore SFF artifacts in ssTEM images.

Abstract: Serial section transmission electron microscopy (ssTEM) plays an important role in biological research. Due to the imperfect sample preparation, however, ssTEM images suffer from inevitable artifacts that pose huge challenges for the subsequent analysis and visualization. In this paper, we propose a novel strategy for modeling the main type of degradation, i.e., Support Film Folds (SFF), by characterizing this degradation process as a combination of content deformation and corruption. Relying on that, we then synthesize a sufficient amount of paired samples (degraded/groundtruth), which enables the training of a tailored deep restoration network. To the best of our knowledge, this is the first learning-based framework for ssTEM image restoration. Experiments on both synthetic and real test data demonstrate the superior performance of our proposed method over existing solutions, in terms of both image restoration quality and neuron segmentation accuracy.

Keywords: Degradation modeling, image restoration, deep learning