Developing and Evaluating Deep Neural Network-based Denoising for Nanoparticle TEM Images with Ultra-low Signal-to-Noise

TL;DR

This paper presents a deep neural network that effectively denoises low-signal TEM images of nanoparticles, outperforming existing methods and providing insights into its denoising mechanisms and atomic structure predictions.

Contribution

The study introduces a novel deep learning-based denoising method tailored for low-signal TEM images, with detailed analysis of its performance and interpretability.

Findings

Outperforms state-of-the-art denoising methods on simulated and experimental data.

Uses multislice simulations for training data generation.

Provides a quantitative measure of atomic structure agreement in denoised images.

Abstract

A deep convolutional neural network has been developed to denoise atomic-resolution TEM image datasets of nanoparticles acquired using direct electron counting detectors, for applications where the image signal is severely limited by shot noise. The network was applied to a model system of CeO2-supported Pt nanoparticles. We leverage multislice image simulations to generate a large and flexible dataset for training and testing the network. The proposed network outperforms state-of-the-art denoising methods by a significant margin both on simulated and experimental test data. Factors contributing to the performance are identified, including most importantly (a) the geometry of the images used during training and (b) the size of the network's receptive field. Through a gradient-based analysis, we investigate the mechanisms learned by the network to denoise experimental images. This shows that the network exploits global and local information in the noisy measurements, for example, by adapting its filtering approach when it encounters atomic-level defects at the nanoparticle surface. Extensive analysis has been done to characterize the network's ability to correctly predict the exact atomic structure at the nanoparticle surface. Finally, we develop an approach based on the log-likelihood ratio test that provides a quantitative measure of the agreement between the noisy observation and the atomic-level structure in the network-denoised image.