Machine Learning Pipeline for Denoising Low Signal-To-Noise Ratio and Out-of-Distribution Transmission Electron Microscopy Datasets

TL;DR

This paper introduces a fast, self-supervised machine learning pipeline for denoising low signal-to-noise ratio HRTEM images, enabling real-time analysis and robust performance across different imaging conditions.

Contribution

A novel self-supervised denoising pipeline combining a blind-spot CNN with pre- and post-processing steps, optimized for speed and out-of-distribution generalization.

Findings

Outperforms existing denoising methods in noise reduction and contrast enhancement.

Achieves inference speeds of milliseconds per image, suitable for in-situ experiments.

Demonstrates robust performance on datasets with varying imaging conditions.

Abstract

High-resolution transmission electron microscopy (HRTEM) is crucial for observing material's structural and morphological evolution at Angstrom scales, but the electron beam can alter these processes. Devices such as CMOS-based direct-electron detectors operating in electron-counting mode can be utilized to substantially reduce the electron dosage. However, the resulting images often lead to low signal-to-noise ratio, which requires frame integration that sacrifices temporal resolution. Several machine learning (ML) models have been recently developed to successfully denoise HRTEM images. Yet, these models are often computationally expensive and their inference speeds on GPUs are outpaced by the imaging speed of advanced detectors, precluding in situ analysis. Furthermore, the performance of these denoising models on datasets with imaging conditions that deviate from the training datasets have not been evaluated. To mitigate these gaps, we propose a new self-supervised ML denoising pipeline specifically designed for time-series HRTEM images. This pipeline integrates a blind-spot convolution neural network with pre-processing and post-processing steps including drift correction and low-pass filtering. Results demonstrate that our model outperforms various other ML and non-ML denoising methods in noise reduction and contrast enhancement, leading to improved visual clarity of atomic features. Additionally, the model is drastically faster than U-Net-based ML models and demonstrates excellent out-of-distribution generalization. The model's computational inference speed is in the order of milliseconds per image, rendering it suitable for application in in-situ HRTEM experiments.