A Fourier-based global denoising model for the smart removal of artifacts in microscopy images
TL;DR
A global denoising model (GDM) to smartly remove artifacts from microscopy images while preserving weaker but physically important features is proposed and the tuning effect between two imaging input channels on the trade-off performance between artifact removal and feature preservation is showcased.
Abstract
Microscopy techniques, such as scanning tunneling microscopy (STM), atomic force microscopy (AFM), and scanning electron microscopy (SEM), are essential tools in material imaging at micro- and nanoscale resolutions to extract physical knowledge and material structure–property relationships. However, tuning microscopy controls (e.g. scanning speed, current setpoint, tip bias, etc) to obtain high-quality images is a nontrivial and time-consuming effort. In contrast, with substandard images, the key features are not accurately discovered due to noise and artifacts, leading to erroneous analysis. Existing denoising models mostly build on generalizing weak signals as noises, whereas the strong signals are enhanced as key features, which is not always the case in microscopy images; hence, a significant amount of hidden physical information can be completely erased. To address these limitations, we propose a global denoising model (GDM) to smartly remove artifacts from microscopy images while preserving weaker but physically important features. The proposed model is developed based on 1) first designing a two-imaging input channel of nonpair and goal-specific preprocessed images with user-defined trade-off information between the two channels and 2) then integrating a loss function of pixel- and fast Fourier-transformed (FFT) based on training the U-Net model. We compare the proposed GDM with a non-FFT denoising model over STM-generated images of copper (Cu) and silicon (Si) materials and AFM-generated Pantoea sp. YR343 bio-film images and SEM-generated plastic degradation images. Next, we showcase the tuning effect between two imaging input channels on the trade-off performance between artifact removal and feature preservation. On STM, AFM, and SEM datasets, the proposed GDM improves the FFT-based peak-to-noise ratio by up to 4.5 dB on average relative to noisy inputs on simulated datasets and by up to 3.5 dB on experimental datasets. We believe that the proposed workflow can be extended to improve other microscopy image quality and will benefit the experimentalists with the proposed design flexibility to smartly tune according to domain experts’ preferences.