Machine learning denoising of high-resolution X-ray nano­tomography data

• Published in: Journal of synchrotron radiation Vol. 29; no. Pt 1; pp. 230 - 238
• Main Authors: Flenner, Silja, Bruns, Stefan, Longo, Elena, Parnell, Andrew J., Stockhausen, Kilian E., Müller, Martin, Greving, Imke
• Format: Journal Article
• Language: English
• Published: International Union of Crystallography 01.01.2022
• Subjects: Research Papers
• ISSN: 0909-0495; 1600-5775
• DOI: 10.1107/S1600577521011139

A high-performance denoising filter based on machine learning for high-resolution synchrotron nano­tomography data is analyzed and evaluated. High-resolution X-ray nano­tomography is a quantitative tool for investigating specimens from a wide range of research areas. However, the quality of the reconstructed tomogram is often obscured by noise and therefore not suitable for automatic segmentation. Filtering methods are often required for a detailed quantitative analysis. However, most filters induce blurring in the reconstructed tomograms. Here, machine learning (ML) techniques offer a powerful alternative to conventional filtering methods. In this article, we verify that a self-supervised denoising ML technique can be used in a very efficient way for eliminating noise from nano­tomography data. The technique presented is applied to high-resolution nano­tomography data and compared to conventional filters, such as a median filter and a nonlocal means filter, optimized for tomographic data sets. The ML approach proves to be a very powerful tool that outperforms conventional filters by eliminating noise without blurring relevant structural features, thus enabling efficient quantitative analysis in different scientific fields.