Enhancing synchrotron radiation micro-CT images using deep learning: an application of Noise2Inverse on bone imaging
Authors:
- Yoshihiro ObataYOYoshihiro Obata
- Dilworth Y. ParkinsonDPDilworth Y. Parkinson
- Daniël M. PeltDPDaniël M. Pelt
- Claire AcevedoCAClaire Acevedo
Open Access
- 1 April 2025
- journal article
- Published by International Union of Crystallography (IUCr) in Journal of Synchrotron Radiation
- Vol. 32 (3) , 690-699
Abstract
In bone-imaging research, in situ synchrotron radiation micro-computed tomography (SRµCT) mechanical tests are used to investigate the mechanical properties of bone in relation to its microstructure. Low-dose computed tomography (CT) is used to preserve bone's mechanical properties from radiation damage, though it increases noise. To reduce this noise, the self-supervised deep learning method Noise2Inverse was used on low-dose SRµCT images where segmentation using traditional thresholding techniques was not possible. Simulated-dose datasets were created by sampling projection data at full, one-half, one-third, one-fourth and one-sixth frequencies of an in situ SRµCT mechanical test. After convolutional neural networks were trained, Noise2Inverse performance on all dose simulations was assessed visually and by analyzing bone microstructural features. Visually, high image quality was recovered for each simulated dose. Lacunae volume, lacunae aspect ratio and mineralization distributions shifted slightly in full, one-half and one-third dose network results, but were distorted in one-fourth and one-sixth dose network results. Following this, new models were trained using a larger dataset to determine differences between full dose and one-third dose simulations. Significant changes were found for all parameters of bone microstructure, indicating that a separate validation scan may be necessary to apply this technique for microstructure quantification. Noise present during data acquisition from the testing setup was determined to be the primary source of concern for Noise2Inverse viability. While these limitations exist, incorporating dose calculations and optimal imaging parameters enables self-supervised deep learning methods such as Noise2Inverse to be integrated into existing experiments to decrease radiation dose.Keywords
Funding Information
- National Science Foundation (2045363)
- U.S. Department of Energy, Office of Science (DE-AC02-05CH11231)
This publication has 43 references indexed in Scilit:
- Femoral osteocyte lacunar density, volume and morphology in women across the lifespanJournal of Structural Biology, 2013
- Fiji: an open-source platform for biological-image analysisNature Methods, 2012
- Characterization of the effects of x-ray irradiation on the hierarchical structure and mechanical properties of human cortical boneBiomaterials, 2011
- Age-related changes in the plasticity and toughness of human cortical bone at multiple length scalesProceedings of the National Academy of Sciences, 2011
- Current Status of Developments and Applications of Micro-CTAnnual Review of Biomedical Engineering, 2011
- Quantitative micro-CTJournal of Microscopy, 2011
- On the effect of X-ray irradiation on the deformation and fracture behavior of human cortical boneBone, 2010
- Investigation of bone with synchrotron radiation imaging: from micro to nanoOsteoporosis International, 2009
- Simultaneous phase and amplitude extraction from a single defocused image of a homogeneous objectJournal of Microscopy, 2002
- A synchrotron radiation microtomography system for the analysis of trabecular bone samplesMedical Physics, 1999