Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine
Abstract A long-standing challenge in tomography is the ‘missing wedge’ problem, which arises when the acquisition of projection images within a certain angular range is restricted due to geometrical constraints. This incomplete dataset results in significant artifacts and poor resolution in the rec...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | npj Computational Materials |
| Online Access: | https://doi.org/10.1038/s41524-025-01724-0 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849342411609735168 |
|---|---|
| author | Chonghang Zhao Mingyuan Ge Xiaogang Yang Yong S. Chu Hanfei Yan |
| author_facet | Chonghang Zhao Mingyuan Ge Xiaogang Yang Yong S. Chu Hanfei Yan |
| author_sort | Chonghang Zhao |
| collection | DOAJ |
| description | Abstract A long-standing challenge in tomography is the ‘missing wedge’ problem, which arises when the acquisition of projection images within a certain angular range is restricted due to geometrical constraints. This incomplete dataset results in significant artifacts and poor resolution in the reconstructed image. To tackle this challenge, we propose an approach dubbed Perception Fused Iterative Tomography Reconstruction Engine, which integrates a convolutional neural network (CNN) with perceptional knowledge as a smart regularizer into an iterative solving engine. We employ the Alternating Direction Method of Multipliers to optimize the solution in both physics and image domains, thereby achieving a physically coherent and visually enhanced result. We demonstrate the effectiveness of the proposed approach using various experimental datasets obtained with different x-ray microscopy techniques. All show significantly improved reconstruction even with a missing wedge of over 100 degrees−a scenario where conventional methods fail. Notably, it also improves the reconstruction in case of sparse projections, despite the network not being specifically trained for that. This demonstrates the robustness and generality of our method of addressing commonly occurring challenges in 3D x-ray imaging applications for real-world problems. |
| format | Article |
| id | doaj-art-ea01b3ced9994a8f8f82039ff54e4722 |
| institution | Kabale University |
| issn | 2057-3960 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | npj Computational Materials |
| spelling | doaj-art-ea01b3ced9994a8f8f82039ff54e47222025-08-20T03:43:22ZengNature Portfolionpj Computational Materials2057-39602025-07-0111111210.1038/s41524-025-01724-0Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engineChonghang Zhao0Mingyuan Ge1Xiaogang Yang2Yong S. Chu3Hanfei Yan4National Synchrotron Light Source II, Brookhaven National LaboratoryNational Synchrotron Light Source II, Brookhaven National LaboratoryNational Synchrotron Light Source II, Brookhaven National LaboratoryNational Synchrotron Light Source II, Brookhaven National LaboratoryNational Synchrotron Light Source II, Brookhaven National LaboratoryAbstract A long-standing challenge in tomography is the ‘missing wedge’ problem, which arises when the acquisition of projection images within a certain angular range is restricted due to geometrical constraints. This incomplete dataset results in significant artifacts and poor resolution in the reconstructed image. To tackle this challenge, we propose an approach dubbed Perception Fused Iterative Tomography Reconstruction Engine, which integrates a convolutional neural network (CNN) with perceptional knowledge as a smart regularizer into an iterative solving engine. We employ the Alternating Direction Method of Multipliers to optimize the solution in both physics and image domains, thereby achieving a physically coherent and visually enhanced result. We demonstrate the effectiveness of the proposed approach using various experimental datasets obtained with different x-ray microscopy techniques. All show significantly improved reconstruction even with a missing wedge of over 100 degrees−a scenario where conventional methods fail. Notably, it also improves the reconstruction in case of sparse projections, despite the network not being specifically trained for that. This demonstrates the robustness and generality of our method of addressing commonly occurring challenges in 3D x-ray imaging applications for real-world problems.https://doi.org/10.1038/s41524-025-01724-0 |
| spellingShingle | Chonghang Zhao Mingyuan Ge Xiaogang Yang Yong S. Chu Hanfei Yan Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine npj Computational Materials |
| title | Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine |
| title_full | Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine |
| title_fullStr | Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine |
| title_full_unstemmed | Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine |
| title_short | Limited-angle x-ray nano-tomography with machine-learning enabled iterative reconstruction engine |
| title_sort | limited angle x ray nano tomography with machine learning enabled iterative reconstruction engine |
| url | https://doi.org/10.1038/s41524-025-01724-0 |
| work_keys_str_mv | AT chonghangzhao limitedanglexraynanotomographywithmachinelearningenablediterativereconstructionengine AT mingyuange limitedanglexraynanotomographywithmachinelearningenablediterativereconstructionengine AT xiaogangyang limitedanglexraynanotomographywithmachinelearningenablediterativereconstructionengine AT yongschu limitedanglexraynanotomographywithmachinelearningenablediterativereconstructionengine AT hanfeiyan limitedanglexraynanotomographywithmachinelearningenablediterativereconstructionengine |