Physics-Guided Deep Learning For High Resolution X-ray Imaging
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918478167932928 |
|---|---|
| author | Lee, Shao Xian Mishra, Aashwin Ananda Arnott, Ariel Berboucha, Meriame Boiadjieva, Nina Chatterjee, Gourab Cunningham, Eric Czapla, Nick Dyer, Gilliss Ehni, Jonathan Ettelbrick, Robert Grassi, Anna Grech, Mickael Hart, Philip Khaghani, Dimitri Lee, Hae Ja McGehee, Peregrine Nagler, Bob Neumayer, Paul Riconda, Caterina Welch, Marc Zabala, Andrea Galtier, Eric Nguyen, Quynh L. |
| author_facet | Lee, Shao Xian Mishra, Aashwin Ananda Arnott, Ariel Berboucha, Meriame Boiadjieva, Nina Chatterjee, Gourab Cunningham, Eric Czapla, Nick Dyer, Gilliss Ehni, Jonathan Ettelbrick, Robert Grassi, Anna Grech, Mickael Hart, Philip Khaghani, Dimitri Lee, Hae Ja McGehee, Peregrine Nagler, Bob Neumayer, Paul Riconda, Caterina Welch, Marc Zabala, Andrea Galtier, Eric Nguyen, Quynh L. |
| contents | Imperfections in X-ray imaging systems can limit their performance, especially in High Energy Density (HED) or Inertial Fusion Energy (IFE)-relevant experiments that are typically single shot, by introducing structured, non-stationary features that overlap with the signal of interest. When the X-ray transmission is reconstructed by typical flat-field normalization, even small shot-to-shot drift of structured features imprints residual patterns onto transmission maps, degrading signal visibility and biasing measurements such as electron density, velocity and feature sizes. We investigate this limitation by modeling the artifacts as a separable feature layer and training a U-Net architecture to estimate and infer them directly from the experimental data. We compare our method against Fourier filtering and more advanced procedures like Dynamic Flat-Field Normalization (DFFN) to evaluate artifact suppression capability and signal preservation in the reconstructed transmission maps. In multiple synthetic injection tests, our Physics-Guided Deep Learning approach is able to obtain an improvement in mean Structural Similarity Index (SSIM) from 0.345 to 0.906 and from 0.0679 to 0.945, while better preserving filament profiles and reducing degradation of the filament signal during artifact suppression. Additionally, we utilize deep ensembles to obtain predictive epistemic uncertainty estimates for the U-Net based reconstruction, to ensure Out Of Distribution (OOD) robustness for this procedure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_01543 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Physics-Guided Deep Learning For High Resolution X-ray Imaging Lee, Shao Xian Mishra, Aashwin Ananda Arnott, Ariel Berboucha, Meriame Boiadjieva, Nina Chatterjee, Gourab Cunningham, Eric Czapla, Nick Dyer, Gilliss Ehni, Jonathan Ettelbrick, Robert Grassi, Anna Grech, Mickael Hart, Philip Khaghani, Dimitri Lee, Hae Ja McGehee, Peregrine Nagler, Bob Neumayer, Paul Riconda, Caterina Welch, Marc Zabala, Andrea Galtier, Eric Nguyen, Quynh L. Signal Processing Computational Physics Imperfections in X-ray imaging systems can limit their performance, especially in High Energy Density (HED) or Inertial Fusion Energy (IFE)-relevant experiments that are typically single shot, by introducing structured, non-stationary features that overlap with the signal of interest. When the X-ray transmission is reconstructed by typical flat-field normalization, even small shot-to-shot drift of structured features imprints residual patterns onto transmission maps, degrading signal visibility and biasing measurements such as electron density, velocity and feature sizes. We investigate this limitation by modeling the artifacts as a separable feature layer and training a U-Net architecture to estimate and infer them directly from the experimental data. We compare our method against Fourier filtering and more advanced procedures like Dynamic Flat-Field Normalization (DFFN) to evaluate artifact suppression capability and signal preservation in the reconstructed transmission maps. In multiple synthetic injection tests, our Physics-Guided Deep Learning approach is able to obtain an improvement in mean Structural Similarity Index (SSIM) from 0.345 to 0.906 and from 0.0679 to 0.945, while better preserving filament profiles and reducing degradation of the filament signal during artifact suppression. Additionally, we utilize deep ensembles to obtain predictive epistemic uncertainty estimates for the U-Net based reconstruction, to ensure Out Of Distribution (OOD) robustness for this procedure. |
| title | Physics-Guided Deep Learning For High Resolution X-ray Imaging |
| topic | Signal Processing Computational Physics |
| url | https://arxiv.org/abs/2605.01543 |