Advancing Limited-Angle CT Reconstruction Through Diffusion-Based Sinogram Completion
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911284132315136 |
|---|---|
| author | Guo, Jiaqi Lopez-Tapia, Santiago Katsaggelos, Aggelos K. |
| author_facet | Guo, Jiaqi Lopez-Tapia, Santiago Katsaggelos, Aggelos K. |
| contents | Limited Angle Computed Tomography (LACT) often faces significant challenges due to missing angular information. Unlike previous methods that operate in the image domain, we propose a new method that focuses on sinogram inpainting. We leverage MR-SDEs, a variant of diffusion models that characterize the diffusion process with mean-reverting stochastic differential equations, to fill in missing angular data at the projection level. Furthermore, by combining distillation with constraining the output of the model using the pseudo-inverse of the inpainting matrix, the diffusion process is accelerated and done in a step, enabling efficient and accurate sinogram completion. A subsequent post-processing module back-projects the inpainted sinogram into the image domain and further refines the reconstruction, effectively suppressing artifacts while preserving critical structural details. Quantitative experimental results demonstrate that the proposed method achieves state-of-the-art performance in both perceptual and fidelity quality, offering a promising solution for LACT reconstruction in scientific and clinical applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_19385 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Advancing Limited-Angle CT Reconstruction Through Diffusion-Based Sinogram Completion Guo, Jiaqi Lopez-Tapia, Santiago Katsaggelos, Aggelos K. Computer Vision and Pattern Recognition Artificial Intelligence Limited Angle Computed Tomography (LACT) often faces significant challenges due to missing angular information. Unlike previous methods that operate in the image domain, we propose a new method that focuses on sinogram inpainting. We leverage MR-SDEs, a variant of diffusion models that characterize the diffusion process with mean-reverting stochastic differential equations, to fill in missing angular data at the projection level. Furthermore, by combining distillation with constraining the output of the model using the pseudo-inverse of the inpainting matrix, the diffusion process is accelerated and done in a step, enabling efficient and accurate sinogram completion. A subsequent post-processing module back-projects the inpainted sinogram into the image domain and further refines the reconstruction, effectively suppressing artifacts while preserving critical structural details. Quantitative experimental results demonstrate that the proposed method achieves state-of-the-art performance in both perceptual and fidelity quality, offering a promising solution for LACT reconstruction in scientific and clinical applications. |
| title | Advancing Limited-Angle CT Reconstruction Through Diffusion-Based Sinogram Completion |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2505.19385 |