Optimization of Analytical Reconstruction Algorithms for Arbitrary CBCT Trajectory Using Deep Learning
This study addresses the challenge of applying analytical methods for Cone Beam Computed Tomography (CBCT) reconstructions along arbitrary trajectories instead of iterative methods. Traditional analytical methods like Filtered Back Projection (FBP) often fail to adequately process CBCT images due t...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | deu |
| Published: |
NDT.net
2025-02-01
|
| Series: | e-Journal of Nondestructive Testing |
| Online Access: | https://www.ndt.net/search/docs.php3?id=30749 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This study addresses the challenge of applying analytical methods for Cone Beam Computed Tomography (CBCT) reconstructions along arbitrary trajectories instead of iterative methods. Traditional analytical methods like Filtered Back Projection (FBP) often fail to adequately process CBCT images due to the intricate and varied paths involved. Although iterative methods are a common solution, they require substantial computational time and resources. To address these challenges, this paper proposes two approaches, the first approach enhances the traditional FBP algorithm by using deep learning to train an optimized filter before reconstruction. The second approach improves upon the Backprojection then Filtering (BPF) algorithm by first reconstructing and then applying a deep learning-trained filter. Both methods significantly optimize the initial reconstruction results and enhance efficiency, offering promising improvements over existing iterative reconstruction techniques.
|
|---|---|
| ISSN: | 1435-4934 |