LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918115536797696 |
|---|---|
| author | Ding, Chi Zhang, Qingchao Wang, Ge Ye, Xiaojing Chen, Yunmei |
| author_facet | Ding, Chi Zhang, Qingchao Wang, Ge Ye, Xiaojing Chen, Yunmei |
| contents | Inverse problems arise in many applications, especially tomographic imaging. We develop a Learned Alternating Minimization Algorithm (LAMA) to solve such problems via two-block optimization by synergizing data-driven and classical techniques with proven convergence. LAMA is naturally induced by a variational model with learnable regularizers in both data and image domains, parameterized as composite functions of neural networks trained with domain-specific data. We allow these regularizers to be nonconvex and nonsmooth to extract features from data effectively. We minimize the overall objective function using Nesterov's smoothing technique and residual learning architecture. It is demonstrated that LAMA reduces network complexity, improves memory efficiency, and enhances reconstruction accuracy, stability, and interpretability. Extensive experiments show that LAMA significantly outperforms state-of-the-art methods on popular benchmark datasets for Computed Tomography. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_21111 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT Ding, Chi Zhang, Qingchao Wang, Ge Ye, Xiaojing Chen, Yunmei Computer Vision and Pattern Recognition Machine Learning Numerical Analysis Inverse problems arise in many applications, especially tomographic imaging. We develop a Learned Alternating Minimization Algorithm (LAMA) to solve such problems via two-block optimization by synergizing data-driven and classical techniques with proven convergence. LAMA is naturally induced by a variational model with learnable regularizers in both data and image domains, parameterized as composite functions of neural networks trained with domain-specific data. We allow these regularizers to be nonconvex and nonsmooth to extract features from data effectively. We minimize the overall objective function using Nesterov's smoothing technique and residual learning architecture. It is demonstrated that LAMA reduces network complexity, improves memory efficiency, and enhances reconstruction accuracy, stability, and interpretability. Extensive experiments show that LAMA significantly outperforms state-of-the-art methods on popular benchmark datasets for Computed Tomography. |
| title | LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT |
| topic | Computer Vision and Pattern Recognition Machine Learning Numerical Analysis |
| url | https://arxiv.org/abs/2410.21111 |