LAMA: Stable Dual-Domain Deep Reconstruction For Sparse-View CT
This work addresses the problem of enhancing CT image reconstruction for medical imaging applications, representing an incremental improvement by combining existing techniques in a novel way.
The paper tackled the inverse problem in sparse-view CT reconstruction by developing LAMA, a learned alternating minimization algorithm that synergizes data-driven and classical techniques, resulting in improved reconstruction accuracy, stability, and interpretability while outperforming state-of-the-art methods on benchmark datasets.
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.