Sparse-View X-Ray CT Reconstruction Using ℓ_1 Prior with Learned Transform
share
A major challenge in X-ray computed tomography (CT) is reducing radiation dose while maintaining high quality of reconstructed images. To reduce the radiation dose, one can reduce the number of projection views (sparse-view CT); however, it becomes difficult to achieve high quality image reconstruction as the number of projection views decreases. Researchers have applied the concept of learning sparse representations from (high-quality) CT image dataset to the sparse-view CT reconstruction. We propose a new statistical CT reconstruction model that combines penalized weighted-least squares (PWLS) and ℓ_1 regularization with learned sparsifying transform (PWLS-ST-ℓ_1), and an algorithm for PWLS-ST-ℓ_1. Numerical experiments for sparse-view 2D fan-beam CT and 3D axial cone-beam CT show that the ℓ_1 regularizer significantly improves the sharpness of edges of reconstructed images compared to the CT reconstruction methods using edge-preserving regularizer and ℓ_2 regularization with learned ST.
READ FULL TEXT
