2017/11/02 by Xuehang Zheng, Zheng, Xuehang, Il Yong Chun +7
Engineering · Medicine · #Advanced MRI Techniques and Applications #Advanced X-ray and CT Imaging #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Medical Imaging Techniques and Applications #Medical Physics (physics.med-ph)
paper · pdf · doi:10.48550/arxiv.1711.00905
openalex publication_date 2017/11/02 · openalex created_date 2022/08/28 · openalex updated_date 2026/07/28
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 ℓ1 prior with learned sparsifying transform (PWLS-ST-ℓ1), and a corresponding efficient algorithm based on Alternating Direction Method of Multipliers (ADMM). To moderate the difficulty of tuning ADMM parameters, we propose a new ADMM parameter selection scheme based on approximated condition numbers. We interpret the proposed model by analyzing the minimum mean square error of its (ℓ2-norm relaxed) image update estimator. Our results with the extended cardiac-torso (XCAT) phantom data and clinical chest data show that, for sparse-view 2D fan-beam CT and 3D axial cone-beam CT, PWLS-ST-ℓ1 improves the quality of reconstructed images compared to the CT reconstruction methods using edge-preserving regularizer and ℓ2 prior with learned ST. These results also show that, for sparse-view 2D fan-beam CT, PWLS-ST-ℓ1 achieves comparable or better image quality and requires much shorter runtime than PWLS-DL using a learned overcomplete dictionary. Our results with clinical chest data show that, methods using the unsupervised learned prior generalize better than a state-of-the-art deep "denoising" neural network that does not use a physical imaging model.