摘要
The unrolling method has been investigated for learning variational models in x-ray computed tomography. However, for incomplete data reconstruction, such as sparse-view and limited-angle problems, the unrolling method of gradient descent of the energy minimization problem cannot yield satisfactory results. In this paper, we present an effective CT reconstruction model, where the low-resolution image is introduced as a regularization for incomplete data problems. In what follows, we utilize the deep equilibrium approach to unfolding of the gradient descent algorithm, thereby constructing the backbone network architecture for solving the minimization model. We theoretically discuss the convergence of the proposed low-resolution prior equilibrium (LRPE) model and provide the necessary conditions to guarantee its convergence. Experimental results on both sparse-view and limited-angle reconstruction problems are provided, demonstrating that our end-to-end LRPE model outperforms other state-of-the-art methods in terms of noise reduction, contrast-to-noise ratio, and preservation of edge details.
学科与关键词
- Learned Full-Sampling Reconstruction From Incomplete DataCheng, Weilin; Wang, Yu; Li, Hongwei; Duan, Yuping*IEEE Transactions on Computational Imaging, 2020, 6: 945-957.被引 18
- A total variation prior unrolling approach for computed tomography reconstructionZhang, Pengcheng; Ren, Shuhui; Liu, Yi; Gui, Zhiguo*; Shangguan, Hong; Wang, Yanling; Shu, Huazhong; Chen, Yang*Medical Physics, 2023, 50(5): 2816-2834.被引 3
- Sparse-view and limited-angle CT reconstruction with untrained networks and deep image priorShu, Ziyu*; Entezari, AlirezaComputer Methods and Programs in Biomedicine, 2022, 226: 107167.被引 8
