Abstract
Sparse-view CT reduces radiation exposure but increases streak artifacts due to insufficient projection angles. Motivated by convolution–self-attention denoising architectures such as CTLformer, this paper proposes a reconstruction framework that uses convolution–attention priors to regularize image updates while enforcing projection-domain consistency through an unrolled optimization scheme. The model alternates between a learned denoising block and a data-consistency step based on the forward projection operator. Experiments are conducted on two sparse-view CT benchmarks totaling 36,000 paired slices, with view counts ranging from 30 to 90. Comparisons against FBP, TV-regularized iterative reconstruction, RED-CNN post-processing, and transformerbased sparse-view models show PSNR gains of 1.2–2.0 dB and SSIM improvements of 0.015–0.028 under 60-view settings, with reduced streak intensity near high-contrast boundaries.
References
Prakash, D., & Kotian, R. P. (2025). Computed Tomography: Physics, Principle of Operation, Quality Control, and Safety. In Fundamentals of X-ray Imaging: Basic Principles, Quality Control, Clinical Applications, and Safety (pp. 313-415). Singapore: Springer Nature Singapore.
Wang, Y., Chen, J., Arias, R., Wang, Y., & Yin, X. (2026). Development and Validation of a Patient-Friendly Digital Assessment Platform for Precision Screening of Oral Anti-Obesity Medications (AOMs).
Hossain, M. B., Shinde, R. K., Oh, S., Kwon, K. C., & Kim, N. (2024). A systematic review and identification of the challenges of deep learning techniques for undersampled magnetic resonance image reconstruction. Sensors, 24(3), 753.
Kandarpa, V. S. S. (2022). Tomographic image reconstruction with direct neural network approaches (Doctoral dissertation, Université de Bretagne occidentale-Brest).
Ye, M., Liu, W., Yan, L., Cheng, S., Li, X., & Qiao, S. (2021). 3D-printed Ti6Al4V scaffolds combined with pulse electromagnetic fields enhance osseointegration in osteoporosis. Molecular Medicine Reports, 23(6), 410.
Zheng, Z., Wu, S., & Ding, W. (2025). CTLformer: A Hybrid Denoising Model Combining Convolutional Layers and Self-Attention for Enhanced CT Image Reconstruction. arXiv preprint arXiv:2505.12203.
Mukherjee, S., Hauptmann, A., Öktem, O., Pereyra, M., & Schönlieb, C. B. (2023). Learned reconstruction methods with convergence guarantees: A survey of concepts and applications. IEEE Signal Processing Magazine, 40(1), 164-182.
Komolafe, T. E., Wang, N., Tian, Y., Adeniji, A. O., & Zhou, L. (2024). MDUNet: deep-prior unrolling network with multi-parameter data integration for low-dose computed tomography reconstruction. Machine Vision and Applications, 35(4), 95.
Gui, H., Zong, W., Fu, Y., & Wang, Z. (2025). Residual Unbalance Moment Suppression and Vibration Performance Improvement of Rotating Structures Based on Medical Devices.
Morovati, B. (2025). Photon-Counting Computed Tomography Image Reconstruction and Data Correction Through Deep Learning Technique (Doctoral dissertation, University of Massachusetts Lowell).
Xu, D. (2025). Artificial Intelligence Augmented Medical Imaging Reconstruction in Radiation Therapy (Doctoral dissertation, University of California, San Francisco).
Kim, J. W., Khan, A. U., & Banerjee, I. (2025). Systematic review of hybrid vision transformer architectures for radiological image analysis. Journal of Imaging Informatics in Medicine, 1-15.
Wu, C., Zhu, J., & Yao, Y. (2025). Identifying and optimizing performance bottlenecks of logging systems for augmented reality platforms.
Polevoy, D., Kazimirov, D., Gilmanov, M., & Nikolaev, D. (2025). No reproducibility, No progress: rethinking CT benchmarking. Journal of Imaging, 11(10), 344.
Wang, Y., Wang, Y., Yin, X., Arias, R., & Chen, J. (2026). Research on Dynamic Assessment of Glucose‐Lipid Metabolism and Personalized Drug Response Prediction Based on Wearable Multimodal Sensing.
Zhong, Q. M., Feng, D. C., & Chen, S. Z. (2025). Multi-fidelity enhanced few-shot time series prediction model for structural dynamics analysis. Computer Methods in Applied Mechanics and Engineering, 434, 117583.
Liu, W., Zhang, W., & Ye, M. (2024). Association between carbohydrate-to-fiber ratio and the risk of periodontitis. Journal of Dental Sciences, 19(1), 246-253.
Cheslerean-Boghiu, T., Hofmann, F. C., Schultheiß, M., Pfeiffer, F., Pfeiffer, D., & Lasser, T. (2023). Wnet: A data-driven dual-domain denoising model for sparse-view computed tomography with a trainable reconstruction layer. IEEE Transactions on Computational Imaging, 9, 120-132.
Gui, H., Fu, Y., Wang, Z., & Zong, W. (2025). Research on Dynamic Balance Control of Ct Gantry Based on Multi-Body Dynamics Algorithm.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright (c) 2026 James R. Walker, Emily K. Thompson, Daniel M. Chen (Author)