|
|
低剂量CT图像去噪方法研究
|
Abstract:
低剂量CT技术在显著降低患者辐射剂量的同时，不可避免地引入多样化的噪声与伪影，其强度与分布特性因成像条件而异，对图像质量及临床诊断准确性构成严峻挑战。传统图像去噪方法通常基于先验知识构建数学模型，虽能有效抑制部分噪声，但其优化过程依赖人工参数调谐，存在计算复杂度高、图像细节保留不足等固有缺陷。近年来，基于深度学习的去噪方法凭借其强大的非线性特征提取与端到端优化能力，在处理复杂噪声场景时展现出显著优势。本文系统性地介绍了低剂量CT图像去噪领域的研究进展：首先剖析了传统方法的理论框架及其局限性；随后重点探讨深度学习方法的技术原理、代表性模型架构及其在医学影像中的创新应用；最后，总结当前技术面临的核心挑战，并展望未来研究方向，旨在为低剂量CT成像技术的优化与临床转化提供理论依据与技术参考。
While significantly reducing patient radiation exposure, low-dose CT technology inevitably introduces diverse noise and artifacts, whose intensity and distribution characteristics vary with imaging conditions, posing a serious challenge to image quality and clinical diagnostic accuracy. Traditional image denoising methods, typically based on prior knowledge to construct mathematical models, can effectively suppress some noise. However, their optimization process relies on manual parameter tuning, exhibiting inherent limitations such as high computational complexity and insufficient preservation of image details. In recent years, deep learning-based denoising methods have demonstrated significant advantages in handling complex noise scenarios, leveraging their powerful nonlinear feature extraction and end-to-end optimization capabilities. This paper systematically introduces the research progress in the field of low-dose CT image denoising: first, it analyzes the theoretical frameworks and limitations of traditional methods; then, it focuses on the technical principles of deep learning methods, representative model architectures, and their innovative applications in medical imaging; finally, it summarizes the core challenges currently faced by the technology and outlines future research directions, aiming to provide theoretical foundations and technical references for the optimization and clinical translation of low-dose CT imaging technology.
| [1] | Brenner, D.J. and Hall, E.J. (2007) Computed Tomography—An Increasing Source of Radiation Exposure. New England Journal of Medicine, 357, 2277-2284. https://doi.org/10.1056/nejmra072149 |
| [2] | Hsieh, J. (1998) Adaptive Streak Artifact Reduction in Computed Tomography Resulting from Excessive X-Ray Photon Noise. Medical Physics, 25, 2139-2147. https://doi.org/10.1118/1.598410 |
| [3] | Ben Yedder, H., Cardoen, B. and Hamarneh, G. (2020) Deep Learning for Biomedical Image Reconstruction: A Survey. Artificial Intelligence Review, 54, 215-251. https://doi.org/10.1007/s10462-020-09861-2 |
| [4] | Sigal-Cinqualbre, A.B., Hennequin, R., Abada, H.T., Chen, X. and Paul, J. (2004) Low-Kilovoltage Multi-Detector Row Chest CT in Adults: Feasibility and Effect on Image Quality and Iodine Dose. Radiology, 231, 169-174. https://doi.org/10.1148/radiol.2311030191 |
| [5] | 江一峰, 叶剑定, 丁晓毅, 等. 胸部低剂量CT图像噪声和伪影分析[J]. 中华放射学杂志, 2010, 44(1): 37-40. |
| [6] | Pan, X., Sidky, E.Y. and Vannier, M. (2009) Why Do Commercial CT Scanners Still Employ Traditional, Filtered Back-Projection for Image Reconstruction? Inverse Problems, 25, Article 123009. https://doi.org/10.1088/0266-5611/25/12/123009 |
| [7] | Balda, M., Hornegger, J. and Heismann, B. (2012) Ray Contribution Masks for Structure Adaptive Sinogram Filtering. IEEE Transactions on Medical Imaging, 31, 1228-1239. https://doi.org/10.1109/tmi.2012.2187213 |
| [8] | Manduca, A., Yu, L., Trzasko, J.D., Khaylova, N., Kofler, J.M., McCollough, C.M., et al. (2009) Projection Space Denoising with Bilateral Filtering and CT Noise Modeling for Dose Reduction in CT. Medical Physics, 36, 4911-4919. https://doi.org/10.1118/1.3232004 |
| [9] | Wang, J., Li, T., Lu, H., et al. (2006) Penalized Weighted Least-Squares Approach to Sinogram Noise Reduction and Image Reconstruction for Low-Dose X-Ray Computed Tomography. IEEE Transactions on Medical Imaging, 25, 1272-1283. |
| [10] | Wang, J., Lu, H., Wen, J., et al. (2008) Multiscale Penalized Weighted Least-Squares Sinogram Restoration for Low-Dose X-Ray Computed Tomography. IEEE Transactions on Biomedical Engineering, 55, 1022-1031. |
| [11] | Rudin, L.I., Osher, S. and Fatemi, E. (1992) Nonlinear Total Variation Based Noise Removal Algorithms. Physica D: Nonlinear Phenomena, 60, 259-268. https://doi.org/10.1016/0167-2789(92)90242-f |
| [12] | Tang, X., Hsieh, J., Hagiwara, A., Nilsen, R.A., Thibault, J. and Drapkin, E. (2005) A Three-Dimensional Weighted Cone Beam Filtered Backprojection (CB-FBP) Algorithm for Image Reconstruction in Volumetric CT under a Circular Source Trajectory. Physics in Medicine and Biology, 50, 3889-3905. https://doi.org/10.1088/0031-9155/50/16/016 |
| [13] | Defrise, M., Noo, F. and Kudo, H. (2000) Quasi-Exact Filtered Backprojection Algorithm for Long-Object Problem in Helical Cone-Beam Tomography. IEEE Transactions on Medical Imaging, 19, 902-921. https://doi.org/10.1109/42.887838 |
| [14] | Feldkamp, L.A., Davis, L.C. and Kress, J.W. (1984) Practical Cone-Beam Algorithm. Journal of the Optical Society of America A, 1, 612-619. https://doi.org/10.1364/josaa.1.000612 |
| [15] | Rodet, T., Noo, F. and Defrise, M. (2004) The Cone-Beam Algorithm of Feldkamp, Davis, and Kress Preserves Oblique Line Integrals. Medical Physics, 31, 1972-1975. https://doi.org/10.1118/1.1759828 |
| [16] | Miao, H., Zhao, H., Gao, F. and Gong, S. (2009) Implementation of FDK Reconstruction Algorithm in Cone-Beam CT Based on the 3D Shepp-Logan Model. 2009 2nd International Conference on Biomedical Engineering and Informatics, Tianjin, 17-19 October 2009, 1-5. https://doi.org/10.1109/bmei.2009.5304987 |
| [17] | 韩泽芳, 上官宏, 张雄, 等. 基于深度学习的低剂量CT成像算法研究进展[J]. CT理论与应用研究, 2022, 31(1): 117-134. |
| [18] | Bender, R., Bellman, S.H. and Gordon, R. (1970) ART and the Ribosome: A Preliminary Report on the Three-Dimensional Structure of Individual Ribosomes Determined by an Algebraic Reconstruction Technique. Journal of Theoretical Biology, 29, 483-487. https://doi.org/10.1016/0022-5193(70)90110-4 |
| [19] | Donato, S., Brombal, L., Arfelli, F., Fanti, V., Longo, R., Oliva, P., et al. (2019) Optimization of a Customized Simultaneous Algebraic Reconstruction Technique Algorithm for Breast CT. 2019 IEEE Nuclear Science Symposium and Medical Imaging Conference (NSS/MIC), Manchester, 26 October-2 November 2019, 1-2. https://doi.org/10.1109/nss/mic42101.2019.9060011 |
| [20] | Sidky, E.Y. and Pan, X. (2008) Image Reconstruction in Circular Cone-Beam Computed Tomography by Constrained, Total-Variation Minimization. Physics in Medicine and Biology, 53, 4777-4807. https://doi.org/10.1088/0031-9155/53/17/021 |
| [21] | Zhang, Y., Zhang, W., Lei, Y. and Zhou, J. (2014) Few-View Image Reconstruction with Fractional-Order Total Variation. Journal of the Optical Society of America A, 31, 981-995. https://doi.org/10.1364/josaa.31.000981 |
| [22] | Zhang, Y., Wang, Y., Zhang, W., Lin, F., Pu, Y. and Zhou, J. (2016) Statistical Iterative Reconstruction Using Adaptive Fractional Order Regularization. Biomedical Optics Express, 7, 1015-1029. https://doi.org/10.1364/boe.7.001015 |
| [23] | Zhang, Y., Zhang, W., Chen, H., Yang, M., Li, T. and Zhou, J. (2013) Few-View Image Reconstruction Combining Total Variation and a High-Order Norm. International Journal of Imaging Systems and Technology, 23, 249-255. https://doi.org/10.1002/ima.22058 |
| [24] | Lu, Y., Zhao, J. and Wang, G. (2011) Few-View Image Reconstruction with Dual Dictionaries. Physics in Medicine and Biology, 57, 173-189. https://doi.org/10.1088/0031-9155/57/1/173 |
| [25] | Liu, Q., Zhang, M. and Zhao, J. (2014) Adaptive Dictionary Learning in Sparse Gradient Domain for CT Reconstruction. 2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI), Beijing, 29 April-2 May 2014, 169-172. https://doi.org/10.1109/isbi.2014.6867836 |
| [26] | Ma, J., Huang, J., Feng, Q., Zhang, H., Lu, H., Liang, Z., et al. (2011) Low-Dose Computed Tomography Image Restoration Using Previous Normal-Dose Scan. Medical Physics, 38, 5713-5731. https://doi.org/10.1118/1.3638125 |
| [27] | Chen, Y., Yang, Z., Hu, Y., Yang, G., Zhu, Y., Li, Y., et al. (2012) Thoracic Low-Dose CT Image Processing Using an Artifact Suppressed Large-Scale Nonlocal Means. Physics in Medicine and Biology, 57, 2667-2688. https://doi.org/10.1088/0031-9155/57/9/2667 |
| [28] | Zhong, J., Ning, R. and Conover, D. (2004) Image Denoising Based on Multiscale Singularity Detection for Cone Beam CT Breast Imaging. IEEE Transactions on Medical Imaging, 23, 696-703. https://doi.org/10.1109/tmi.2004.826944 |
| [29] | Fumene Feruglio, P., Vinegoni, C., Gros, J., Sbarbati, A. and Weissleder, R. (2010) Block Matching 3D Random Noise Filtering for Absorption Optical Projection Tomography. Physics in Medicine and Biology, 55, 5401-5415. https://doi.org/10.1088/0031-9155/55/18/009 |
| [30] | Chen, L.L., Gou, S.P., Yao, Y., Bai, J., Jiao, L. and Sheng, K. (2016) Denoising of Low Dose CT Image with Context-Based BM3D. 2016 IEEE Region 10 Conference (TENCON), Singapore, 22-25 November 2016, 682-685. https://doi.org/10.1109/tencon.2016.7848089 |
| [31] | Chen, Y., Yin, X., Shi, L., Shu, H., Luo, L., Coatrieux, J., et al. (2013) Improving Abdomen Tumor Low-Dose CT Images Using a Fast Dictionary Learning Based Processing. Physics in Medicine and Biology, 58, 5803-5820. https://doi.org/10.1088/0031-9155/58/16/5803 |
| [32] | Ronneberger, O., Fischer, P. and Brox, T. (2015) U-Net: Convolutional Networks for Biomedical Image Segmentation. In: Lecture Notes in Computer Science, Springer, 234-241. https://doi.org/10.1007/978-3-319-24574-4_28 |
| [33] | Mazandarani, F.N., Babyn, P. and Alirezaie, J. (2023) UNeXt: A Low-Dose CT Denoising UNet Model with the Modified Convnext Block. ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, 4-10 June 2023, 1-5. https://doi.org/10.1109/icassp49357.2023.10095645 |
| [34] | Nasrin, S., Alom, M.Z., Burada, R., Taha, T.M. and Asari, V.K. (2019) Medical Image Denoising with Recurrent Residual U-Net (R2U-Net) Base Auto-Encoder. 2019 IEEE National Aerospace and Electronics Conference (NAECON), Dayton, 15-19 July 2019, 345-350. https://doi.org/10.1109/naecon46414.2019.9057834 |
| [35] | Chen, H., Zhang, Y., Kalra, M.K., Lin, F., Chen, Y., Liao, P., et al. (2017) Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network. IEEE Transactions on Medical Imaging, 36, 2524-2535. https://doi.org/10.1109/tmi.2017.2715284 |
| [36] | Liang, T., Jin, Y., Li, Y. and Wang, T. (2020) EDCNN: Edge Enhancement-Based Densely Connected Network with Compound Loss for Low-Dose CT Denoising. 2020 15th IEEE International Conference on Signal Processing (ICSP), Beijing, 6-9 December 2020, 193-198. https://doi.org/10.1109/icsp48669.2020.9320928 |
| [37] | Won, D.K., An, S., Park, S.H. and Ye, D.H. (2020) Low-Dose CT Denoising Using Octave Convolution with High and Low Frequency Bands. In: Lecture Notes in Computer Science, Springer, 68-78. https://doi.org/10.1007/978-3-030-59354-4_7 |
| [38] | Gu, L., Deng, W. and Wang, G. (2024) UNAD: Universal Anatomy-Initialized Noise Distribution Learning Framework towards Low-Dose CT Denoising. ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, 14-19 April 2024, 1671-1675. https://doi.org/10.1109/icassp48485.2024.10446919 |
| [39] | Su, W., Qu, Y., Deng, C., Wang, Y., Zheng, F. and Chen, Z. (2020) Enhance Generative Adversarial Networks by Wavelet Transform to Denoise Low-Dose CT Images. 2020 IEEE International Conference on Image Processing (ICIP), Abu Dhabi, 25-28 October 2020, 350-354. https://doi.org/10.1109/icip40778.2020.9190766 |
| [40] | Tong, G., Hu, F. and Liu, H. (2024) DAGAN: A GAN Network for Image Denoising of Medical Images Using Deep Learning of Residual Attention Structures. International Journal of Pattern Recognition and Artificial Intelligence, 38, Article 2452003. https://doi.org/10.1142/s0218001424520037 |
| [41] | Yang, Q., Yan, P., Zhang, Y., Yu, H., Shi, Y., Mou, X., et al. (2018) Low-Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss. IEEE Transactions on Medical Imaging, 37, 1348-1357. https://doi.org/10.1109/tmi.2018.2827462 |
| [42] | Zhu, J., Park, T., Isola, P. and Efros, A.A. (2017) Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. 2017 IEEE International Conference on Computer Vision (ICCV), Venice, 22-29 October 2017, 2242-2251. https://doi.org/10.1109/iccv.2017.244 |
| [43] | Sowjanya, M., Laxmi, M., Sreelatha, B., et al. (2023) Unsupervised Medical Image Denoising Using Cyclegan: Improving Low-Dose CT Image Quality. 2023 International Conference on System, Computation, Automation and Networking (ICSCAN), Puducherry, 17-18 November 2023, 1-6. https://doi.org/10.1109/icscan58655.2023.10395736 |
| [44] | Wang, D., Wu, Z. and Yu, H. (2021) Ted-Net: Convolution-Free T2T Vision Transformer-Based Encoder-Decoder Dilation Network for Low-Dose CT Denoising. In: Lecture Notes in Computer Science, Springer, 416-425. https://doi.org/10.1007/978-3-030-87589-3_43 |
| [45] | Wang, D., Fan, F., Wu, Z., Liu, R., Wang, F. and Yu, H. (2023) CTformer: Convolution-Free Token2Token Dilated Vision Transformer for Low-Dose CT Denoising. Physics in Medicine & Biology, 68, Article 065012. https://doi.org/10.1088/1361-6560/acc000 |
| [46] | Zhang, B., Zhang, Y., Wang, B., He, X., Zhang, F. and Zhang, X. (2024) Denoising Swin Transformer and Perceptual Peak Signal-to-Noise Ratio for Low-Dose CT Image Denoising. Measurement, 227, Article 114303. https://doi.org/10.1016/j.measurement.2024.114303 |
