Total generalized variation (TGV) based CT iterative reconstruction algorithm has the ability to effectively suppress the staircase effects caused by the piecewise constant assumption of total variation regularization. By unrolling the model-based iterative reconstruction to networks, the deep unrolling approach can further improve image quality within a finite number of iterations by data-driven training. However, most deep unrolling approaches focus on unrolling the data fidelity term into deep neural networks, which limit the performance of the deep unrolling approach.
Objective
To address this issue, we unrolled both the data fidelity term and the TGV term to construct a novel low-dose CT reconstruction network, called TGV based deep unrolling approach (TGV-DU).
Methods
The Chambolle-Pock algorithm was employed to solve the TGV based CT iterative reconstruction problem to obtain a single-loop CT iterative reconstruction algorithm, which is easy to be unrolled to neural networks. In the proposed algorithm, the parameterized mapping that updates primal variables and dual variables across successive iterations was implemented by convolutional neural networks and was dynamically learned from big data.
Results
To validate the effectiveness of our proposed algorithm, we perform the experiment on the “Low-Does CT Image and Projection Data” dataset. The results show that the proposed TGV-DU outperforms other state-of-the-art methods quantitatively and qualitatively.
Conclusions
Experiments show that our proposed algorithm can effectively alleviate the piecewise smoothness while preserve more structural details.
TsalafoutasIAHassan KharitaMAl-NaemiH, et al.Radiation dose monitoring in computed tomography: status, options and limitations. Phys Med2020; 79: 1-15.
2.
ChenHLiQZhouL, et al.Deep learning-based algorithms for low-dose CT imaging: a review. Eur J Radiol2024; 172: 1-13.
3.
YuLLiuXLengS, et al.Radiation dose reduction in computed tomography: techniques and future perspective. Imaging Med2009; 1: 65-84.
4.
WilleminkMJde JongPALeinerT, et al.Iterative reconstruction techniques for computed tomography part 1: technical principles. Eur Radiol2013; 23: 1623-1631.
5.
ChenXXiaWYangZ, et al.SOUL-Net: a sparse and low-rank unrolling network for spectral CT image reconstruction. IEEE Trans Neural Netw Learn Syst2024; 35: 18620-18634.
6.
GhaniMUKarlWC. Deep learning-based sinogram completion for low-dose CT. In: 2018 IEEE 13th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP). 2018; pp.1-5.
7.
YangLLiZGeR, et al.Low-Dose CT denoising via sinogram inner-structure transformer. IEEE Trans Med Imaging2023; 42: 910-921.
8.
LiYLiKZhangC, et al.Learning to reconstruct computed tomography images directly from sinogram data under A variety of data acquisition conditions. IEEE Trans Med Imaging2019; 38: 2469-2481.
9.
ChenHZhangYKalraMK, et al.Low-Dose CT with a residual encoder-decoder convolutional neural network. IEEE Trans Med Imaging2017; 36: 2524-2535.
10.
FanFShanHKalraMK, et al.Quadratic autoencoder (Q-AE) for low-dose CT denoising. IEEE Trans Med Imaging2020; 39: 2035-2050.
11.
YangQYanPZhangP, et al.Low-dose CT image denoising using a generative adversarial network with wasserstein distance and perceptual loss. IEEE Trans Med Imag2018; 37: 1348-1357.
12.
LiSLiuYYanR, et al.DD-DCSR: image denoising for low-dose CT via dual-dictionary deep convolutional sparse representation. IEEE Trans Comput Imaging2024; 10: 899-914.
13.
JiaoFGuiZLiK, et al.A dual-domain CNN-based network for CT reconstruction. IEEE Access2021; 9: 71091-71103.
14.
WuWHuDNiuC, et al.DRONE: dual-domain residual-based optimization NEtwork for sparse-view CT reconstruction. IEEE Trans Med Imaging2021; 40: 3002-3014.
15.
PanJZhangHWuW, et al.Multi-domain integrative swin transformer network for sparse-view tomographic reconstruction. Patterns2022; 3: 1-14.
16.
HuDLiuJLvT, et al.Hybrid-Domain neural network processing for sparse-view CT reconstruction. IEEE Trans Radiat Plasma Med Sci2021; 5: 88-98.
17.
ChenHZhangYChenY, et al.LEARN: learned Experts’ assessment-based reconstruction network for sparse-data CT. IEEE Trans Med Imaging2018; 37: 1333-1347.
18.
XiaWLuZHuangY, et al.MAGIC: manifold and graph integrative convolutional network for low-dose CT reconstruction. IEEE Trans Med Imaging2021; 40: 3459-3472.
19.
ÖKETM OALDERJ. Learned primal-dual reconstruction. IEEE Trans Med Imaging2018; 37: 1322-1332.
20.
ZhangJGhanemB. ISTA-net: Interpretable optimization-inspired deep network for image compressive sensing. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2018: pp.1828-1837.
21.
XiangJDongYYangY. FISTA-Net: learning a fast iterative shrinkage thresholding network for inverse problems in imaging. IEEE Trans Med Imaging2021; 40: 1329-1339.
22.
WangJZengLWangC, et al.ADMM-based deep reconstruction for limited-angle CT. Phys Med Biol2019; 64: 1-13.
23.
HeJYangYWangY, et al. Optimizing a parameterized plug-and-play ADMM for iterative low-dose CT reconstruction. IEEE Trans Med Imaging2019: 38: 371-382.
24.
ZhangPRenSLiuY, et al.A total variation prior unrolling approach for computed tomography reconstruction. Med Phys2023; 50: 2816-2834.
25.
NiuSGaoYBianZ, et al. Sparse-view x-ray CT reconstruction via total generalized variation regularization. Phys Med Biol2014; 59: 2997-3017.
26.
LvY. Parameter selection and solution algorithm for TGV-based image restoration model. SN Appl Sci2019; 1: 766.
27.
BrediesKValkonenT. Inverse problems with second-order Total Generalized Variation constraints. arXiv 2005.09725.
28.
KnollFBrediesKPockT, et al.Second order total generalized variation (TGV) for MRI. Magn Reson Med2011; 65: 480-491.
29.
SidkyEYJørgensenJHPanX. Convex optimization problem prototyping for image reconstruction in computed tomography with the Chambolle–Pock algorithm. Phys Med Biol2012; 57: 3065-3091.
30.
DongCLoyCCHeK, et al.Learning a deep convolutional network for image super-resolution. In: Computer Vision – ECCV 2014. Zurich, Switzerland: Springer, 2014, pp.184-199.
ZengGLGullbergGT. Unmatched projector/backprojector pairs in an iterative reconstruction algorithm. IEEE Trans Med Imag2000; 19: 548-555.
33.
HeKZhangXRenS, et al.Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2016: pp.770-778.
34.
MoenTRChenBHolmesDR, et al. Low-dose CT image and projection dataset. Med Phys2021; 48: 902-911.
35.
IonescuCVantzosOSminchisescuC. Matrix backpropagation for deep networks with structured layers. In: 2015 IEEE International Conference on Computer Vision (ICCV). 2015: pp.2965-2973.
36.
KingmaDPBaJ. Adam: A method for stochastic optimization. arXiv:1412.6980.
37.
McCannMTJinKHUnserM. Convolutional neural networks for inverse problems in imaging: a review. IEEE Signal Process Mag2017; 34: 85-95.
38.
LiJDuSWuC, et al.DRCR Net: dense residual channel re-calibration network with non-local purification for spectral super resolution. In: 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). 2022: pp. 1258-1267.
39.
WangZBovikACSheikhHR, et al.Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process2004; 13: 600-612.
40.
PanZYuHGaoZ, et al.Iterative residual optimization network for limited-angle tomographic reconstruction. IEEE Trans Image Process2024; 33: 910-925.
41.
KomolafeTWangNTianY, et al.MDUNet: deep-prior unrolling network with multi-parameter data integration for low-dose computed tomography reconstruction. Mach Vis Appl2024; 35: 95.
NiuSZhangMQiuY, et al.Evaluation of low-dose computed tomography reconstruction using spatial-radon domain total generalized variation regularization. Phys Med Biol2024; 8: 105005.
44.
GuoTLiuYZhangP, et al.MAIR-Net: a sparse-view CT reconstruction network based on a combination of mixed attention and iterative optimization learning. J Instrum2024; 19: 1-22.
