X-ray ionizing radiation from Computed Tomography (CT) scanning increases cancer risk for patients, thus making sparse view CT, which diminishes X-ray exposure by lowering the number of projections, highly significant in diagnostic imaging. However, reducing the number of projections inherently degrades image quality, negatively impacting clinical diagnosis. Consequently, attaining reconstructed images that meet diagnostic imaging criteria for sparse view CT is challenging. This paper presents a novel network (CSUF), specifically designed for ultra-sparse view lung CT image reconstruction. The CSUF network consists of three cohesive components including (1) a compressed sensing-based CT image reconstruction module (VdCS module), (2) a U-shaped end-to-end network, CT-RDNet, enhanced with a self-attention mechanism, acting as the generator in a Generative Adversarial Network (GAN) for CT image restoration and denoising, and (3) a feedback loop. The VdCS module enriches CT-RDNet with enhanced features, while CT-RDNet supplies the VdCS module with prior images infused with rich details and minimized artifacts, facilitated by the feedback loop. Engineering simulation experimental results demonstrate the robustness of the CSUF network and its potential to deliver lung CT images with diagnostic imaging quality even under ultra-sparse view conditions.
Bosch de Basea GomezM, et al.Risk of hematological malignancies from CT radiation exposure in children, adolescents and young adults. Nat Med2023; 29: 3111–3119.
2.
BernardACombyPOLemogneB, et al.Deep learning reconstruction versus iterative reconstruction for cardiac CT angiography in a stroke imaging protocol: reduced radiation dose and improved image quality. Quant Imaging Med Surg2021; 11: 392–401.
3.
TanHQiCCaoY, et al.Ultralow-dose [18F] FDG PET/CT imaging: demonstration of feasibility in dynamic and static images. Eur Radiol2023; 33: 5017–5027.
4.
Ruano-RavinaA, et al.Low-dose CT for lung cancer screening. Lancet Oncol2018; 19: e131–e132.
5.
WuLSunFYangJ, et al.View-driven compressed sensing method of CT image reconstruction. In: 3rd Int. Symp. Appl. Mater. Sci. Energy Mater. (SAMSE 2019), Shanghai, China, 2019.
DengZ, et al.RFormer: transformer-based generative adversarial network for real Fundus image restoration on a new clinical bench-mark. IEEE J. Biomed. Health Inform2022; 26: 4645–4655.
10.
MaYWeiBFengP, et al.Low-Dose CT image denoising using a generative adversarial network with a hybrid loss function for noise learning. IEEE Access2020; 8: 67519–67529.
11.
KulathilakeKASHAbdullahNABandaraAMR, et al.InNetGAN: inception network-based generative adversarial network for denoising low-dose computed tomography. J. Healthc. Eng2021; 2021: 1–20.
12.
YiXBabynP. Sharpness-aware low-dose CT denoising using conditional generative adversarial network. J. Digit. Imaging2018; 31: 655–669.
13.
HuSYuWChenZ, et al.Medical Image Reconstruction Using Generative Adversarial Network for Alzheimer Disease Assessment with Class-Imbalance Problem. In: Proc. 2020 IEEE 6th Int. Conf. Comput. Commun. (ICCC), Chengdu, China, 2020.
14.
KrizhevskyAHintonGE. ImageNet classification with deep convolutional neural networks. In: Proc. NIPS, 2012.
15.
RonnebergerOFischerPBroxT. U-Net: Convolutional networks for biomedical image segmentation. In: Proc. Int. Conf. Med. Image Comput. Comput. Assist. Intervent., 2015.
16.
SidkyEYKaoC-MPanX. Accurate image reconstruction from few-views and limited-angle data in divergent-beam CT. J X-Ray Sci Technol2006; 14: 119–139.
17.
XuQYuHMouX, et al.Low-dose X-ray CT reconstruction via dictionary learning. IEEE Trans Med Imag2012; 31: 1682–1697.
18.
SinghS, et al.Abdominal CT: comparison of adaptive statistical iterative and filtered back projection reconstruction techniques. Radiology2010; 257: 373–383.
19.
DonohoDL. Compressed sensing. IEEE Trans Inf Theory2006; 52: 1289–1306.
20.
ChenG-HTangJLengS. Prior image constrained compressed sensing (PICCS): a method to accurately reconstruct dynamic CT images from highly undersampled projection data sets. Med Phys2008; 35: 660–663.
21.
WangG. A perspective on deep imaging. IEEE Access2016; 4: 8914–8924.
22.
WangGYeJCMuellerK, et al.Image reconstruction is a new frontier of machine learning. IEEE Trans Med Imag2018; 37: 1289–1296.
23.
ZhangCLiYChenGH. Accurate and robust sparse-view angle CT image reconstruction using deep learning and prior image constrained compressed sensing (DL-PICCS). Med Phys2021; 48: 5765–5781.
24.
JinKHMcCannMTFrousteyE, et al.Deep convolutional neural network for inverse problems in imaging. IEEE Trans Image Process2017; 26: 4509–4522.
25.
ZhangZLiangXDongX, et al.A sparse-view CT reconstruction method based on combination of DenseNet and deconvolution. IEEE Trans Med Imag2018; 37: 1407–1417.
26.
SunCLiuYYangH. Degradation-Aware deep learning framework for sparse-view CT reconstruction. Tomography2021; 7: 932–949.
27.
LeeHLeesJKimH, et al.Deep-neural-network-based sinogram synthesis f or sparse-view CT image reconstruction. IEEE Trans Radiat Plasma Med Sci2019; 3: 109–119.
28.
OkamotoTOhnishiTHaneishiH. Artifact reduction for sparse-view ct using deep learning with band patch. IEEE Trans Radiat Plasma Med Sci2022; 6: 859–873.
29.
GuanB, et al.Generative modeling in sinogram domain for sparse-view CT reconstruction. IEEE Trans Radiat Plasma Med Sci2024; 8: 195–207.
30.
WuWHuDNiuC, et al.DRONE: dual-domain residual-based optimization network for sparse-view CT reconstruction. IEEE Trans Med Imag2021; 40: 3002–3014.
31.
LiR, et al.DDPTransformer: dual-domain with parallel transformer network for sparse view CT image reconstruction. IEEE Trans Comput Imaging2022; 8: 1101–1116.
32.
ZhangYChenHXiaW, et al.LEARN++: recurrent dual-domain reconstruction network for compressed sensing CT. IEEE Trans Radiat Plasma Med Sci2023; 7: 132–142.
33.
YangQ, 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.
34.
ChenH, et al.LEARN: learned experts’ assessment-based reconstruction network for sparse-data CT. IEEE Trans Med Imag2018; 37: 1333–1347.
35.
ZhangH., GoodfellowI., MetaxasD., et al. : Self-Attention Generative Adversarial Networks. In Proc. Int. Conf. Mach. Learn. (ICML), PMLR, 2019.
36.
VaswaniA, et al.Attention is all you need. In: Proc. Adv. Neural Inf. Process. Syst., 2017.
WangZBovikACSheikhHR, et al.Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process2004; 13: 600–612.
39.
ZhaoHGalloOFrosioI, et al.Loss functions for image restoration with neural networks. IEEE Trans Comput Imag2017; 3: 1–11.
40.
ArmatoSGIII,., et al. The lung image database consortium (LIDC) and image database resource initiative (IDRI): a completed reference database of lung nodules on CT scans. Med Phys2011; 38: 915–931.
XieL, et al.DeSRA: detect and delete the artifacts of GAN-based real-world super-resolution models. In: Proc. 40th Int. Conf. Mach. Learn. (ICML’23), 2023.
