Due to the hardware constraints of Computed Tomography (CT) imaging, acquiring high-resolution (HR) CT images in clinical settings poses a significant challenge. In recent years, convolutional neural networks have shown great potential in CT super-resolution (SR) problems. However, the reconstruction results of many deep learning-based SR methods have structural distortion and detail ambiguity. In this paper, a new SR network based on generative adversarial learning is proposed. The network consists of gradient branch and SR branch. Gradient branch is used to recover HR gradient maps. The network merges gradient image features of the gradient branch into the SR branch, offering gradient information guidance for super-resolution (SR) reconstruction. Further, the loss function of the network combines the image space loss function with the gradient loss and the gradient variance loss to further generate a more realistic detail texture. Compared to other comparison algorithms, the structural similarity index of the SR results obtained by the proposed method on simulation and experimental data has increased by 1.8% and 1.4%, respectively. The experimental results demonstrate that the proposed CT SR network exhibits superior performance in terms of structure preservation and detail restoration.
UmeharaKOtaJIshidaT. Application of super-resolution convolutional neural network for enhancing image resolution in chest CT. J Digital Imaging2018; 31: 441–450.
2.
LiYSixouBPeyrinF. A review of the deep learning methods for medical images super resolution problems. Irbm2021; 42: 120–133.
3.
JiangXXuYWeiP,et al.CT Image super resolution based on improved SRGAN. In: 2020 5th International Conference on Computer and Communication Systems (ICCCS), 2020, IEEE, pp. 363–367.
4.
YanZLiJLuY, et al.Super resolution in CT. Int J Imaging Syst Technol2015; 25: 92–101.
5.
ChiJSunZWangH, et al.CT Image super-resolution reconstruction based on global hybrid attention. Comput Biol Med2022; 150: 106112.
6.
JiangCZhangQFanR,et al.Super-resolution CT image reconstruction based on dictionary learning and sparse representation. SciRep2018; 8: 8799.
7.
HatvaniJHorváthAMichettiJ, et al.Deep learning-based super-resolution applied to dental computed tomography. IEEE Trans Radiat Plasma Med Sci2019; 3: 120–128.
8.
RenZHeCZhangQ. Fractional order total variation regularization for image super-resolution. Signal Process2013; 93: 2408–2421.
9.
TomaADenisLSixouB, et al.Total variation super-resolution for 3D trabecular bone micro-structure segmentation. In: 2014 22nd European Signal Processing Conference (EUSIPCO), 2014, IEEE, pp. 2220–2224.
10.
MejiaJMederosBOrtegaL, et al.Small animal PET image super-resolution using Tikhonov and modified total variation regularisation. The Imaging Sci J2017; 65: 162–170.
11.
LiuXChenLWangW,et al.Robust multi-frame super-resolution based on spatially weighted half-quadratic estimation and adaptive BTV regularization. IEEE Trans Image Process2018; 27: 4971–4986.
12.
VenkatakrishnanSVBoumanCAWohlbergB. Plug-and-play priors for model based reconstruction. In: 2013 IEEE global conference on signal and information processing, 2013, IEEE, pp. 945–948.
13.
CascaranoPPiccolominiELMorottiE,et al.Plug-and-Play gradient-based denoisers applied to CT image enhancement. Appl Math Comput2022; 422: 126967.
14.
LedigCTheisLHuszarF, et al.Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2017, pp. 4681–4690.
15.
GoodfellowIPouget-AbadieJMirzaM, et al.Generative adversarial networks. Commun ACM2020; 63: 139–144.
16.
KimJLeeJKLeeKM. Accurate image super-resolution using very deep convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 1646–1654.
17.
WangYTengQHeX, et al.CT-image of rock samples super resolution using 3D convolutional neural network. Comput Geosci2019; 133: 104314.
18.
YuHLiuDShiH, et al.Computed tomography super-resolution using convolutional neural networks. In: 2017 IEEE International Conference on Image Processing (ICIP), 2017, IEEE, pp. 3944–3948.
19.
ParkJHwangDKimKY, et al.Computed tomography super-resolution using deep convolutional neural network. Phys Med Biol2018; 63: 145011.
20.
WangXYuKWuS, et al.Esrgan: enhanced super-resolution generative adversarial networks. In: Proceedings of the European conference on computer vision (ECCV) workshops, 2018, pp. 0–0.
21.
YouCCongWVannierMW, et al.CT super-resolution GAN constrained by the identical, residual, and cycle learning ensemble (GAN-CIRCLE). IEEE Trans Med Imaging2020; 39: 188–203.
22.
ZhuJ-YParkTIsolaP,et al.Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, 2017, pp. 2223–2232.
23.
ZhangXFengCWangA, et al.CT super-resolution using multiple dense residual block based GAN. Signal Image Video Process2021; 15: 725–733.
24.
YangQYanPZhangY, et al.Low-dose CT image denoising using a generative adversarial network with Wasserstein distance and perceptual loss. IEEE Trans Med Imaging2018; 37: 1348–1357.
25.
YiXBabynP. Sharpness-aware low-dose CT denoising using conditional generative adversarial network. J Digital Imaging2018; 31: 655–669.
26.
MaCRaoYChengY, et al.Structure-preserving super resolution with gradient guidance. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 7769–7778.
27.
ZhaoMNingJHuJ,et al.Hyperspectral image super-resolution under the guidance of deep gradient information. Remote Sens2021; 13: 2382.
KongFLiMLiuS, et al.Residual local feature network for efficient super-resolution. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 766–776.
30.
LiuJZhangWTangY, et al.Residual feature aggregation network for image super-resolution. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 2359–2368.
31.
JohnsonJAlahiAFei-FeiL. Perceptual losses for real-time style transfer and super-resolution. In: Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11–14, 2016, Proceedings, Part II 14, 2016: Springer, pp. 694–711.
32.
SimonyanK. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
33.
SiddonRL. Fast calculation of the exact radiological path for a three-dimensional CT array. Med Phy1985; 12: 252–255.
34.
International Commission on Radiation Units and Measurements. Phantoms and computational models in therapy, diagnosis and protection. International Commission on Radiation Units and Measurements, 1992.
35.
PaszkeAGrossSChintalaS, et al.Automatic differentiation in pytorch. 2017.
36.
LiuJGanZZhuX. Directional bicubic interpolation—A new method of image super-resolution. In: in 3rd International Conference on Multimedia Technology (ICMT-13), 2013, Atlantis Press, pp. 463–470.
37.
YuanYLiuSZhangJ, et al.Unsupervised image super-resolution using cycle-in-cycle generative adversarial networks. In: in Proceedings of the IEEE conference on computer vision and pattern recognition workshops, 2018, pp. 701–710.
38.
SaraUAkterMUddinMS. Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study. J Comput Commun2019; 7: 8–18.
39.
ChannappayyaSSBovikACHeathRW. Rate bounds on SSIM index of quantized images. IEEE Trans Image Process2008; 17: 1624–1639.
