Metal Artifact Correction in Industrial CT Images Based on a Dual-Domain Joint Deep Learning Framework

被引:1
作者
Jiang, Shibo [1 ,2 ]
Sun, Yuewen [1 ,2 ]
Xu, Shuo [1 ,2 ]
Zhang, Zehuan [1 ,2 ]
Wu, Zhifang [1 ,2 ]
机构
[1] Tsinghua Univ, Inst Nucl & New Energy Technol, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Beijing Key Lab Nucl Detect Technol, Beijing 100084, Peoples R China
来源
APPLIED SCIENCES-BASEL | 2024年 / 14卷 / 08期
关键词
industrial CT; metal artifact correction; dual-domain; UNet; ResNet; joint framework; REDUCTION;
D O I
10.3390/app14083261
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Industrial computed tomography (CT) images reconstructed directly from projection data using the filtered back projection (FBP) method exhibit strong metal artifacts due to factors such as beam hardening, scatter, statistical noise, and deficiencies in the reconstruction algorithms. Traditional correction approaches, confined to either the projection domain or the image domain, fail to fully utilize the rich information embedded in the data. To leverage information from both domains, we propose a joint deep learning framework that integrates UNet and ResNet architectures for the correction of metal artifacts in CT images. Initially, the UNet network is employed to correct the imperfect projection data (sinograms), the output of which serves as the input for the CT image reconstruction unit. Subsequently, the reconstructed CT images are fed into the ResNet, with both networks undergoing a joint training process to optimize image quality. We take the projection data obtained by analytical simulation as the data set. The resulting optimized industrial CT images show a significant reduction in metal artifacts, with the average Peak Signal-to-Noise Ratio (PSNR) reaching 36.13 and the average Structural Similarity Index (SSIM) achieving 0.953. By conducting simultaneous correction in both the projection and image domains, our method effectively harnesses the complementary information from both, exhibiting a marked improvement in correction results over the deep learning-based single-domain corrections. The generalization capability of our proposed method is further verified in ablation experiments and multi-material phantom CT artifact correction.
引用
收藏
页数:15
相关论文
共 50 条
[31]   Syn2Real: synthesis of CT image ring artifacts for deep learning-based correction [J].
Hein, Dennis ;
Holmin, Staffan ;
Prochazka, Vladimir ;
Yin, Zhye ;
Danielsson, Mats ;
Persson, Mats ;
Wang, Ge .
PHYSICS IN MEDICINE AND BIOLOGY, 2025, 70 (04)
[32]   Comparison of Conventional and Deep Learning Based Methods for Pulmonary Nodule Segmentation in CT Images [J].
Rocha, Joana ;
Cunha, Antonio ;
Mendonca, Ana Maria .
PROGRESS IN ARTIFICIAL INTELLIGENCE, EPIA 2019, PT I, 2019, 11804 :361-371
[33]   DU-GAN: Generative Adversarial Networks With Dual-Domain U-Net-Based Discriminators for Low-Dose CT Denoising [J].
Huang, Zhizhong ;
Zhang, Junping ;
Zhang, Yi ;
Shan, Hongming .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
[34]   Metal artifact reduction for practical dental computed tomography by improving interpolation-based reconstruction with deep learning [J].
Liang, Kaichao ;
Zhang, Li ;
Yang, Hongkai ;
Yang, Yirong ;
Chen, Zhiqiang ;
Xing, Yuxiang .
MEDICAL PHYSICS, 2019, 46 (12) :E823-E834
[35]   CAEB7-UNet: An Attention-Based Deep Learning Framework for Automated Segmentation of C-Spine Vertebrae in CT Images [J].
Pandey, Abhishek Kumar ;
Senapati, Kedarnath ;
Pateel, G. P. .
IEEE ACCESS, 2025, 13 :39051-39065
[36]   Deep learning model-based segmentation of medical diseases from MRI and CT images [J].
Murmu, Anita ;
Kumar, Piyush .
2021 IEEE REGION 10 CONFERENCE (TENCON 2021), 2021, :608-613
[37]   A semi-supervised learning method of latent features based on convolutional neural networks for CT metal artifact reduction [J].
Shi, Zaifeng ;
Wang, Ning ;
Kong, Fanning ;
Cao, Huaisheng ;
Cao, Qingjie .
MEDICAL PHYSICS, 2022, 49 (06) :3845-3859
[38]   Framework for COVID-19 Segmentation and Classification Based on Deep Learning of Computed Tomography Lung Images [J].
Salama W.M. ;
Aly M.H. .
Journal of Electronic Science and Technology, 2022, 20 (03) :246-256
[39]   Pulmonary Nodule Segmentation Framework Based on Fine-Tuned and Pretrained Deep Neural Network Using CT Images [J].
Bhattacharjee, Ananya ;
Murugan, R. ;
Goel, Tripti ;
Mirjalili, Seyedali .
IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES, 2023, 7 (04) :394-409
[40]   Is AI the way forward for reducing metal artifacts in CT? Development of a generic deep learning-based method and initial evaluation in patients with sacroiliac joint implants [J].
Selles, Mark ;
Slotman, Derk J. ;
van Osch, Jochen A. C. ;
Nijholt, Ingrid M. ;
Wellenberg, Ruud. H. H. ;
Maas, Mario ;
Boomsma, Martijn. F. .
EUROPEAN JOURNAL OF RADIOLOGY, 2023, 163