Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging
Limited-angle computed tomography (CT) image reconstruction is a challenging problem in the field of CT imaging. In some special applications, limited by the geometric space and mechanical structure of the imaging system, projections can only be collected with a scanning range of less than 90...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-09-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/18/3941 |
_version_ | 1798038814668619776 |
---|---|
author | Ziheng Li Ailong Cai Linyuan Wang Wenkun Zhang Chao Tang Lei Li Ningning Liang Bin Yan |
author_facet | Ziheng Li Ailong Cai Linyuan Wang Wenkun Zhang Chao Tang Lei Li Ningning Liang Bin Yan |
author_sort | Ziheng Li |
collection | DOAJ |
description | Limited-angle computed tomography (CT) image reconstruction is a challenging problem in the field of CT imaging. In some special applications, limited by the geometric space and mechanical structure of the imaging system, projections can only be collected with a scanning range of less than 90°. We call this kind of serious limited-angle problem the ultra-limited-angle problem, which is difficult to effectively alleviate by traditional iterative reconstruction algorithms. With the development of deep learning, the generative adversarial network (GAN) performs well in image inpainting tasks and can add effective image information to restore missing parts of an image. In this study, given the characteristic of GAN to generate missing information, the sinogram-inpainting-GAN (SI-GAN) is proposed to restore missing sinogram data to suppress the singularity of the truncated sinogram for ultra-limited-angle reconstruction. We propose the U-Net generator and patch-design discriminator in SI-GAN to make the network suitable for standard medical CT images. Furthermore, we propose a joint projection domain and image domain loss function, in which the weighted image domain loss can be added by the back-projection operation. Then, by inputting a paired limited-angle/180° sinogram into the network for training, we can obtain the trained model, which has extracted the continuity feature of sinogram data. Finally, the classic CT reconstruction method is used to reconstruct the images after obtaining the estimated sinograms. The simulation studies and actual data experiments indicate that the proposed method performed well to reduce the serious artifacts caused by ultra-limited-angle scanning. |
first_indexed | 2024-04-11T21:45:30Z |
format | Article |
id | doaj.art-01378e0d2bdf4a05878617384abacb97 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T21:45:30Z |
publishDate | 2019-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-01378e0d2bdf4a05878617384abacb972022-12-22T04:01:25ZengMDPI AGSensors1424-82202019-09-011918394110.3390/s19183941s19183941Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography ImagingZiheng Li0Ailong Cai1Linyuan Wang2Wenkun Zhang3Chao Tang4Lei Li5Ningning Liang6Bin Yan7PLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaPLA Strategy Support Force Information Engineering University, Zhengzhou 450001, ChinaLimited-angle computed tomography (CT) image reconstruction is a challenging problem in the field of CT imaging. In some special applications, limited by the geometric space and mechanical structure of the imaging system, projections can only be collected with a scanning range of less than 90°. We call this kind of serious limited-angle problem the ultra-limited-angle problem, which is difficult to effectively alleviate by traditional iterative reconstruction algorithms. With the development of deep learning, the generative adversarial network (GAN) performs well in image inpainting tasks and can add effective image information to restore missing parts of an image. In this study, given the characteristic of GAN to generate missing information, the sinogram-inpainting-GAN (SI-GAN) is proposed to restore missing sinogram data to suppress the singularity of the truncated sinogram for ultra-limited-angle reconstruction. We propose the U-Net generator and patch-design discriminator in SI-GAN to make the network suitable for standard medical CT images. Furthermore, we propose a joint projection domain and image domain loss function, in which the weighted image domain loss can be added by the back-projection operation. Then, by inputting a paired limited-angle/180° sinogram into the network for training, we can obtain the trained model, which has extracted the continuity feature of sinogram data. Finally, the classic CT reconstruction method is used to reconstruct the images after obtaining the estimated sinograms. The simulation studies and actual data experiments indicate that the proposed method performed well to reduce the serious artifacts caused by ultra-limited-angle scanning.https://www.mdpi.com/1424-8220/19/18/3941CT image reconstructionultra-limited-angle problemsinogram inpaintinggenerative adversarial network |
spellingShingle | Ziheng Li Ailong Cai Linyuan Wang Wenkun Zhang Chao Tang Lei Li Ningning Liang Bin Yan Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging Sensors CT image reconstruction ultra-limited-angle problem sinogram inpainting generative adversarial network |
title | Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging |
title_full | Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging |
title_fullStr | Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging |
title_full_unstemmed | Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging |
title_short | Promising Generative Adversarial Network Based Sinogram Inpainting Method for Ultra-Limited-Angle Computed Tomography Imaging |
title_sort | promising generative adversarial network based sinogram inpainting method for ultra limited angle computed tomography imaging |
topic | CT image reconstruction ultra-limited-angle problem sinogram inpainting generative adversarial network |
url | https://www.mdpi.com/1424-8220/19/18/3941 |
work_keys_str_mv | AT zihengli promisinggenerativeadversarialnetworkbasedsinograminpaintingmethodforultralimitedanglecomputedtomographyimaging AT ailongcai promisinggenerativeadversarialnetworkbasedsinograminpaintingmethodforultralimitedanglecomputedtomographyimaging AT linyuanwang promisinggenerativeadversarialnetworkbasedsinograminpaintingmethodforultralimitedanglecomputedtomographyimaging AT wenkunzhang promisinggenerativeadversarialnetworkbasedsinograminpaintingmethodforultralimitedanglecomputedtomographyimaging AT chaotang promisinggenerativeadversarialnetworkbasedsinograminpaintingmethodforultralimitedanglecomputedtomographyimaging AT leili promisinggenerativeadversarialnetworkbasedsinograminpaintingmethodforultralimitedanglecomputedtomographyimaging AT ningningliang promisinggenerativeadversarialnetworkbasedsinograminpaintingmethodforultralimitedanglecomputedtomographyimaging AT binyan promisinggenerativeadversarialnetworkbasedsinograminpaintingmethodforultralimitedanglecomputedtomographyimaging |