CT图像的金属伪影校正方法综述
|
摘要
一般情况下,计算机断层扫描(computed tomography,CT)重建后的图像与真实物体之间会存在一些差异,这种差异很大程度体现在重建图像上的伪影。受到金属植入物的影响,CT图像中出现了不同程度的金属伪影,因此近40年出现了大量的金属伪影校正(metal artifacts reduction,MAR)方法对CT图像中的金属伪影进行去除。本文首先回顾了产生金属伪影的基本原因,并介绍了CT图像的传统的MAR方法和目前取得较大进展的基于深度学习的MAR方法的发展趋势;接着文中详细介绍了几种基于卷积神经网络的MAR方法;最后对本文进行了总结并对金属伪影校正方法的前景进行了展望。
In general,reconstructed images of computed tomography(CT) differs from ground truth of objects. The main differences is artifacts on reconstructed images. Caused by metal implants,metal artifacts appear often in CT images. Therefore,a large number of metal artifact reduction(MAR) methodshave been published in last forty years. This paper firstly reviews the basic causes of metal artifacts,and introduces the development of MAR methods for CT images,including the traditional MAR methods and the successful MAR methods based on deep learning. Then,several MAR methods based on convolutional neural networks are introduced in detail. Finally,we summarizes with the prospects of MAR methods.
In general,reconstructed images of computed tomography(CT) differs from ground truth of objects. The main differences is artifacts on reconstructed images. Caused by metal implants,metal artifacts appear often in CT images. Therefore,a large number of metal artifact reduction(MAR) methodshave been published in last forty years. This paper firstly reviews the basic causes of metal artifacts,and introduces the development of MAR methods for CT images,including the traditional MAR methods and the successful MAR methods based on deep learning. Then,several MAR methods based on convolutional neural networks are introduced in detail. Finally,we summarizes with the prospects of MAR methods.
引文
[1]Man B De,Nuyts J,P. Dupont,et al. Metal streak artifacts in X-ray computed tomography:A simulation study[J].IEEE Transactions on Nuclear Science,1999,46(3):691-696.
[2]Man B De,Nuyts J,Dupont P,et al. Metal streak artifacts in X-ray computed tomography:A simulation study[J].IEEE Trans Nucl Sci,1999,46(3):691-696.
[3]KachelrieM. Reduction von metal artefacts in der roentgen-computer-tomographie[J] Inst Med Phys,Univ. Er-langen-Nuremberg, Erlangen, Germany, Tech Rep,1998.
[4]Glover G H,Pelc N J. Nonlinear partial volume artifacts in X-ray computed tomography[J]. Med Phys,1980,7(3):238-248.
[5]Department of Radiology,Renmin Hospital of Wuhan University. The Causes of CT Artifacts. http://www. 360doc.com/content/18/0928/10/58229565_790350571. shtml,2018.(in Chinese).
[6] Park H S,Hwang D,Seo J K. Metal artifact reduction for polychromatic X-ray CT based on a beam-hardening corrector[J]. IEEE Transactions on Medical Imaging,2016,35(2):480-487.
[7]Schüller S9ren,Sawall Stefan,Stannigel Kai,et al. Segmentation-free empirical beam hardening correction for CT[J].Med Phys,2015,42(2):794-803.
[8]Edward Boas F,Dominik Fleischmann. Evaluation of two iterative techniques for reducing metal artifacts in computed tomography[J]. Radiology,2011,259(3):894-902.
[9] Esther Meyer,Rainer Raupach,Michael Lell,et al. Normalized metal artifact reduction(nmar)in computed tomography[J]. Medical Physics, 2010, 37(10):5482-5493.
[10]Veldkamp W J H,Joemai R M S,van der Molen A J,et al. Development and validation of segmentation and interpolation techniques in sinograms for metal artifact suppression in CT[J]. Med Phys,2010,37(2):620-628.
[11]Mehranian A,Ay M R,Rahmim A,et al. X-ray CT metal artifact reduction using wavelet domain L0 sparse regularization[J]. IEEE Trans Med Imag,2013,32(9):1707-1722.
[12] Kratz B,Weyers I,Buzug T M. A fully 3D approach for metal artifact reduction in computed tomography[J]. Med Phys,2012,39(11):7042.
[13]Zhang Y,Pu Y F,Hu J R,et al. A new CT metal artifacts reduction algorithm based on fractional-order sinogram inpainting[J]. J Xray Sci Technol,2011,19(3):373-384.
[14]Jakob Toftegaard,Walther Fledelius,Dieter Seghers,et al.Moving metal artifact reduction in cone-beam CT scans with implanted cylindrical gold markers[J]. Med. Phys,2014,41(12):121710.
[15] Zhang Y,Mou X,Yan H. Weighted total variation constrained reconstruction for reduction of metal artifact in CT[J]. IEEE Nuclear Science Symposium and Medical Imaging Conference(2010 NSS/MIC),2010,2630-2634.
[16] Zhang X,Wang J,Xing L. Metal artifact reduction in X-ray computed tomography(CT)by constrained optimization[J]. Medical Physics,2011,38(2):701-711.
[17]Yao Lan. Research on Metal Artifact Removal Method in CT Images[D]. Southeast University,2013.(in Chinese)
[18] Zhang Xiaomeng,Wang Jing,Xing Lei. Metal artifact reduction in X-ray computed tomography(ct)by constrained optimization[J]. Medical Physics,2011,38(2):701-711.
[19]Chen Z,Jin X,Li L,et al. A limited-angle CT reconstruction method based on anisotropic TV minimization[J]. Phys Med Biol,2013,58(7):2119-2141.
[20]Frikel J,Quinto E T. Characterization and reduction of artifacts in limited angle tomography[J]. Inverse Problems,2013,29(12):2091-2128.
[21] Zhang X,Wang J,Xing L. Metal artifact reduction in X-ray computed tomography(CT)by constrained optimization[J]. Med Phys,2011,38(2):701-711.
[22]Soltanian Zadeh H,Windham J P,Soltanianzadeh J. CT artifact correction:An image-processing approach[C]//Proceedings of SPIE Medical Imaging Conference, Newport Beach,CA,1996:477-485.
[23]Bal M,Celik H,Subramanyan K,et al. A radial adaptive filter for metal artifact reduction[C]//Proceedingd of SPIE Medical Image Conference,2005:2075-2082.
[24]Watzke O,Kalender W A. A pragmatic approach to metal artifact reduction in CT:Merging of metal artifact reduced images[J]. Eur. Radiol,2004,14(5):849-856.
[25]Zhang Y,Yan H,Jia X,et al. A hybrid metal artifact reduction algorithm for X-ray CT[J]. Medical Physics,2013,40(4):041910.
[26] Zhang Y,Mou X. Metal artifact reduction based on beam hardening correction and statistical iterative reconstruction for X-ray computed tomography[C]//Proceedings of SPIE Physics of Medical Imaging,2013,866820.
[27] Mouton A,Megherbi N,Flitton G T,et al. A novel intensity limiting approach to metal artefact reduction in 3D CT baggage imagery[C]//Proceedings of ICIP,2012:2057-2060.
[28]Gjesteby L,Yang Q,Xi Y,et al. Deep learning methods to guide CT image reconstruction and reduce metal artifacts[C]//Proceedings of SPIE Medical Imaging,International Society for Optics and Photonics,2017:101 322W-101-322W-107.
[29] Gjesteby L,Yang Q,Xi Y,et al. Reducing metal streak artifacts in CT images via deep learning:Pilot results[C]//Proceedings of 14th International Meeting on Fully ThreeDimensional Image Reconstruction in Radiology and Nuclear Medicine,2017:611-614.
[30]Gjesteby L,Yang Q,Xi Y,et al. Deep learning methods for CT image-domain metal artifact reduction[C]//Proceedings of SPIE Optical Engineering+Applications,2017:03910W.
[31]Zhang Yanbo,Yu Hengyong. Convolutional Neural Network based Metal Artifact Reduction in X-ray Computed Tomography[C]//Proceedings of IEEE Transactions on Medical Imaging,2018:1709. 01581.
[32]Li Daiyuan. Application of Deep Convolution Belief Network in Intracranial CT Image Classification[D]. Hunan Normal University,2017.(in Chinese)
[33] Zhang Hanming, Li Liang, Qiao Kai, et al. Image prediction for limited-angle tomography via deep learning with convolutional neural network[J]. In ar Xiv:1607. 08707,2016.
[34]Zhang C,Xing Y. CT artifact reduction via U-net CNN[C]//Proceedings in SPIE Medical Imaging, 2018,(10574):105741R.
[35]Xu Shiyu,Dang Hao. Deep residual learning enabled metal artifact reduction in CT[C]//Proceedings of SPIE,2018:105733O-5.
[36] Ghani Muhammad Usman,Karl W Clem. Deep learning based sinogram correction for metal artifact reduction[C]//Proceedings of Electronic Imaging,Computational Imaging XVI,2018:4721-4728.
[37]Ronneberger O,Fischer P,Brox T. U-Net:Convolutional networks for biomedical image segmentation[C]//Proceedings of Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015:18thInternational Conference,Munich,Germany,October 5-9,Part III. Cham:Springer International Publishing,2015,234-241.
[38]Han Y S,Yoo J,Ye J C. Deep residual learning for compressed sensing CT reconstruction via persistent homology analysis[J]. Ar Xiv,2016.
[39]Kim Jiwon,Lee Jung Kwon,Lee Kyoung Mu. Accurate image super-resolution using very deep convolutional networks[C]//In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:1646-1654.
[40] Ioffe Sergey, Szegedy Christian. Batch normalization:Accelerating deep network training by reducing internal covariate shift[J]. Ar Xiv Preprint Ar Xiv:1502. 03167,2015.
[2]Man B De,Nuyts J,Dupont P,et al. Metal streak artifacts in X-ray computed tomography:A simulation study[J].IEEE Trans Nucl Sci,1999,46(3):691-696.
[3]KachelrieM. Reduction von metal artefacts in der roentgen-computer-tomographie[J] Inst Med Phys,Univ. Er-langen-Nuremberg, Erlangen, Germany, Tech Rep,1998.
[4]Glover G H,Pelc N J. Nonlinear partial volume artifacts in X-ray computed tomography[J]. Med Phys,1980,7(3):238-248.
[5]Department of Radiology,Renmin Hospital of Wuhan University. The Causes of CT Artifacts. http://www. 360doc.com/content/18/0928/10/58229565_790350571. shtml,2018.(in Chinese).
[6] Park H S,Hwang D,Seo J K. Metal artifact reduction for polychromatic X-ray CT based on a beam-hardening corrector[J]. IEEE Transactions on Medical Imaging,2016,35(2):480-487.
[7]Schüller S9ren,Sawall Stefan,Stannigel Kai,et al. Segmentation-free empirical beam hardening correction for CT[J].Med Phys,2015,42(2):794-803.
[8]Edward Boas F,Dominik Fleischmann. Evaluation of two iterative techniques for reducing metal artifacts in computed tomography[J]. Radiology,2011,259(3):894-902.
[9] Esther Meyer,Rainer Raupach,Michael Lell,et al. Normalized metal artifact reduction(nmar)in computed tomography[J]. Medical Physics, 2010, 37(10):5482-5493.
[10]Veldkamp W J H,Joemai R M S,van der Molen A J,et al. Development and validation of segmentation and interpolation techniques in sinograms for metal artifact suppression in CT[J]. Med Phys,2010,37(2):620-628.
[11]Mehranian A,Ay M R,Rahmim A,et al. X-ray CT metal artifact reduction using wavelet domain L0 sparse regularization[J]. IEEE Trans Med Imag,2013,32(9):1707-1722.
[12] Kratz B,Weyers I,Buzug T M. A fully 3D approach for metal artifact reduction in computed tomography[J]. Med Phys,2012,39(11):7042.
[13]Zhang Y,Pu Y F,Hu J R,et al. A new CT metal artifacts reduction algorithm based on fractional-order sinogram inpainting[J]. J Xray Sci Technol,2011,19(3):373-384.
[14]Jakob Toftegaard,Walther Fledelius,Dieter Seghers,et al.Moving metal artifact reduction in cone-beam CT scans with implanted cylindrical gold markers[J]. Med. Phys,2014,41(12):121710.
[15] Zhang Y,Mou X,Yan H. Weighted total variation constrained reconstruction for reduction of metal artifact in CT[J]. IEEE Nuclear Science Symposium and Medical Imaging Conference(2010 NSS/MIC),2010,2630-2634.
[16] Zhang X,Wang J,Xing L. Metal artifact reduction in X-ray computed tomography(CT)by constrained optimization[J]. Medical Physics,2011,38(2):701-711.
[17]Yao Lan. Research on Metal Artifact Removal Method in CT Images[D]. Southeast University,2013.(in Chinese)
[18] Zhang Xiaomeng,Wang Jing,Xing Lei. Metal artifact reduction in X-ray computed tomography(ct)by constrained optimization[J]. Medical Physics,2011,38(2):701-711.
[19]Chen Z,Jin X,Li L,et al. A limited-angle CT reconstruction method based on anisotropic TV minimization[J]. Phys Med Biol,2013,58(7):2119-2141.
[20]Frikel J,Quinto E T. Characterization and reduction of artifacts in limited angle tomography[J]. Inverse Problems,2013,29(12):2091-2128.
[21] Zhang X,Wang J,Xing L. Metal artifact reduction in X-ray computed tomography(CT)by constrained optimization[J]. Med Phys,2011,38(2):701-711.
[22]Soltanian Zadeh H,Windham J P,Soltanianzadeh J. CT artifact correction:An image-processing approach[C]//Proceedings of SPIE Medical Imaging Conference, Newport Beach,CA,1996:477-485.
[23]Bal M,Celik H,Subramanyan K,et al. A radial adaptive filter for metal artifact reduction[C]//Proceedingd of SPIE Medical Image Conference,2005:2075-2082.
[24]Watzke O,Kalender W A. A pragmatic approach to metal artifact reduction in CT:Merging of metal artifact reduced images[J]. Eur. Radiol,2004,14(5):849-856.
[25]Zhang Y,Yan H,Jia X,et al. A hybrid metal artifact reduction algorithm for X-ray CT[J]. Medical Physics,2013,40(4):041910.
[26] Zhang Y,Mou X. Metal artifact reduction based on beam hardening correction and statistical iterative reconstruction for X-ray computed tomography[C]//Proceedings of SPIE Physics of Medical Imaging,2013,866820.
[27] Mouton A,Megherbi N,Flitton G T,et al. A novel intensity limiting approach to metal artefact reduction in 3D CT baggage imagery[C]//Proceedings of ICIP,2012:2057-2060.
[28]Gjesteby L,Yang Q,Xi Y,et al. Deep learning methods to guide CT image reconstruction and reduce metal artifacts[C]//Proceedings of SPIE Medical Imaging,International Society for Optics and Photonics,2017:101 322W-101-322W-107.
[29] Gjesteby L,Yang Q,Xi Y,et al. Reducing metal streak artifacts in CT images via deep learning:Pilot results[C]//Proceedings of 14th International Meeting on Fully ThreeDimensional Image Reconstruction in Radiology and Nuclear Medicine,2017:611-614.
[30]Gjesteby L,Yang Q,Xi Y,et al. Deep learning methods for CT image-domain metal artifact reduction[C]//Proceedings of SPIE Optical Engineering+Applications,2017:03910W.
[31]Zhang Yanbo,Yu Hengyong. Convolutional Neural Network based Metal Artifact Reduction in X-ray Computed Tomography[C]//Proceedings of IEEE Transactions on Medical Imaging,2018:1709. 01581.
[32]Li Daiyuan. Application of Deep Convolution Belief Network in Intracranial CT Image Classification[D]. Hunan Normal University,2017.(in Chinese)
[33] Zhang Hanming, Li Liang, Qiao Kai, et al. Image prediction for limited-angle tomography via deep learning with convolutional neural network[J]. In ar Xiv:1607. 08707,2016.
[34]Zhang C,Xing Y. CT artifact reduction via U-net CNN[C]//Proceedings in SPIE Medical Imaging, 2018,(10574):105741R.
[35]Xu Shiyu,Dang Hao. Deep residual learning enabled metal artifact reduction in CT[C]//Proceedings of SPIE,2018:105733O-5.
[36] Ghani Muhammad Usman,Karl W Clem. Deep learning based sinogram correction for metal artifact reduction[C]//Proceedings of Electronic Imaging,Computational Imaging XVI,2018:4721-4728.
[37]Ronneberger O,Fischer P,Brox T. U-Net:Convolutional networks for biomedical image segmentation[C]//Proceedings of Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015:18thInternational Conference,Munich,Germany,October 5-9,Part III. Cham:Springer International Publishing,2015,234-241.
[38]Han Y S,Yoo J,Ye J C. Deep residual learning for compressed sensing CT reconstruction via persistent homology analysis[J]. Ar Xiv,2016.
[39]Kim Jiwon,Lee Jung Kwon,Lee Kyoung Mu. Accurate image super-resolution using very deep convolutional networks[C]//In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition,2016:1646-1654.
[40] Ioffe Sergey, Szegedy Christian. Batch normalization:Accelerating deep network training by reducing internal covariate shift[J]. Ar Xiv Preprint Ar Xiv:1502. 03167,2015.