Development of a denoising convolutional neural network-based algorithm for metal artifact reduction in digital tomosynthesis for arthroplasty: A phantom study
Autoři:
Tsutomu Gomi aff001; Rina Sakai aff001; Hidetake Hara aff001; Yusuke Watanabe aff001; Shinya Mizukami aff001
Působiště autorů:
School of Allied Health Sciences, Kitasato University, Sagamihara, Kanagawa, Japan
aff001
Vyšlo v časopise:
PLoS ONE 14(9)
Kategorie:
Research Article
doi:
https://doi.org/10.1371/journal.pone.0222406
Souhrn
The present study aimed to develop a denoising convolutional neural network metal artifact reduction hybrid reconstruction (DnCNN-MARHR) algorithm for decreasing metal objects in digital tomosynthesis (DT) for arthroplasty by using projection data. For metal artifact reduction (MAR), we implemented a DnCNN-MARHR algorithm based on a training network (mini-batch stochastic gradient descent algorithm with momentum) to estimate the residual reference (140 keV virtual monochromatic [VM]) and object (70 kV with metal artifacts) images. For this, we used projection data and subtracted the estimated residual images from the object images, involving hybrid and subjectively reconstructed image usage (back projection and maximum likelihood expectation maximization [MLEM]). The DnCNN-MARHR algorithm was compared with the dual-energy material decomposition reconstruction algorithm (DEMDRA), VM, MLEM, established and commonly used filtered back projection (FBP), and a simultaneous algebraic reconstruction technique-total variation (SART-TV) with MAR processing. MAR was compared using artifact index (AI) and texture analysis. Artifact spread functions (ASFs) for images that were out-of-plane and in-focus were evaluated using a prosthesis phantom. The overall performance of the DnCNN-MARHR algorithm was adequate with regard to the ASF, and the derived images showed better results, without being influenced by the metal type (AI was almost equal to the best value for the DEMDRA). In the ASF analysis, the DnCNN-MARHR algorithm generated better MAR compared with that obtained employing usual algorithms for reconstruction using MAR processing. In addition, comparison of the difference (mean square error) between DnCNN-MARHR and the conventional algorithm resulted in the smallest VM. The DnCNN-MARHR algorithm showed the best performance with regard to image homogeneity in the texture analysis. The proposed algorithm is particularly useful for reducing artifacts in the longitudinal direction, and it is not affected by tissue misclassification.
Klíčová slova:
Physical sciences – Mathematics – Applied mathematics – Algorithms – Research and analysis methods – Simulation and modeling – Imaging techniques – Bone imaging – X-ray radiography – Mathematical and statistical techniques – Mathematical functions – Engineering and technology – Signal processing – Image processing – Assistive technologies – Prosthetics – Medicine and health sciences – Diagnostic medicine – Diagnostic radiology – Radiology and imaging – Surgical and invasive medical procedures – Musculoskeletal system procedures – Arthroplasty – Biology and life sciences – Bioengineering – Biotechnology – Medical devices and equipment – Neuroscience – Neural networks – Computer and information sciences
Zdroje
1. Tang H, Yang D, Guo S, Tang J, Liu J, Wang D, et al. Digital tomosynthesis with metal artifact reduction for assessing cementless hip arthroplasty: a diagnostic cohort study of 48 patients. Skeletal Radiol. 2016;45(11):1523–32. Epub 2016/09/04. doi: 10.1007/s00256-016-2466-8 27589968.
2. Gothlin JH, Geijer M. The utility of digital linear tomosynthesis imaging of total hip joint arthroplasty with suspicion of loosening: a prospective study in 40 patients. Biomed Res Int. 2013;2013:594631. Epub 2013/10/01. doi: 10.1155/2013/594631 24078921; PubMed Central PMCID: PMC3776365.
3. Machida H, Yuhara T, Mori T, Ueno E, Moribe Y, Sabol JM. Optimizing parameters for flat-panel detector digital tomosynthesis. Radiographics. 2010;30(2):549–62. Epub 2010/03/17. doi: 10.1148/rg.302095097 20228334.
4. Duryea J, Dobbins JT 3rd, Lynch JA. Digital tomosynthesis of hand joints for arthritis assessment. Med Phys. 2003;30(3):325–33. Epub 2003/04/04. doi: 10.1118/1.1543573 12674232.
5. Dobbins JT 3rd, Godfrey DJ. Digital x-ray tomosynthesis: current state of the art and clinical potential. Phys Med Biol. 2003;48(19):R65–106. Epub 2003/10/29. doi: 10.1088/0031-9155/48/19/r01 14579853.
6. Gomi T, Hirano H. Clinical potential of digital linear tomosynthesis imaging of total joint arthroplasty. J Digit Imaging. 2008;21(3):312–22. Epub 2007/06/09. doi: 10.1007/s10278-007-9040-9 17557182; PubMed Central PMCID: PMC3043838.
7. Gomi T, Sakai R, Goto M, Watanabe Y, Takeda T, Umeda T. Comparison of Reconstruction Algorithms for Decreasing the Exposure Dose During Digital Tomosynthesis for Arthroplasty: a Phantom Study. J Digit Imaging. 2016;29(4):488–95. Epub 2016/03/05. doi: 10.1007/s10278-016-9876-y 26943661; PubMed Central PMCID: PMC4942396.
8. Becker AS, Martini K, Higashigaito K, Guggenberger R, Andreisek G, Frauenfelder T. Dose Reduction in Tomosynthesis of the Wrist. AJR Am J Roentgenol. 2017;208(1):159–64. Epub 2016/10/21. doi: 10.2214/AJR.16.16729 27762599.
9. Gomi T, Sakai R, Goto M, Hara H, Watanabe Y, Umeda T. Evaluation of digital tomosynthesis reconstruction algorithms used to reduce metal artifacts for arthroplasty: A phantom study. Phys Med. 2017;42:28–38. Epub 2017/11/28. doi: 10.1016/j.ejmp.2017.07.023 29173918.
10. Candes EJ, Romberg J, Tao T. Robust uncertainty principles: exact signal reconstruction from highly incomplete frequency information. IEEE Trans Inf Theory. 2006;52:489–509. doi: 10.1109/TIT.2005.862083
11. Sidky EY, Pan X. Image reconstruction in circular cone-beam computed tomography by constrained, total-variation minimization. Phys Med Biol. 2008;53(17):4777–807. Epub 2008/08/15. doi: 10.1088/0031-9155/53/17/021 18701771; PubMed Central PMCID: PMC2630711.
12. Aharon M, Elad M, Rruckstein A. A K-SVD an algorithm for denoising overcomplete dictionaries for sparse representation. IEEE Trans Signal Process. 2006;54:4311–22. doi: 10.1109/TSP.2006.881199
13. Du Y, Wang X, Xiang X, Wei Z. Evaluation of hybrid SART + OS + TV iterative reconstruction algorithm for optical-CT gel dosimeter imaging. Phys Med Biol. 2016;61(24):8425–39. Epub 2016/11/16. doi: 10.1088/0031-9155/61/24/8425 27845916.
14. Wu T, Moore RH, Rafferty EA, Kopans DB. A comparison of reconstruction algorithms for breast tomosynthesis. Med Phys. 2004;31(9):2636–47. Epub 2004/10/19. doi: 10.1118/1.1786692 15487747.
15. Gomi T, Hirano H, Umeda T. Evaluation of the X-ray digital linear tomosynthesis reconstruction processing method for metal artifact reduction. Comput Med Imaging Graph. 2009;33(4):267–74. Epub 2009/02/25. doi: 10.1016/j.compmedimag.2009.01.004 19237263.
16. Gomi T, Sakai R, Goto M, Hara H, Watanabe Y. Development of a novel algorithm for metal artifact reduction in digital tomosynthesis using projection-based dual-energy material decomposition for arthroplasty: A phantom study. Phys Med. 2018;53:4–16. Epub 2018/09/23. doi: 10.1016/j.ejmp.2018.07.011 30241753.
17. Wellenberg RH, Boomsma MF, van Osch JA, Vlassenbroek A, Milles J, Edens MA, et al. Low-dose CT imaging of a total hip arthroplasty phantom using model-based iterative reconstruction and orthopedic metal artifact reduction. Skeletal Radiol. 2017;46(5):623–32. Epub 2017/02/17. doi: 10.1007/s00256-017-2580-2 28204857; PubMed Central PMCID: PMC5355502.
18. Funama Y, Taguchi K, Utsunomiya D, Oda S, Hirata K, Yuki H, et al. A newly-developed metal artifact reduction algorithm improves the visibility of oral cavity lesions on 320-MDCT volume scans. Phys Med. 2015;31(1):66–71. Epub 2014/12/03. doi: 10.1016/j.ejmp.2014.10.003 25455439.
19. Zhang K, Zuo W, Chen Y, Meng D, Zhang L. Beyond a gauaaian denoiser: residual learning of deep CNN for image denoising. IEEE Trans Image Process. 2017;26(7):3142–55. doi: 10.1109/TIP.2017.2662206 28166495
20. Yoon Y, Jeon HG, Yoo D, Lee JY, Kweon IS. Learning a deep convolutional network for light-field image super-resolution IEEE international conference on computer vision workshop. 2015:57–65. doi: 10.1109/ICCVW.2015.17
21. Chen H, Zhang Y, Kalra MK, Lin F, Chen Y, Liao P, et al. Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network. IEEE Trans Med Imaging. 2017;36(12):2524–35. Epub 2017/06/18. doi: 10.1109/TMI.2017.2715284 28622671; PubMed Central PMCID: PMC5727581.
22. Wolterink JM, Leiner T, Viergever MA, Isgum I. Generative Adversarial Networks for Noise Reduction in Low-Dose CT. IEEE Trans Med Imaging. 2017;36(12):2536–45. Epub 2017/06/03. doi: 10.1109/TMI.2017.2708987 28574346.
23. Zhang Y, Yu H. Convolutional Neural Network Based Metal Artifact Reduction in X-Ray Computed Tomography. IEEE Trans Med Imaging. 2018;37(6):1370–81. Epub 2018/06/06. doi: 10.1109/TMI.2018.2823083 29870366; PubMed Central PMCID: PMC5998663.
24. Park HS, Lee SM, Kim HP, Seo JK, Chung YE. CT sinogram-consistency learning for metal-induced beam hardening correction. Med Phys. 2018;45(12):5376–84. Epub 2018/09/22. doi: 10.1002/mp.13199 30238586.
25. Pessis E, Campagna R, Sverzut JM, Bach F, Rodallec M, Guerini H, et al. Virtual monochromatic spectral imaging with fast kilovoltage switching: reduction of metal artifacts at CT. Radiographics. 2013;33(2):573–83. Epub 2013/03/13. doi: 10.1148/rg.332125124 23479714.
26. Kuchenbecker S, Faby S, Sawall S, Lell M, Kachelriess M. Dual energy CT: how well can pseudo-monochromatic imaging reduce metal artifacts? Med Phys. 2015;42(2):1023–36. Epub 2015/02/06. doi: 10.1118/1.4905106 25652515.
27. Yue D, Fan Rong C, Ning C, Liang H, Ai Lian L, Ru Xin W, et al. Reduction of metal artifacts from unilateral hip arthroplasty on dual-energy CT with metal artifact reduction software. Acta Radiol. 2018;59(7):853–60. Epub 2017/09/14. doi: 10.1177/0284185117731475 28899125.
28. Hegazy MAA, Eldib ME, Hernandez D, Cho MH, Cho MH, Lee SY. Dual-energy-based metal segmentation for metal artifact reduction in dental computed tomography. Med Phys. 2018;45(2):714–24. Epub 2017/12/09. doi: 10.1002/mp.12719 29220087.
29. Katsura M, Sato J, Akahane M, Kunimatsu A, Abe O. Current and Novel Techniques for Metal Artifact Reduction at CT: Practical Guide for Radiologists. Radiographics. 2018;38(2):450–61. Epub 2018/03/13. doi: 10.1148/rg.2018170102 29528826.
30. Maeda K, Matsumoto M, Taniguchi A. Compton-scattering measurement of diagnostic x-ray spectrum using high-resolution Schottky CdTe detector. Med Phys. 2005;32(6):1542–7. Epub 2005/07/15. doi: 10.1118/1.1921647 16013712.
31. Alvarez RE, Macovski A. Energy-selective reconstructions in X-ray computerized tomography. Phys Med Biol. 1976;21(5):733–44. Epub 1976/09/01. doi: 10.1088/0031-9155/21/5/002 967922.
32. Berger M, Hubbell J. Photon cross sections on a personal computer. Gent Radiat Res. 1987:1–28. doi: 10.2172/6016002
33. Sutskever I, Martens J, Dahl G, Hinton G. On the importance of initialization and momentum in deep learning. Proceedings of the 30th international conference on machine learning. 2013;PMLR 28(3):1139–47.
34. Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. International conference on machine learning. 2015:448–56.
35. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems. 2012:1097–105.
36. Chen Y, Yu W, Pock T. On learning optimized reaction diffusion processes for effective image restoration. IEEE Conference on Computer Vision and Pattern Recognition. 2015:5261–9. doi: 10.1109/CVPR.2015.7299163
37. Chen Y, Pock T. Trainable nonlinear reaction diffusion: A flexible framework for fast and effective image restoration. IEEE transactions on Pattern Analysis and Machine Intelligence. 2017;39(6):1256–72. doi: 10.1109/TPAMI.2016.2596743 27529868
38. Wang Y, Qian B, Li B, Qin G, Zhou Z, Qiu Y, et al. Metal artifacts reduction using monochromatic images from spectral CT: evaluation of pedicle screws in patients with scoliosis. Eur J Radiol. 2013;82(8):e360–6. Epub 2013/03/23. doi: 10.1016/j.ejrad.2013.02.024 23518146.
39. Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern. 1973;SMC-3(6):610–21. doi: 10.1109/TSMC.1973.4309314
Článek vyšel v časopise
PLOS One
2019 Číslo 9
- Jak a kdy u celiakie začíná reakce na lepek? Možnou odpověď poodkryla čerstvá kanadská studie
- Pomůže v budoucnu s triáží na pohotovostech umělá inteligence?
- Spermie, vajíčka a mozky – „jednohubky“ z výzkumu 2024/38
- Infekce se v Americe po příjezdu Kolumba šířily nesrovnatelně déle, než se traduje
- Metamizol jako analgetikum první volby: kdy, pro koho, jak a proč?
Nejčtenější v tomto čísle
- Graviola (Annona muricata) attenuates behavioural alterations and testicular oxidative stress induced by streptozotocin in diabetic rats
- CH(II), a cerebroprotein hydrolysate, exhibits potential neuro-protective effect on Alzheimer’s disease
- Comparison between Aptima Assays (Hologic) and the Allplex STI Essential Assay (Seegene) for the diagnosis of Sexually transmitted infections
- Assessment of glucose-6-phosphate dehydrogenase activity using CareStart G6PD rapid diagnostic test and associated genetic variants in Plasmodium vivax malaria endemic setting in Mauritania
Zvyšte si kvalifikaci online z pohodlí domova
Všechny kurzy