請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81777完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 周呈霙(Cheng-Ying Chou) | |
| dc.contributor.author | Zi-Ping Zhong | en |
| dc.contributor.author | 鍾子平 | zh_TW |
| dc.date.accessioned | 2022-11-24T09:27:12Z | - |
| dc.date.available | 2022-11-24T09:27:12Z | - |
| dc.date.copyright | 2021-11-03 | |
| dc.date.issued | 2021 | |
| dc.date.submitted | 2021-10-28 | |
| dc.identifier.citation | Barrett, H. H. and Myers, K. J. (2007). Statistical characterization of radiological images: basic principles and recent progress. Medical Imaging 2007: Physics of Medical Imaging, 6510: 651002. Barrett, H. H. and Myers, K. J. (2013). Foundations of image science. John Wiley Sons. Bochud, F. O., Abbey, C. K., and Eckstein, M. P. (1999). Statistical texture synthesis of mammographic images with clustered lumpy backgrounds. Optics express, 4(1): 33–43. Caucci, L., Barrett, H.H., Devaney, N., and Rodríguez, J.J.(2007). JOSAA, 24(12): B13–B24. Chi, J., Wu, C., Yu, X., Ji, P., and Chu, H. (2020). Single low dose ct image denoising using a generative adversarial network with modified unet generator and multi-level discriminator. IEEE Access, 8: 133470–133487. Chou, C.Y., Huang, Y., Shi, D., and Anastasio, M. A. (2007). Image reconstruction in quantitative x-ray phase-contrast imaging employing multiple measurements. Optics express, 15(16): 10002–10025. Dorta, G., Vicente, S., Agapito, L., Campbell, N. D., and Simpson, I. (2018). Structured uncertainty prediction networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 5477–5485. Ge, Y., Liu, P., Ni, Y., Chen, J., Yang, J., Su, T., Zhang, H., Guo, J., Zheng, H., Li, Z., et al. (2020). Enhancing the x-ray differential phase contrast image quality with deep learning technique. IEEE Transactions on Biomedical Engineering, 68(6): 1751–1758. Gradl, R., Dierolf, M., Hehn, L., Günther, B., Yildirim, A. Ö., Gleich, B., Achterhold, K., Pfeiffer, F., and Morgan, K.S. (2017). Propagation-based phase-contrast x-ray imaging at a compact light source.Scientific reports, 7(1):1–9. Groso, A., Abela, R., and Stampanoni, M. (2006). Implementation of a fast method for high resolution phase contrast tomography. Optics express, 14(18):8103–8110. He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778. Ion, V. (2013). Nonlinear approaches for phase retrieval in the Fresnel region for hard Xray imaging. PhD thesis, Lyon, INSA. Isola, P., Zhu, J.Y., Zhou, T., and Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1125–1134. Keskitalo, R., Ashdown, M., Cabella, P., Kisner, T., Poutanen, T., Stompor, R., Bartlett, J., Borrill, J., Cantalupo, C., De Gasperis, G., et al. (2010). Residual noise covariance for planck low resolution data analysis. Astronomy Astrophysics, 522:A94. Kim, B., Han, M., Shim, H., and Baek, J. (2019). A performance comparison of convolutional neural networkbased image denoising methods: The effect of loss functions onlowdose ct images. Medical physics, 46(9): 3906–3923. Kingma, D. P. and Ba, J. (2014). Adam: A method for stochastic optimization.arXivpreprint arXiv: 1412.6980. Kupinski, M. A., Clarkson, E., and Hesterman, J. Y. (2007). Bias in hotelling observer performance computed from finite data. In Medical Imaging 2007: Image Perception, Observer Performance, and Technology Assessment, volume 6515, page 65150S. International Society for Optics and Photonics. Kupinski, M. A., Edwards, D. C., Giger, M. L., and Metz, C. E. (2001). Ideal observer approximation using bayesian classification neural networks. IEEE transactions on medical imaging, 20(9): 886–899. Langer, M., Cloetens, P., Guigay, J.P., and Peyrin, F. (2008). Quantitative comparison of direct phase retrieval algorithms in-inline phase tomography. Medical physics, 35(10): 4556–4566. Langer, M., Cloetens, P., and Peyrin, F. (2010). Regularization of phase retrieval with phase-attenuation duality prior for 3-d holotomography. IEEE Transactions on ImageProcessing, 19(9): 2428–2436. Li, Y., Tang, S., Zhang, R., Zhang, Y., Li, J., and Yan, S. (2019). Asymmetric gan for unpaired image-to-image translation. IEEE Transactions on Image Processing, 28(12): 5881–5896. Lim, B., Son, S., Kim, H., Nah, S., and Mu Lee, K. (2017). Enhanced deep residual networks for single image superresolution. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 136–144. Moseley, T. W. (2016). Digital mammography and digital breast tomosynthesis. Clinical obstetrics and gynecology, 59(2): 362–379. Park, S. and Clarkson, E. (2009). Efficient estimation of ideal-observer performance in classification tasks involving high dimensional complex backgrounds. JOSA A, 26(11): B59–B71. Park, S., Clarkson, E., Kupinski, M. A., and Barrett, H. H. (2005). Efficiency of human and model observers for signal detection tasks in non-gaussian distributed lumpy backgrounds. In Medical Imaging 2005: Image Perception, Observer Performance, and Technology Assessment, volume 5749, pages 138–149. International Society for Optics and Photonics. Park, S., Kupinski, M. A., Clarkson, E., and Barrett, H. H. (2003). Ideal-observer performance under signal and background uncertainty. In Biennial International Conference on Information Processing in Medical Imaging, pages 342–353. Springer. Pinilla, S., Bacca, J., and Arguello, H. (2018). Phase retrieval algorithm via nonconvex minimization using a smoothing function. IEEE Transactions on Signal Processing, 66(17): 4574–4584. Qian, J., Wu, Y., Zhuang, B., Wang, S., Xiao, J., et al. (2021). Understanding gradient clipping in incremental gradient methods. In International Conference on Artificial Intelligence and Statistics, pages 1504–1512. PMLR. Rivenson, Y., Wu, Y., and Ozcan, A. (2019). Deep learning in holography and coherent imaging.Light: Science Applications, 8(1): 1–8. Rivenson, Y., Zhang, Y., Günaydın, H., Teng, D., and Ozcan, A. (2018). Phase recovery and holographic image reconstruction using deep learning in neural networks. Light: Science Applications, 7(2): 17141–17141. Ronneberger, O., Fischer, P., and Brox, T. (2015). Unet: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention, pages 234–241. Springer. Taba, S. T., Arhatari, B. D., Nesterets, Y. I., Gadomkar, Z., Mayo, S. C., Thompson, D., Fox, J., Kumar, B., Prodanovic, Z., Hausermann, D., et al. (2021). Propagationbased phase-contrast ct of the breast demonstrates higher quality than conventional absorption-based ct even at lower radiation dose. Academic radiology, 28(1): e20–e26. Vedantham, S. and Karellas, A. (2013). X-ray phase contrast imaging of the breast: Analysis of tissue simulating materials a. Medical physics, 40(4): 041906. Xia, X.andKulis, B. (2017). Wnet: A deep model for fully unsupervised image segmentation. arXiv preprint arXiv: 1711.08506. Zhang, Y., Noack, M. A., Vagovic, P., Fezzaa, K., GarciaMoreno, F., Ritschel, T., and Villanueva-Perez, P. (2020). Phasegan: A deep-learning phase-retrieval approach for unpaired datasets. arXiv preprint arXiv: 2011.08660. Zhou, W., Li, H., and Anastasio, M. A. (2019). Approximating the ideal observer and hotelling observer for binary signal detection tasks by use of supervised learning methods. IEEE transactions on medical imaging, 38(10): 2456–2468. Zhou, W., Li, H., and Anastasio, M.A. (2020). Approximating the ideal observer for joint signal detection and localization tasks by use of supervised learning methods. IEEE transactions on medical imaging, 39(12): 3992–4000. Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the IEEE international conference on computer vision, pages 2223–2232. Zuo, C., Li, J., Sun, J., Fan, Y., Zhang, J., Lu, L., Zhang, R., Wang, B., Huang, L., andChen, Q. (2020). Transport of intensity equation: a tutorial. Optics and Lasers in Engineering, 135: 106187. | |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/81777 | - |
| dc.description.abstract | X光相位對比成像是一種藉由X光穿透物體後的相位變化，在軟組織等對於X光吸收對比度較弱的物質，可以提供良好影像品質的成像技術。在傳播X光相位對比成像技術下，基於不同物體和探測器的距離，可以在探測器上量測到強度影像。這些強度影像需要經由相位擷取演算法來回復相位資訊。然而，在這些相位擷取演算法當中存在奇異點，以致影像造成雜訊放大效應。在以往，可以利用非線性迭代方法去處理這個問題，但是這樣的方法缺乏達到良好影像品質的效能。在本論文當中，我們將迭代和深度學習的方法結合以重建相位資訊。這裡使用的深度學習方法是利用生成對抗網路來實現，其生成器於本論文的架構包括UNet、WNet以及SRResNet。我們隨後利用觀察者研究方法下的接受器操作曲線作定性評估，驗證這些經由深度學習後的重建相位。結果顯示藉由深度學習的方式可以提供一個良好的框架解決相位擷取演算法的問題，使我們可以得到影像品質較好的回復相位。在這些深度學習架構的結果當中，SRResNet擁有最佳的分類能力，其接受器操作曲線下面積達到82.6%。另一方面，WNet則擁有最高的對比度，其峰值訊雜比達到26.05。 | zh_TW |
| dc.description.provenance | Made available in DSpace on 2022-11-24T09:27:12Z (GMT). No. of bitstreams: 1 U0001-2709202112555900.pdf: 11795755 bytes, checksum: c39a9364b2db02ae22172cb1c7ddb1e8 (MD5) Previous issue date: 2021 | en |
| dc.description.tableofcontents | Verification Letter from the Oral Examination Committee i Acknowledgments ii 摘要 iii Abstract iv Contents vi List of Figures ix List of Tables xiii Denotation xiv Chapter 1 Introduction 1 Chapter 2 Literature Review 6 2.1 Experimental setup of the X-ray imaging system 6 2.2 Phase retrieval algorithms 10 2.2.1 Contrast transfer function model 13 2.2.2 Transport of intensity equation model 15 2.2.3 Mixed transfer function model 18 Chapter 3 Materials and methods 24 3.1 Statistical background and signal models 24 3.2 Image formation 26 3.2.1 Background-Known-Statistically (BKS) models 27 3.2.2 SKE/BKS signal detection task 28 3.2.3 SKS/BKS signal detection task 28 3.3 Observer studies 33 3.3.1 Test statistic 33 3.3.2 MCMC method in SKE/BKS and SKS/BKS signal detection tasks 43 Chapter 4 Deep learning approach 51 4.1 Generative adversarial network approach 51 4.1.1 Proposed discriminator: PatchGAN architecture 53 4.1.2 Proposed generator: U-Net architecture 53 4.1.3 Proposed generator: W-Net architecture 54 4.1.4 Proposed generator: SRResNet architecture 58 4.1.5 Covariance estimation network 58 4.2 The model process and loss functions design 60 4.2.1 The model process 60 4.2.2 Loss functions 62 4.2.2.1 Adversarial loss 64 4.2.2.2 Cycle-consistency loss and VGG feature loss 65 4.2.2.3 Covariance loss 66 Chapter 5 Computer simulation Studies 69 5.1 Description of the dataset and neural network 69 5.1.1 The dataset 69 5.1.2 The details related to neural network 69 5.2 Validation and testing results 70 Chapter 6 Conclusions 87 References 89 | |
| dc.language.iso | en | |
| dc.subject | 觀察者研究 | zh_TW |
| dc.subject | 相位對比成像 | zh_TW |
| dc.subject | 相位擷取演算法 | zh_TW |
| dc.subject | 迭代方法 | zh_TW |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | deep learning | en |
| dc.subject | phase contrast imaging | en |
| dc.subject | phase retrieval algorithm | en |
| dc.subject | iterative approach | en |
| dc.subject | observer studies | en |
| dc.title | 神經網路於X光相位對比成像之應用 | zh_TW |
| dc.title | Application of Neural Networks for the Improvement of X-ray Phase Contrast Imaging | en |
| dc.date.schoolyear | 109-2 | |
| dc.description.degree | 碩士 | |
| dc.contributor.oralexamcommittee | 許靖涵(Hsin-Tsai Liu),王偉仲(Chih-Yang Tseng) | |
| dc.subject.keyword | 相位對比成像,相位擷取演算法,迭代方法,深度學習,觀察者研究, | zh_TW |
| dc.subject.keyword | phase contrast imaging,phase retrieval algorithm,iterative approach,deep learning,observer studies, | en |
| dc.relation.page | 94 | |
| dc.identifier.doi | 10.6342/NTU202103387 | |
| dc.rights.note | 未授權 | |
| dc.date.accepted | 2021-10-29 | |
| dc.contributor.author-college | 生物資源暨農學院 | zh_TW |
| dc.contributor.author-dept | 生物機電工程學系 | zh_TW |
| 顯示於系所單位： | 生物機電工程學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| U0001-2709202112555900.pdf 未授權公開取用 | 11.52 MB | Adobe PDF |
系統中的文件，除了特別指名其著作權條款之外，均受到著作權保護，並且保留所有的權利。