請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69361
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 | Ke-Chia Kao | en |
dc.contributor.author | 高可嘉 | zh_TW |
dc.date.accessioned | 2021-06-17T03:13:46Z | - |
dc.date.available | 2020-08-21 | |
dc.date.copyright | 2020-08-21 | |
dc.date.issued | 2020 | |
dc.date.submitted | 2020-08-19 | |
dc.identifier.citation | Beck, A., and Teboulle, M. 2009. A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM journal on imaging sciences, 2(1): 183-202. Berti, V., Pupi, A., and Mosconi, L. 2011. PET/CT in diagnosis of dementia. Annals of the New York Academy of Sciences, 1228: 81. Bioucas-Dias, J. M., and Figueiredo, M. A. 2007. A new TwIST: Two-step iterative shrinkage/thresholding algorithms for image restoration. IEEE Transactions on Image processing, 16(12): 2992-3004. Björck, Å. 1996. Numerical methods for least squares problems: SIAM. E. Nolf, T. V., F. Jacobs, R.A. Dierckx, I. Lemahieu. 2003. (X)MedCon An OpenSource Medical Image Conversion Toolkit. Foucart, S., and Rauhut, H. 2017. A mathematical introduction to compressive sensing. Bull. Am. Math, 54: 151-165. Jones, T. 1996. The role of positron emission tomography within the spectrum of medical imaging. European journal of nuclear medicine, 23(2): 207-211. Khan, A., Sohail, A., Zahoora, U., and Qureshi, A. S. 2020. A survey of the recent architectures of deep convolutional neural networks. Artificial Intelligence Review: 1-62. Kingma, D. P., and Ba, J. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. La Fougère, C., Rominger, A., Förster, S., Geisler, J., and Bartenstein, P. 2009. PET and SPECT in epilepsy: a critical review. Epilepsy Behavior, 15(1): 50-55. Maier, A., Steidl, S., Christlein, V., and Hornegger, J. 2018. Medical Imaging Systems: An Introductory Guide (Vol. 11111): Springer. Malczewski, K. 2013. PET image reconstruction using compressed sensing. 2013 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA). Marcus, C., Mena, E., and Subramaniam, R. M. 2014. Brain PET in the diagnosis of Alzheimer’s disease. Clinical nuclear medicine, 39(10): e413. Natarajan, B. K. 1995. Sparse approximate solutions to linear systems. SIAM journal on computing, 24(2): 227-234. Orović, I., Papić, V., Ioana, C., Li, X., and Stanković, S. 2016. Compressive sensing in signal processing: algorithms and transform domain formulations. Mathematical Problems in Engineering, 2016. Portnow, L. H., Vaillancourt, D. E., and Okun, M. S. 2013. The history of cerebral PET scanning: from physiology to cutting-edge technology. Neurology, 80(10): 952-956. Sakellios, N., Rubio, J. L., Karakatsanis, N., Kontaxakis, G., Loudos, G., Santos, A., Nikita, K., and Majewski, S. 2006. GATE simulations for small animal SPECT/PET using voxelized phantoms and rotating-head detectors. 2006 IEEE Nuclear Science Symposium Conference Record. Santin, G., Strul, D., Lazaro, D., Simon, L., Krieguer, M., Martins, M. V., Breton, V., and Morel, C. 2003. GATE: A Geant4-based simulation platform for PET and SPECT integrating movement and time management. IEEE Transactions on nuclear science, 50(5): 1516-1521. Segars, W. P., Tsui, B. M., Frey, E. C., Johnson, G. A., and Berr, S. S. 2004. Development of a 4-D digital mouse phantom for molecular imaging research. Molecular Imaging Biology, 6(3): 149-159. Siddon, R. L. 1985. Prism representation: a 3D ray-tracing algorithm for radiotherapy applications. Physics in Medicine Biology, 30(8): 817. Yamashita, R., Nishio, M., Do, R. K. G., and Togashi, K. 2018. Convolutional neural networks: an overview and application in radiology. Insights into imaging, 9(4): 611-629. Yan, J., Schaefferkoetter, J., Conti, M., and Townsend, D. 2016. A method to assess image quality for low-dose PET: analysis of SNR, CNR, bias and image noise. Cancer Imaging, 16(1): 1-12. Yao, R., Lecomte, R., and Crawford, E. S. 2012. Small-animal PET: what is it, and why do we need it? Journal of nuclear medicine technology, 40(3): 157-165. Zhang, J., and Ghanem, B. 2018. ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing. Proceedings of the IEEE conference on computer vision and pattern recognition. Zhang, Z. 2016. Derivation of backpropagation in convolutional neural network (cnn). University of Tennessee, Knoxville, TN. Ziran, W., Huachuang, W., and Jianlin, Z. Wavelet sparse transform optimization in image reconstruction based on compressed sensing. 許悅. (2015). 飛行時間法之正子斷層掃描系統衰減暨正子影像之同步估算. (碩士), 國立臺灣大學, 台北市. Retrieved from https://hdl.handle.net/11296/9b3bb7 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/69361 | - |
dc.description.abstract | 因為雙平板式小動物正子斷層掃描具有高靈敏度和靈活的系統配置等特性,此系統常常被用於神經疾病的臨床前研究。但也因為雙平板式的硬體設計,許多事件無法被偵測到,而導致影像模糊,進而影響重建品質。為了要解決事件遺失的問題,本論文使用壓縮感知的技術搭配深度學習在影像重建演算法上。有別於以往的重建技術,重建模型必須經過訓練才可使用。訓練資料來自於以C語言以及GATE與MATLAB所撰寫的自動化資料生成程式,並且由Python工具包製作以ISTA-Net為基底之網路模型,用以訓練模型之學習參數。所得的重建影像,相對於傳統的最大似然與期望最大化估計演算法(MLEM)擁有更高的訊號雜訊比以及對比雜訊比。 | zh_TW |
dc.description.abstract | Dual-head small-animal positron emission tomography (DHAPET) can be used for preclinical studies of neurological diseases because it possesses the characteristics of high detection sensitivity and flexible system configuration. However, the system geometry also leads to undetected events in the trans-axial direction and results in blurring of the reconstructed result. In order to solve the problem, a compressive sensing method incorporated with deep learning was applied to reconstruct images. Apart from traditional reconstruction algorithms, deep learning network models need to be trained before using. The training data were generated by use of a C based program, which integrated GATE and MATLAB codes. Then, the ISTA-Net based image reconstruction network model was built by using Python toolkits. The reconstructed results demonstrate higher signal-to-noise ratio and contrast- to-noisy ratio than those obtained by used of the maximum likelihood expectation maximization method. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T03:13:46Z (GMT). No. of bitstreams: 1 U0001-1808202014440100.pdf: 2012537 bytes, checksum: 767e3e3dcc88d44f0b31a7dad4cdd37f (MD5) Previous issue date: 2020 | en |
dc.description.tableofcontents | Table of contents 摘要 i Abstract ii Table of contents iii List of figures vi CHAPTER 1 Introduction - 1 - Background - 1 - Purpose - 3 - CHAPTER 2 Literature Review - 4 - 2.1 Positron emission tomography - 4 - 2.1.1 Principles of positron emission tomography - 4 - 2.1.2 Small animal PET system - 6 - 2.2 Geat4 application for tomography emission - 7 - 2.3 Image reconstruction - 8 - 2.4 System matrix - 11 - 2.5 Iterative shrinkage thresholding algorithms (ISTA) - 13 - 2.6 Neural network - 14 - 2.6.1 Convolutional neural network (CNN) - 15 - 2.6.2 Universal approximation theorem - 16 - 2.7 Compressive sensing - 16 - CHAPTER 3 Method - 19 - 3.1 Simulation flowchart - 19 - 3.2 System configuration - 20 - 3.3 System matrix calculation - 22 - 3.3.1 Ray tracing - 22 - 3.3.2 System symmetry - 23 - 3.4 Data generation - 26 - 3.4.1 Training data generation - 26 - 3.4.2 Mouse whole body (MOBY) source - 29 - 3.5 Image quality and mask - 34 - 3.6 Projection - 35 - 3.7 ISTA-Net - 37 - 3.7.1 ISTA-Net structure - 37 - 3.7.2 Training loss function - 41 - 3.7.3 Training strategy - 42 - CHAPTER 4 Results - 46 - 4.1 Test data - 46 - 4.2 System matrix comparison - 49 - 4.3 Algorithm performance - 51 - 4.3.1 Derenzo - 54 - 4.4 Epoch performance comparison - 56 - 4.4.1 Loss profile - 56 - 4.4.2 Epoch performance - 57 - 4.5 MOBY testing - 62 - 4.5.1 MOBY mouse central slice sources test - 62 - 4.5.2 MOBY mouse phantom test - 69 - CHAPTER 5 Conclusions - 76 - Future work - 77 - Reference - 78 - Appendix - 80 - List of symbols - 80 - | |
dc.language.iso | en | |
dc.title | 卷積神經網路於正子斷層掃描影像重建之應用 | zh_TW |
dc.title | Application of Convolutional Neural Networks in the Optimization of PET Image Reconstruction | en |
dc.type | Thesis | |
dc.date.schoolyear | 108-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 尼普迪(Mythra-Varun Nemallapudi),林志勳(Chih-Hsun Lin), 蕭穎聰 (Ing-Tsung Hsiao) | |
dc.subject.keyword | 正子斷層掃描,深度學習,壓縮感知, | zh_TW |
dc.subject.keyword | PET,Deep Learning,Compressive sensing, | en |
dc.relation.page | 82 | |
dc.identifier.doi | 10.6342/NTU202003975 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2020-08-20 | |
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 | |
---|---|---|---|
U0001-1808202014440100.pdf 目前未授權公開取用 | 1.97 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。