跳到主要內容

臺灣博碩士論文加值系統

(3.236.110.106) 您好!臺灣時間:2021/07/26 00:32
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

我願授權國圖
: 
twitterline
研究生:蘇冠豪
研究生(外文):Kuan-Hao Su
論文名稱:應用類神經網路及整體學習獨立成分分析法提升小動物正子斷層影像之定量準確性
論文名稱(外文):A Novel Method to Improve Quantitative Accuracy for small animal PET using Artificial Neural Networks and Ensemble Learning Independent Component Analysis
指導教授:陳志成陳志成引用關係
指導教授(外文):Jyh-Cheng Chen
學位類別:博士
校院名稱:國立陽明大學
系所名稱:生物醫學影像暨放射科學系暨研究所
學門:醫藥衛生學門
學類:醫學技術及檢驗學類
論文種類:學術論文
論文出版年:2009
畢業學年度:97
語文別:英文
論文頁數:134
中文關鍵詞:正子斷層影像類神經網路獨立成分分析法
外文關鍵詞:PETartificial neural networkindepedent component analysis
相關次數:
  • 被引用被引用:0
  • 點閱點閱:157
  • 評分評分:
  • 下載下載:0
  • 收藏至我的研究室書目清單書目收藏:0
本論文主要的目的在提升小動物正子斷層影像 (positron emission tomography, PET) 中定量數據的準確性,以使得未來PET定量分析之結果更趨可靠,以達成能增進PET對疾病診斷及病程判讀正確率之目標。在提升影像數據準確性的問題中,本論文以空間及時間域的兩個方面分別提出精進的辦法。在空間域的部分,主要方法是透過類神經網路 (artificial neural network, ANN) 來修正原始的系統反應矩陣 (system matrix, SM),以提升統計式疊代演算法所得的PET影像品質。其中,用以訓練 ANN 的資料,是使用高解析光學掃描儀掃描物理假體,以取得ANN的輸入資料,並將該假體經由PET得其系統的真實輸出並訓練之。完成訓練後,修正後的SM即可用來做影像重建,並比較結果。由結果可知,經修正後的SM所重建的影像,比其它臨床上所用方法能產生更高解析度且準確的結果。另一方面,在時間域的研究上,使用了整體學習獨立成分分析法 (ensemble learning independent component analysis, EL-ICA) 來從PET影像中直接估算出較準確的輸入函數,並以最不侵入的方式,提升PET 定量分析的準確性。EL-ICA 被用來解算本論文所提出的部分體積模式,以自含有部分體積效應的時間活性曲線中解出正確的輸入函數。在EL-ICA的理論中,原始訊號的事後機率可在空間混合比重未知的情形下由混合訊號中估算出。因此,EL-ICA方法可用來解算本研究中所提出的部分體積模式,並求出輸入函數。在本研究中,使用了另一種獨立成分分析法──FastICA──來進一步與EL-ICA 結果比較。根據結果顯示,以EL-ICA方法確實可以降低周邊組織所造成的部分體積效應,並且也明顯的比直接從影像圈選感興趣區域(region-of-interest)或 FastICA方法有更穩定且準確的結果。如此,透過本論文所提的方法,則能夠真正能使精確且正確的小動物PET定量分析進一步落實,並增廣未來PET臨床應用之價值與範疇。
The aim of this dissertation was to improve the accuracy of PET quantification in both spatial and temporal domain. In spatial domain, the image quality of statistical reconstruction was improved using a system matrix (SM) trained with artificial neural network (ANN). For training the ANN SM, input and desired output pairs were generated. The inputs, the digital images, were generated by scanning a physical phantom using an optical scanner. Furthermore, the desired outputs were generated by acquiring the projection data with the corresponding angles using the microPET R4. After training, the ANN modified SM can be used for image reconstruction. The image quality reconstructed by the ANN SM was better than that reconstructed by the original SM. The results suggested that SM can be updated toward ideal SM using ANN for statistical reconstruction. On the other hand, an ensemble learning independent component analysis (EL-ICA) approach was proposed to improve the accuracy of image-derived input function for PET quantification in temporal domain. The EL-ICA was designed to resolve the latent input function from TACs acquired from multi-tissue model. In the EL-ICA algorithm, the posterior distribution of the possible sources can be estimated without knowing the mixing matrix. Therefore, the method can be used to solve the multi-tissue partial volume model proposed in this dissertation. Input functions estimated by FastICA method were also used for comparison. The results showed that the proposed EL-ICA method can reduce the PVE in all cases and improve the quantitative accuracy of PET studies.
CONTENTS

Table of contents…………………………………………...……………………….. I
List of figures……………………..………………………………………………....V
List of tables………………..…………………………………………..………...…VII
Abstract………………………………………………….…………………………VIII

Chapter 1 Introduction 1
1.1 Background and significance of PET research 1
1.2 Motivation 2
1.3 Review of improvements in image quality in nuclear medicine 2
1.3.1 Partial volume correction for static image 2
1.3.2 Partial volume correction for dynamic images 5
1.4 Objective of this dissertation 10
1.5 Contribution of the dissertation work 10
1.6 Organization of this dissertation 11
Chapter 2 Theory 12
2.1 Artificial neural networks (ANN) 12
2.2 A forward projector for image reconstruction 17
2.3 Theory of Monte Carlo simulation 18
2.4 Independent component analysis (ICA) 20
2.4.1 Ensemble learning algorithm for ICA (EL-ICA) 23
Chapter 3 Materials and Methods 29
3.1 ANN method for improving image quality 29
3.1.1 Statistical image reconstruction 29
3.1.2 Artificial neural network for correcting SM 30
3.1.3 ANN training 32
3.1.3.1 Generating inputs for ANN training 32
3.1.3.2 Generating desired output for training 34
3.1.3.3 Pre-registration of input-output pairs 35
3.1.3.4 The parameters for training the network 36
3.1.4 Monte Carlo Simulation for generating SM 38
3.2 The materials to evaluate the ANN corrected SM 44
3.2.1 Simulation experiments for ANN training and evaluation 44
3.2.2 Phantom experiments for ANN training and evaluation 46
3.2.3 Real rat experiments for testing the ANN 47
3.2.4 The microPET scanner 49
3.3 EL-ICA method for reducing partial volume effect 50
3.3.1 Partial volume models 50
3.3.2 Partial volume correction using temporal EL-ICA 53
3.4 FastICA estimated input function 55
3.5 The materials for evaluating the PVC input function 56
3.5.1 Digital dynamic rat cardiac phantom 56
3.5.1.1 The convoluted cardiac phantom 58
3.5.1.2 The reconstructed cardiac phantom 59
3.5.2 Real rat experiments for EL-ICA method 60
3.5.3 The steps of input function estimation using EL-ICA and FastICA 61
3.5.4 Evaluations for the EL-ICA corrected input function 63
Chapter 4 Results 65
4.5 Results of the ANN method 65
4.5.1 The results of the simulation study 66
4.5.2 The results of the multi-line source and Mini-Deluxe phantom 68
4.5.3 The results of four-segment phantom 73
4.5.4 The results of the real rat study 73
4.5.5 The results of computation cost of the ANN approach 75
4.6 The results of partial volume correction using EL-ICA 75
4.6.1 The results of the convoluted cardiac phantom 75
4.6.2 The results of the reconstructed cardiac phantom 81
4.6.3 The results of the real rat experiments 82
Chapter 5 Discussion 85
5.1 In the results of the ANN approach 85
5.1.1 In the results of the simulation experiments 85
5.1.2 In the results of the phantom experiments 87
5.1.2.1 In the results of multi-line source phantom 87
5.1.2.2 In the results of the four-segment phantom 89
5.1.2.3 In the results of the Mini-Deluxe cold spot PhantomTM 91
5.1.2.4 In the results of the real rat experiments 93
5.2 General discussion on the ANN approach 93
5.2.1 The model errors of the ANN corrected SM 93
5.2.2 Inherent property of the SM symmetry 95
5.3 In the results of the EL-ICA approach 96
5.3.1 In the results of the simulation experiments 96
5.3.1.1 In the results of the convolution cardiac phantom 97
5.3.1.2 In the results of the reconstructed cardiac phantom 99
5.3.2 In the results of the real rat experiments 100
Chapter 6 Conclusions and Future work 103
6.1 Conclusions 103
6.2 Future works 105
6.2.1 Simplified the ANN training by SM decomposition 106
6.2.2 The possibility for ANN training in a 3D SM case 106
6.2.3 The possibility of combining the ANN and EL-ICA approaches 109
References ……...………..………………………………………………………...117
Appendix Publication list ……………..……………………………………....119
[1] H. W. Muller-Gartner, J. M. Links, J. L. Prince, R. N. Bryan, E. McVeigh, J. P. Leal, C. Davatzikos, and J. J. Frost, "Measurement of radiotracer concentration in brain gray matter using positron emission tomography: MRI-based correction for partial volume effects," Journal of Cerebral Blood Flow & Metabolism, vol. 12, no. 4, pp. 571-583, 1992.
[2] J. Yang, S. C. Huang, M. Mega, K. P. Lin, A. W. Toga, G. W. Small, and M. E. Phelps, "Investigation of partial volume correction methods for brain FDG PET studies," IEEE Trans Nucl Sci, vol. 43, no. 6, pp. 3322-3327, Dec.1996.
[3] C.H.Chen, R.F.Muzic, A.D.Nelson, and L.P.Adler, "A nonlinear spatially variant object-dependent system model for prediction of partial volume effects and scatter in PET," IEEE Trans Medical imageing, vol. 17, no. 2, pp. 214-227, Apr.1998.
[4] A.J.Rockmore and A.Macovski, "A Maximum Likelihood Approach to Emission Image Reconstruction from Projection," IEEE Trans Nucl Sci, vol. 23, pp. 1428-1432, 1976.
[5] V. Y. Panin, F. Kehren, C. Michel, and M. Casey, "Fully 3-D PET reconstruction with system matrix derived from point source measurements," IEEE Trans Med. Imaging, vol. 25, no. 7, pp. 907-921, July2006.
[6] Roberto D.L.Prieta, "An Accurate and Parallelizable Geometric Projector/Backprojector for 3D PET Image Reconstruction," Lect Notes Comput Sci, vol. 3337, pp. 27-38, 2004.
[7] E.N.Gimenez, E.Nacher, M.Gimenez, J.M.Benlloch, and M.Rafecas, "Comparison of different approaches based on Monte Carlo methods to calculate the system matrix for small animal PET," Nucl Instrum Methods Phys Res A, vol. 569, pp. 346-349, Sept.2006.
[8] C. Lartizien, C. Kuntner, A. L. Goertzen, A. C. Evans, and A. Reilhac, "Validation of PET-SORTEO Monte Carlo simulations for the geometries of the MicroPET R4 and Focus 220 PET scanners," Phys Med. Biol., vol. 52, no. 16, pp. 4845-4862, Aug.2007.
[9] S. Vandenberghe, S. Staelens, C. L. Byrne, E. J. Soares, I. Lemahieu, and S. J. Glick, "Reconstruction of 2D PET data with Monte Carlo generated system matrix for generalized natural pixels," Phys Med. Biol., vol. 51, no. 12, pp. 3105-3125, June2006.
[10] C.E.Floyd, "An Artificial Neural Network for SPECT Image Reconstruction," IEEE Trans Medical Imaging, vol. 10, no. 3, pp. 485-487, Sept.1991.
[11] M.T.Munley, C.E.Floyd, J.E.Bowsher, and R.E.Coleman, "A spatially-variant SPECT reconstruction scheme using artificial neural networks," Conference Record of the 1992 IEEE Nuclear Science Symposium and Medical Imaging Conference, vol. 2, pp. 1279-1281, Oct.1992.
[12] C.E.Floyd, J.E.Bowsher, M.T.Munley, G.D.Tourassi, S.Garg, A.H.Baydush, J.Y.Lo, and R.E.Coleman, "Artificial neural networks for SPECT image reconstruction with optimized weighted backprojection," Conference Record of the 1991 IEEE Nuclear Science Symposium and Medical Imaging Conference, vol. 3, pp. 2184-2188, Nov.1991.
[13] P.Paschalis, N.D.Giokaris, A.Karabarbounis, G.K.Loudos, D.Maintas, C.N.Papanicolas, V.Spanoudaki, Ch.Tsoumpas, and E.Stiliaris, "Tomographic image reconstruction using Artificial Neural Networks," Nucl Instrum Methods Phys Res A, vol. 527, pp. 211-215, 2004.
[14] A. F. Rodriguez, W. E. Blass, J. H. Missimer, and K. L. Leenders, "Artificial neural network Radon inversion for image reconstruction," Med. Phys, vol. 28, no. 4, pp. 508-514, Apr.2001.
[15] S.S.Gopal and T.J.Hebert, "Pre-reconstruction restoration of SPECT projection images by a neural network," IEEE Trans Nucl Sci, vol. 41, no. 4, pp. 1620-1625, Aug.1994.
[16] P. Knoll, S. Mirzaei, A. Mullner, T. Leitha, K. Koriska, H. Kohn, and M. Neumann, "An artificial neural net and error backpropagation to reconstruct single photon emission computerized tomography data," Med. Phys, vol. 26, no. 2, pp. 244-248, Feb.1999.
[17] Y.H.Chiu and S.F.Yau, "Training of artificial neural network for tomographic reconstruction of time varying object," IEEE International Symposium on Circuits and Systems, vol. 3, pp. 225-228, June1994.
[18] David A., Mankoff, Mark Muzi, Kenneth A., and Krohn, "Quantitative positron emission tomography imaging to measure tumor response to therapy: what is the best method?," Molecular Imaging and Biology, vol. 5, no. 5, pp. 281-285, 2003.
[19] M. A. Mejia, M. Itoh, H. Watabe, T. Fujiwara, and T. Nakamura, "Simplified nonlinearity correction of oxygen-15-water regional cerebral blood flow images without blood sampling.," J. Nucl. Med., vol. 35, no. 11, pp. 1870-1877, Nov.1994.
[20] H. Watabe, M. Itoh, M. Mejia, T. Fujiwara, T. Jones, and T. Nakamura, "Validation of noninvasive quantification of rCBF compared with dynamic/integral method by using positron emission tomography and oxygen-15 labeled water," Ann. Nucl. Med., vol. 9, no. 4, pp. 191-198, Nov.1995.
[21] D. Feng, S. Huang, and X. Wang, "Models for computer simulation studies of input functions for tracer kinetic modeling with positron emission tomography," Int J Biomed Comput, vol. 32, pp. 95-110, 1993.
[22] D. Feng, K. Wong, C. Wu, and W. Siu, "A technique for extracting physiological parameters and the required input function simultaneously from PET image measurements: theory and simulation study," IEEE Trans Inform Technol Biomed, vol. 1, pp. 243-254, 1997.
[23] K. Wong, D. Feng, S. Meikle, and M. Fulham, "Simultaneous estimation of physiological parameter and the input function—in vivo PET data," IEEE Trans Inform Technol Biomed, vol. 5, pp. 67-76, 2001.
[24] Y. H. Fang and R. F. Muzic, Jr., "Spillover and partial-volume correction for image-derived input functions for small-animal 18F-FDG PET studies," J Nucl Med, vol. 49, no. 4, pp. 606-614, Apr.2008.
[25] W. H. Wong and K. Hicks, "A clinically practical method to acquire parametric images of unidirectional metabolic rates and blood spaces," J. Nucl. Med., vol. 35, no. 7, pp. 1206-1212, July1994.
[26] M. A. Mejia, M. Itoh, H. Watabe, T. Fujiwara, and T. Nakamura, "Simplified nonlinearity correction of oxygen-15-water regional cerebral blood flow images without blood sampling.," J. Nucl. Med., vol. 35, no. 11, pp. 1870-1877, Nov.1994.
[27] A. P. van der Weerdt, L. J. Klein, R. Boellaard, C. A. Visser, F. C. Visser, and A. A. Lammertsma, "Image-derived input functions for determination of MRGlu in cardiac (18)F-FDG PET scans," Journal of Nuclear Medicine., vol. 42, no. 11, pp. 1622-1629, Nov.2001.
[28] H. Iida, C. G. Rhodes, R. de Silva, L. I. Araujo, P. M. Bloomfield, A. A. Lammertsma, and T. Jones, "Use of the left ventricular time-activity curve as a noninvasive input function in dynamic oxygen-15-water positron emission tomography," J. Nucl. Med., vol. 33, no. 9, pp. 1669-1677, Sept.1992.
[29] I. N. Weinberg, S. C. Huang, E. J. Hoffman, L. Araujo, C. Nienaber, M. Grover-McKay, M. Dahlbom, and H. Schelbert, "Validation of PET-acquired input functions for cardiac studies.," J. Nucl. Med., vol. 29, no. 2, pp. 241-247, Feb.1988.
[30] K. Chen, D. Bandy, E. Reiman, S. C. Huang, M. Lawson, D. Feng, L. S. Yun, and A. Palant, "Noninvasive quantification of the cerebral metabolic rate for glucose using positron emission tomography, 18F-fluoro-2-deoxyglucose, the Patlak method, and an image-derived input function," J. Cereb. Blood Flow Metab, vol. 18, no. 7, pp. 716-723, July1998.
[31] T.Schroeder, Marcos F.Vidal Melo, G.Musch, R.Scott Harris, Jose G.Venegas, and T.Winkler, "Image-Derived Input Function for Assessment of 18F-FDG Uptake by the Inflamed Lung," J Nucl Med, vol. 48, pp. 1889-1896, 2007.
[32] Y. Fang, T. Kao, R. Liu, and L. Wu, "Estimating the input function non-invasively for FDG-PET quantification with multiple linear regression analysis: simulation and verification with in vivo data," Eur J Nucl Med Mol Imaging, vol. 31, pp. 692-702, 2004.
[33] J. S. Lee, D. S. Lee, J. Y. Ahn, G. J. Cheon, S. K. Kim, J. S. Yeo, K. Seo, K. S. Park, J. K. Chung, and M. C. Lee, "Blind separation of cardiac components and extraction of input function from H(2)(15)O dynamic myocardial PET using independent component analysis," J. Nucl. Med., vol. 42, no. 6, pp. 938-943, June2001.
[34] J. Y. Ahn, D. S. Lee, J. S. Lee, S. K. Kim, G. J. Cheon, J. S. Yeo, S. A. Shin, J. K. Chung, and M. C. Lee, "Quantification of regional myocardial blood flow using dynamic H2(15)O PET and factor analysis," J. Nucl. Med., vol. 42, no. 5, pp. 782-787, May2001.
[35] M. Naganawa, Y. Imur, K. Shii, K. Da, K. Shiwata, and A. Atani, "Extraction of a Plasma Time-Activity Curve From Dynamic Brain PET Images Based on Independent Component Analysis," IEEE Trans Biomed Eng, vol. 52, no. 2, pp. 201-210, Feb.2005.
[36] J. Kim, P. Herrero, T. Sharp, R. Laforest, D. J. Rowland, Y. C. Tai, J. S. Lewis, and M. J. Welch, "Minimally Invasive Method of Determining Blood Input Function from PET Images in Rodents," J Nucl Med, vol. 47, no. 2, pp. 330-336, Feb.2006.
[37] M.Naganawa, Y.Kimura, T.Nariai, K.Ishii, K.i Oda, Y.Manabe, K.Chihara, and K.Ishiwatab, "Omission of serial arterial blood sampling in neuroreceptor imaging with independent component analysis," Neuroimage, vol. 26, pp. 885-890, 2005.
[38] Zheng Fu, Mohammed N.Tantawy, and Todd E.Peterson, "Ensemble Learning (EL) Independent Component Analysis (ICA) Approach to Derive Blood Input Function from FDG-PET Images in Small Animal," IEEE Nuclear Science Symposium Conference Record, pp. 2708-2712, 2006.
[39] F. Esposito, E. Formisano, E. Seifritz, R. Goebel, R. Morrone, G. Tedeschi, and S. F. Di, "Spatial independent component analysis of functional MRI time-series: to what extent do results depend on the algorithm used?," Hum Brain Mapp, vol. 16, no. 3, pp. 146-157, July2002.
[40] V.D.Calhoun, T.Adali, G.D.Pearlson, and J.J.Pekar, "Spatial and Temporal Independent Component Analysis of Functional MRI Data Containing a Pair of Task-Related Waveforms," Hum Brain Mapp, vol. 13, no. 43, p. 53, 2001.
[41] A.Hyvärinen, "Fast and Robust Fixed-Point Algorithms for Independent Component Analysis.," IEEE Transactions on Neural Networks, vol. 10, no. 3, pp. 626-634, 1999.
[42] A. J. Bell and T. J. Sejnowski, "An information–maximization approach to blind separation and blind deconvolution," Neural Comput, vol. 7, pp. 1004-1034, 1995.
[43] J.F.Cardoso, "High-order contrasts for independent component analysis. Neural Computation," Neural Comput, vol. 11, no. 1, pp. 157-192, 1999.
[44] J. A. Fessler, "Penalized weighted least-squares image reconstruction for positron emission tomography," IEEE Trans Med Imaging, vol. 13, no. 2, pp. 290-300, 1994.
[45] H.Hudson and R.Larkin, "Accelerated image reconstruction using ordered subsets of projection data," IEEE Trans Medical Imaging, vol. 13, no. 4, pp. 601-609, Dec.1994.
[46] E. Levitan and G. T. Herman, "A maximum a posteriori probability expectation maximization algorithm for image reconstruction in emission tomography," IEEE Trans Med Imaging, vol. 6, no. 3, pp. 185-192, 1987.
[47] A. Rahmim, J. Tang, M. A. Lodge, S. Lashkari, M. R. Ay, R. Lautamaki, B. M. Tsui, and F. M. Bengel, "Analytic system matrix resolution modeling in PET: an application to Rb-82 cardiac imaging," Phys Med Biol., vol. 53, no. 21, pp. 5947-5965, Nov.2008.
[48] J. L. Herraiz, S. Espana, J. J. Vaquero, M. Desco, and J. M. Udias, "FIRST: Fast Iterative Reconstruction Software for (PET) tomography," Phys Med Biol., vol. 51, no. 18, pp. 4547-4565, Sept.2006.
[49] M. Rafecas, G. Böning, B. J. Pichler, E. Lorenz, M. Schwaiger, and S. I. Ziegler, "Effect of Noise in the Probability Matrix Used for Statistical Reconstruction of PET Data," IEEE Trans Nucl Sci, vol. 25, no. 1, pp. 149-156, 2004.
[50] M. Rafecas, B. Mosler, M. Dietz, M. Pögl, A. Stamatakis, D. P. McElroy, and S. I. Ziegler, "Use of a Monte Carlo based probability matrix for 3D iterative reconstruction of MAD,PETII data," IEEE Trans Nucl Sci, vol. 51, no. 5, pp. 2597-2605, 2004.
[51] N. Rehfeld and M. Alber, "A parallelizable compression scheme for Monte Carlo scatter system matrices in PET image reconstruction," Phys Med Biol., vol. 52, no. 12, pp. 3421-3437, June2007.
[52] D. Lazaro, B. Z. El, V. Breton, D. Hill, and I. Buvat, "Fully 3D Monte Carlo reconstruction in SPECT: a feasibility study," Phys Med Biol., vol. 50, no. 16, pp. 3739-3754, Aug.2005.
[53] R. L. Morin, Monte Carlo simulation in the radiological sciences. United States: CRC Press Inc.,Boca Raton, FL, 1988.
[54] L. L. Carter and E. D. Cashwell, Particle Transport Simulation with the Monte Carlo Method U. S. Department of Energy, 1975.
[55] M. Matsumoto and T. Nishimura, "Mersenne Twister: A 623-Dimensionally Equidistributed Uniform Pseudorandom Number Generator," ACM Transactions on Modeling and Computer Simulation, vol. 8, no. 1, pp. 3-30, 1998.
[56] A. Hyvärinen, J. Karhunen, and E. Oja, Independent component analysis Wiley Interscience, 2001.
[57] K. H. Su, L. C. Wu, R. S. Liu, S. J. Wang, and J. C. Chen, "Quantification method in [F-18]fluorodeoxyglucose brain positron emission tomography using independent component analysis," Nuclear Medicine Communications, vol. 26, pp. 995-1004, 2005.
[58] J.W.Miskin, "Ensemble Learning for Independent Component Analysis (Thesis)." 2000.
[59] M.T.Hagan, H.B.Demuth, and M.Beale, Neural network design PWS Pub. Co., 1996.
[60] H.Zaidi and K.F.Koral, "Scatter modelling and compensation in emission tomography," Eur. J. Nucl. Med. Mol. Imaging, vol. 31, pp. 761-782, Mar.2004.
[61] C.C.Watson, "New, Faster, Image-Based Scatter Correction for 3D PET," IEEE Trans Nucl Sci, vol. 47, no. 4, pp. 1587-1594, Aug.2000.
[62] K.Sivakumar and U.B.Desai, "Image Restoration Using a Multilayer Perceptron with a Multilevel Sigmoidal Function," IEEE Trans Signal Process, vol. 41, no. 5, pp. 2018-2022, May1993.
[63] S.R.Cherry, J.A.Sorenson, and M.E.Phelps, "Positron Emission Tomography," in Physics in Nuclear Medicine, 3rd ed. Allan Ross, Ed. Philadelphia: Saunders/Elsevier Science, 2003.
[64] V.V.Selivanov, Y.Picard, J.Cadorette, and S.Rodrigue, "Detector Response Models for Statistical Iterative Image Reconstructionin High Resolution PET," IEEE Trans Nucl Sci, vol. 47, no. 3, pp. 1168-1175, June2000.
[65] J. Qi and R. M. Leahy, "Resolution and noise properties of MAP reconstruction for fully 3-D PET," IEEE Trans Med Imaging, vol. 19, no. 5, pp. 493-506, May2000.
[66] C. Knoess, S. Siegel, A. Smith, D. Newport, N. Richerzhagen, A. Winkeler, A. Jacobs, R. N. Goble, R. Graf, K. Wienhard, and W. D. Heiss, "Performance evaluation of the microPET R4 PET scanner for rodents," Eur. J Nucl Med. Mol. Imaging, vol. 30, no. 5, pp. 737-747, 2003.
[67] M. Naganawa, Y. Kimura, T. Nariai, K. Ishii, K. i. Oda, Y. Manabe, K. Chihara, and K. Ishiwatab, "Omission of serial arterial blood sampling in neuroreceptor imaging with independent component analysis," Neuroimage, vol. 26, pp. 885-890, Apr.2005.
[68] K. Chen, X. Chen, R. Renaut, G. E. Alexander, D. Bandy, H. Guo, and E. M. Reiman, "Characterization of the image-derived carotid artery input function using independent component analysis for the quantitation of [18F] fluorodeoxyglucose positron emission tomography images," Phys Med Biol., vol. 52, no. 23, pp. 7055-7071, Dec.2007.
[69] M. E. Phelps, S. C. Huang, E. J. Hoffman, C. Selin, L. Sokoloff, and D. E. Kuhl, "Tomographic measurement of local cerebral glucose metabolic rate in humans with (F-18)2-fluoro-2-deoxy-D-glucose: validation of method," Annals of Neurology, vol. 6, no. 5, pp. 371-388, Nov.1979.
[70] B.Weber, C.Burger, P.Biro, and A.Buck, "A femoral arteriovenous shunt facilitates arterial whole blood sampling in animals," Eur J Nucl Med, vol. 29, no. 319, p. 323, 2002.
[71] S. Eberl, A. R. Anayat, R. R. Fulton, P. K. Hooper, and M. J. Fulham, "Evaluation of two population-based input functions for quantitative neurological FDG PET studies," Eur. J. Nucl. Med., vol. 24, pp. 299-304, 1997.
[72] O. G. Rousset, Y. Ma, and A. C. Evans, "Correction for partial volume effects in PET: principle and validation," Journal of Nuclear Medicine, vol. 39, no. 5, pp. 904-911, 1998.
[73] E. Ű. Mumcuoğlu, R. Leahy, S. R. Cherry, and Z. Zhou, "Fast Gradient-Based Methods for Bayesian Reconstruction of Transmission and Emission PET Images," IEEE Trans Med Imaging, vol. 13, no. 4, pp. 687-701, Dec.1994.
[74] E. Ű. Mumcuoğlu, R. M. Leahy, and S. R. Cherry, "Bayesian reconstruction of PET images: methodology and performance analysis," Phys Med Biol., vol. 41, no. 9, pp. 1777-1807, Sept.1996.
[75] J. Qi, R. M. Leahy, S. R. Cherry, A. Chatziioannou, and T. H. Farquhar, "High-resolution 3D Bayesian image reconstruction using the microPET small-animal scanner," Phys Med Biol., vol. 43, no. 4, pp. 1001-1013, Apr.1998.
[76] D. Lazaro, B. Z. El, V. Breton, D. Hill, and I. Buvat, "Fully 3D Monte Carlo reconstruction in SPECT: a feasibility study," Phys Med Biol., vol. 50, no. 16, pp. 3739-3754, Aug.2005.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top