https://scholars.lib.ntu.edu.tw/handle/123456789/149024
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor | 朱樹勳 | en |
dc.contributor | 郭德盛 | en |
dc.contributor | 臺灣大學: | zh_TW |
dc.contributor.author | 蕭聿謙 | zh |
dc.contributor.author | Shiau, Yu-Chien | en |
dc.creator | 蕭聿謙 | zh |
dc.creator | Shiau, Yu-Chien | en |
dc.date | 2004 | en |
dc.date.accessioned | 2007-11-26T06:34:03Z | - |
dc.date.accessioned | 2018-07-06T10:11:37Z | - |
dc.date.available | 2007-11-26T06:34:03Z | - |
dc.date.available | 2018-07-06T10:11:37Z | - |
dc.date.issued | 2004 | - |
dc.identifier | en-US | en |
dc.identifier.uri | http://ntur.lib.ntu.edu.tw//handle/246246/53333 | - |
dc.description.abstract | 動態心臟影像的運動弁鄐尷R對於心臟病的診斷與病情的評估是非常重要的。由於影像處理技術的進步,目前已有多種方法可提供動態影像運動分析的弁遄A其中,應用類神經網路於醫學影像處理為近年來的新發展領域,值得深入研究。 本論文提出新的方法,應用逆傳導神經網路分析多種動態心臟影像,包括:心導管心室攝影 (catheterization ventriculography)、核醫心肌灌注門控單光子斷層掃描 (myocardial perfusion gated single photon emission computed tomography, GSPECT)、核醫血池門控單光子斷層掃描 (blood-pool GSPECT)、與核醫心室攝影 (radionuclide ventriculography)等,以提供動態心臟影像的運動弁鄐尷R。針對各項動態心臟影像,設計合適的假體模擬影像以訓練逆傳導神經網路,當誤差函數呈現收斂,神經網路訓練完成之後,該神經網路即可用於動態心臟影像之運動偵測與分析,心臟各部分之運動方向,以運動向量場與都卜勒顏色法顯示。並由專科醫師判讀原始動態心臟影像、運動向量場、與都卜勒顏色法顯示影像,以「接收者操作特性 (receiver operating characteristic)曲線分析」比較統計差異。 統計結果顯示,以運動向量場、都卜勒顏色法影像評估心臟運動弁遄A與原始動態心臟影像之影像判讀無顯著差異。以逆傳導神經網路分析所得之運動向量場與都卜勒顏色法影像,較不受雜訊干擾,可呈現客觀的判讀資訊,提供醫師作為心臟病的診斷、病情評估、與治療追蹤的參考工具。 逆傳導神經網路用於分析多種動態心臟影像,所得到的運動向量場與都卜勒顏色法影像是有用的,並且逆傳導神經網路具有潛力可供應用於其他心臟動態影像分析,以及其他醫學影像分析,提供豐富的資訊與臨床應用。 | zh_TW |
dc.description.abstract | Cardiac motion analysis is very important for the clinical diagnosis and disease evaluation of heart disease. There have been several image processing techniques for motion detection and motion analysis. Among those techniques, artificial neural network has been an important new approach in recent years. We propose a new approach and a novel algorithm, which uses a three-layer backpropagation neural network for cardiac motion analysis of catheterization ventriculography, myocardial perfusion gated single photon emission computed tomography (GSPECT), blood-pool GSPECT, and radionuclide ventriculography. The backpropagation neural network is trained by phantom images or sample images, which simulate different kinds of dynamic cardiac images. After the training is completed, the neural network can perform motion detection on patients’ dynamic cardiac images. The results of motion detection are displayed in the formats of motion vector fields and Doppler color display, which are superimposed on the original cardiac images. The physician specialists interpret cardiac wall motion on patients’ original images, motion vector fields, and Doppler color display. Receiver operating characteristic (ROC) curve analysis is used to test the statistical differences among the accuracy of the image interpretations. There is no significant statistical differences among the areas under ROC curves for the image interpretations made on original dynamic cardiac images, motion vector fields, and Doppler color displays. Cardiac wall motion detection and analysis by backpropagation neural network is useful for dynamic cardiac images. It is highly suggestive that the algorithm can be also useful for cardiac cine MRI, cardiac multidetector CT, and cardiac ultrasonography. | en |
dc.description.tableofcontents | Chapter 1 Introduction 1-1 Motivation and purpose ……………………………………………………. 1 1-2 Dynamic cardiac images …………………………………………………… 3 1-3 Artificial neural network…………………………………………………… 3 1-4 Receiver operating characteristic curve analysis…………………………… 5 1-5 Literature Review ………………………………………………………..… 7 1-6 Organization of the thesis …………………...………..………….………… 8 Chapter 2 Methods 2-1 Backpropagation neural network …………………………………………..10 2-1-1 Structure of backpropagation neural network 2-1-2 Learning and testing of the neural network 2-2 Pre-processing and filters ………………………………………………… 18 2-3 Motion vector fields and Doppler color display……………………………19 Chapter 3 Catheterization ventriculography 3-1 Catheterization ventriculography …………………………………………..21 3-2 Learning and testing of phantom images …………………………………..23 3-2-1 Learning by phantom images 3-2-2 Testing by phantom images 3-3 Motion analysis of the clinical images ……………………………………..29 3-3-1 Motion analysis of the clinical images 3-3-2 Results of motion analysis 3-3-3 Receiver operating characteristic curve analysis Chapter 4 Myocardial perfusion GSPECT 4-1 Myocardial perfusion GSPECT ………………………………..…………..39 4-2 Learning and testing of phantom images ……………………………….….41 4-2-1 Learning by phantom images 4-2-2 Testing by phantom images 4-3 Motion analysis of the clinical images ………………………………….….49 4-3-1 Motion analysis of the clinical images 4-3-2 Results of motion analysis 4-3-3 Receiver operating characteristic curve analysis Chapter 5 Blood-pool GSPECT 5-1 Blood-pool GSPECT …………………………………………..…………...69 5-2 Learning and testing of phantom images..……………………………….….70 5-2-1 Learning by phantom images 5-2-2 Testing by phantom images 5-3 Motion analysis of the clinical images ………………………………….….76 5-3-1 Motion analysis of the clinical images 5-3-2 Results of motion analysis 5-3-3 Receiver operating characteristic curve analysis Chapter 6 Discussion 6-1 Advantages of backpropagation neural network..……………………….… 86 6-2 Comparison with other methods..…………………………….………….…86 6-3 Techniques for backpropagation neural network..……………………….…91 6-4 Error source and programming techniques………………….………………93 6-5 Feasibility of backpropagation neural network……………….……………. 94 6-6 Clinical applications of artificial neural network……………….………….. 94 Chapter 7 Conclusions and future work 7-1 Conclusions..………………………………………………….………….…97 7-2 Main achievements of this thesis…………………………….………….…. 98 7-3 Future work….……………………………………………….………….…. 99 References..……………………………………………….………….…100 Appendix – List of program names……………………….………….…106 | en |
dc.language | en-US | en |
dc.language.iso | en_US | - |
dc.subject | 心臟影像 | en |
dc.subject | 類神經網路 | en |
dc.subject | 運動分析 | en |
dc.subject | neural network | en |
dc.subject | heart image | en |
dc.subject | motion analysis | en |
dc.title | 類神經網路在心導管心室攝影與單光子斷層掃描之分析與臨床應用 | zh |
dc.title | Analysis and Clinical Applications of Backpropagation Neural Network in Catheterization Ventriculography and GSPECT | en |
dc.type | thesis | en |
dc.relation.reference | [1] R.D. White and R.M. Setser, “Integrated approach to evaluating coronary artery disease and ischemic heart disease”, American Journal of Cardiology, vol. 90 (10C), 2002, pp. 49L-55L. [2] Tekalp, A.M., Digital video processing, Prentice Hall, Upper Saddle River, NJ, 1995. [3] Shapiro, L.G. and Stockman, G.C., Computer Vision, Prentice Hall, Upper Saddle River, NJ, 2001. [4] E. Atsumi, M. Takagi, and K. Yokosawa, “Local motion detection by hierarchical neural network”, Systems and Computers in Japan, vol. 25, No. 11, 1994, pp. 24-35. [5] T. Roska, T. Boros, A. Radvanyi, P. Thiran, and L.O. Chua, “Detecting moving and standing objects using cellular neural networks”, International Journal of circuit theory and applications, vol. 20, 1992, pp. 613-628. [6] T. Nakata, R. Noda, T. Takahashi, and H. Murakami, “Radionuclide ventriculography and gated blood-pool SPECT in coronary artery disease,” Japanese Journal of Clinical Medicine, vol. 61, Suppl 4, pp. 342-346, 2003. [7] J.P. Ioannidis, T.A. Trikalinos, P.G. Danias, “Electro-cardiogram-gated single-photon emission computed tomography versus cardiac magnetic resonance imaging for the assessment of left ventricular volumes and ejection fraction: a meta-analysis,” Journal of the American College of Cardiology, vol. 39, pp. 2059-2068, 2002. [8] Chester, M., Neural Networks – A Tutorial, PTR Prentice Hall, Englewood Cliffs, HJ, 1993. [9] 葉怡成,類神經網路模式應用與實作,儒林圖書有限公司,台北,2002. [10] C.E. Metz, “ROC methodology in radiologic imaging,” Invest Radiology 21:720-733, 1986. [11] C.E. Metz, “Some practical issues of experimental design and data analysis in radiological ROC studies,” Invest Radiology 24:234-245, 1989. [12] A.D. Bimbo, P. Nesi, and J.L.C. Sanz, “Optical flow computation using extended constraints”, IEEE Transactions on Image Processing, 5, 1996, pp. 720-739. [13] S.C. Amartur, and H.J. Vesselle, “A new approach to study cardiac motion: the optical flow of cine MR images,” Magnetic Resonance in Medicine, Vol. 29, No. 1:59-67, 1993. [14] G. Convertino, E. Stella, A. Branca, and A. Distante, “Optic flow estimation by a Hopfield neural network using geometrical constraints,” Machine Vision and Applications, 10, pp. 114-122, 1997. [15] S.S. Skrzypkowiak and V.K. Jain, “Affine motion estimation using a neural network,” Proceedings – IEEE International Conference on Image Processing, 1, pp. 418-421, 1995. [16] S.S. Skrzypkowiak and V.K. Jain, “Video motion estimation using a neural network,” Proceedings – IEEE International Symposium on Circuit and Systems, 3, pp. 217-220, 1994. [17] T. Chen, W.C. Lin, and C.T. Chen, “Artificial neural network for 3-D motion analysis- Part I: Rigid motion,” IEEE Transactions on Neural Networks, vol. 6, No. 6, pp. 1386-1393, 1995. [18] T. Chen, W.C. Lin, and C.T. Chen, “Artificial neural network for 3-D motion analysis- Part I: Nonrigid motion,” IEEE Transactions on Neural Networks, vol. 6, No. 6, pp. 1394-1401, 1995. [19] C. Wohler and J.K. Anlauf, “A time delay neural network algorithm for estimating image-pattern shape and motion,” Image and Vision Computing, 17, pp. 281-294, 1999. [20] T. Chen, “Fuzzy neural network applications in medicine,” IEEE International Conference on Fuzzy Systems, v 2, International Joint Conference on the 4th IEEE International Conference on Fuzzy Systems and the 2nd International Fuzzy Engineering Symposium, 1995, pp. 627-634. [21] T. Kobayashi, M. Yagyu, and K. Shirai, “Application of neural networks to articulatory motion estimation,” Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, v 1, 1991, pp. 489-492. [22] K. Chida, T. Tanaka, H. Saito, M. Zuguchi, A. Ozawa, S. Watanabe, K. Sato, and M. Kohzuki, “Ventriculography using ECG-gated multiple diastolic injection of contrast material in pediatric angiocardiography,” Pediatric Cardiology, 23(2), 2002, pp. 200-204. [23] C.A. Kaiser, S.I. Yoon, C.E. Zaugg, N. Jander, P.T. Buser, and M.E. Pfisterer, “Accuracy of biplane analysis of left ventricular ejection fraction based on two consecutive single plane studies,” Journal of Invasive Cardiology, 12(11), 2000, pp. 566-70. [24] A. Heusch, J.A. Koch, O.N. Krogmann, B. Korbmacher, and M. Bourgeois, “Volumetric analysis of the right and left ventricle in a porcine heart model: comparison of three-dimensional echocardiography, magnetic resonance imaging and angiocardiography,” European Journal of Ultrasound, 9(3), 1999, pp. 245-255. [25] N. Kubo, M. Mabuchi, C. Katoh, H. Arai, K. Morita, E. Tsukamoto, Y. Morita, and N. Tamaki, “Validation of left ventricular function from gated single photon computed emission tomography by using a scintillator-photodiode camera: a dynamic myocardial phantom study,” Nuclear Medicine Communications, 23(7), 2002, pp. 639-643. [26] M.W. Groch, D.J. Schippers, R.C. Marshall, P.J. Groch, and W.D. Erwin, “Quantitative gated blood pool SPECT: analysis of 3-dimensional models for the assessment of regional myocardial wall motion,” Journal of Nuclear Cardiology, 9(3), 2002, pp. 271-284. [27] E. Vallejo, H. Chaya, G. Plancarte, D. Victoria, and D. Bialostozky, “Variability of serial same-day left ventricular ejection fraction using quantitative gated SPECT,” Journal of Nuclear Cardiology, 9(4), 2002, 377-384. [28] D. Le Guludec, H. Gauthier, R. Porcher, R. Frank, D. Daou, S. Benelhadj, A. Leenhardt, T. Lavergne, M. Faraggi, and M.S. Slama, “Prognostic value of radionuclide angiography in patients with right ventricular arrhythmias,” Circulation, 103(15), 2001, pp. 1972-1976. [29] A.D. Kelion, A.P. Banning, M.A. Gardner, and O.J. Ormerod, “Exercise equilibrium radionuclide angiography predicts long-term cardiac prognosis in patients with abdominal aortic aneurysm being considered for surgery,” Journal of Nuclear Cardiology, 7(3) 4, 2000, pp. 249-255. [30] B.W. Eidem, “Measuring the MPI in adults with a previous myocardial infarction and comparing this index value to the EF obtained with radionuclide angiography,” Journal of the American Society of Echocardiography, 13(9), 2000, pp. 882-883. [31] Mettler, F.A., Essentials of nuclear medicine imaging, Grune & Stratton, Inc., Orlando, FL, 1986, pp. 141-149. [32] Y.C. Shiau, H.H. Chou, S.H. Chu, and T.S. Kuo, “Cardiac wall motion detection by neural network analysis on Tc-99m MIBI myocardial perfusion gated single photon emission computed tomography”, Proc. IEEE EMBS Asian-Pacific Conf. on Biomedical Engineering 2003, Kyoto, Japan, 2003, p. 13. [33] Y.C. Shiau, H.H. Chou, S.H. Chu, and T.S. Kuo, “Using back propagation neural network for cardiac wall motion detection on angiocardiography,” Proc. the 17th IEEE Symposium on Computer-based Medical Systems 2004, Bethesda, MD, U.S.A., 2004, pp. 210-215. [34] F. Behloul, B.P. Lelieveldt, A. Boudraa, M.F. Janier, D. Revel, and J.H. Reiber, “Neuro-fuzzy systems for computer-aided myocardial viability assessment,” IEEE Transactions on Medical Imaging, 20(12), 2001, pp. 1302-1313. [35] A.F. Rodriguez, W.E. Blass, J.H. Missimer, and K.L. Leenders, “Artificial neural network Radon inversion for image reconstruction,” Medical Physics, 28(4), 2001, pp. 508-514. [36] J.S. Lee, D.S. Lee, S.K. Kim, S.K. Lee, J.K. Chung, M.C. Lee, and K.S. Park, “Localization of epileptogenic zones in F-18 FDG brain PET of patients with temporal lobe epilepsy using artificial neural network,” IEEE Transactions on Medical Imaging, 19(4), 2000, pp. 347-355. [37] A.P. Zijdenbos, B.M. Dawant, and R.A. Margolin, “Automatic detection of intracranial contours in MR images,” Computerized Medical Imaging & Graphics, 18(1), 1994, pp. 11-23. [38] G. Porenta, G. Dorffner, S. Kundrat, P. Petta, J. Duit-Schedlmayer, and H. Sochor, “Automated interpretation of planar thallium-201-dipyridamole stress-redistribution scintigrams using artificial neural networks,” Journal of Nuclear Medicine, 35(12), 1994, pp. 2041-2047. [39] J.S. Kippenhan, W.W. Barker, J. Nagel, C. Grady, and R. Duara, “Neural-network classification of normal and Alzheimer's disease subjects using high-resolution and low-resolution PET cameras,” Journal of Nuclear Medicine, 35(1), 1994, pp. 7-15. [40] Y.C. Shiau, S.C. Tsai, J.J. Wang, S.T. Ho, and A. Kao, “Detecting parathyroid adenoma using technetium-99m tetrofosmin: comparison with P-glycoprotein and multidrug resistance related protein expression,” Nuclear Medicine and Biology, 29, 2002, pp. 339-344. [41] Y.C. Shiau, S.C. Tsai, Y.J. Ho, and C.H. Kao, “Comparison of Technetium-99m Methoxyisobutylisonitrile Single Photon Emission Computed Tomography and Computed Tomography to Detect Recurrent or Residual Nasopharyngeal Carcinomas after Radiotherapy,” Anticancer Research, 21, 2001, pp. 2213-2218. [42] Y.C. Shiau, S.C. Tsai, J.J. Wang, Y.J. Ho, S.T. Ho, and C.H. Kao, “Predicting chemotherapy response and comparing with P-glycoprotein expression using technetium-99m tetrofosmin scan in untreated malignant lymphomas,” Cancer Letters, 170, 2001, pp. 139-146. [43] Y.C. Shiau, S.C. Tsai, J.J. Wang, Y.J. Ho, S.T. Ho, C.H. Kao, “To predict chemotherapy response using technetium-99m tetrofosmin and compare with p-glycoprotein and multidrug resistance related protein-1 expression in patients with untreated small cell cancer,” Cancer Letters, 169, 2001, pp. 181-188. [44] Pratt, W.K., Digital image processing, John Wiley & Sons, Inc., New York, NY, 1991. [45] S. Uras, F. Girosi, A. Verri, and V. Torre, “A computational approach to motion perception,” Biological Cybernetics, vol. 60, 1988, pp. 79-87. [46] Hirahara, M. and Nagano, T. (1993): ‘A neural network model for visual motion detection that can explain psychophysical and neurophysiological phenomena’, Biological Cybernetics, vol. 68, pp. 247-252. [47] Lehky, S. R. and Sejnowski, T. J. (1988): ‘Network model of shape-from-shading: neural function aries from both receptive and projective fields’, Nature, vol. 333, pp. 452-454. | zh_TW |
item.openairecristype | http://purl.org/coar/resource_type/c_46ec | - |
item.fulltext | no fulltext | - |
item.cerifentitytype | Publications | - |
item.languageiso639-1 | en_US | - |
item.openairetype | thesis | - |
item.grantfulltext | none | - |
顯示於: | 電機工程學系 |
在 IR 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。