跳到主要內容

臺灣博碩士論文加值系統

(3.237.6.124) 您好!臺灣時間:2021/07/24 03:10
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:李宜修
研究生(外文):Yi-Hsiu Lee
論文名稱:改善多通道相位陣列線圈之腦部磁振造影像組織分類ICA+SVM績效之研究
論文名稱(外文):Improving Brain Tissue Classification ICA+SVM of MRI acquired with multiple-channel phase-array coil
指導教授:歐陽彥杰張建禕陳啟昌陳啟昌引用關係蔡志文蔡志文引用關係
學位類別:碩士
校院名稱:國立中興大學
系所名稱:電機工程學系所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
畢業學年度:96
語文別:英文
論文頁數:75
中文關鍵詞:非均一性獨立成分分析支援向量機
外文關鍵詞:InhomogeneityIndependent component analysis (ICA)Support vector machine (SVM)
相關次數:
  • 被引用被引用:0
  • 點閱點閱:200
  • 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
非均一性在MRI中是一個重要的現象,它會影響MRI的應用,使其在醫學上的研究因此受影響。而現在MR儀器中多使用多通道線圈,因為訊號的干擾使其非均一性現象將更加嚴重。在另一方面分類方法獨立成分分析+支援向量機也受到非均一性的因素,造成分類效果受到影響。所以本研究將針獨立成分分析+支援向量機搜尋最適合的非均一性修正方法,進而改善期分類效果。我們選取了三種修正非均一性的方法DWT、LEM-CS以及LEM-BS。而LEM-BS是所有這些方法中最適合ICA+SVM分類器的,此外我們將LEM-BS做修改,將其濾波器置換為Gaussian濾波器,進而獲得更好的結果。另外LEM-BS不單只執行單張影像,更可一次執行多張修正非均一性,其多張修正效果不亞於單張修正,有時更勝。最後LEM-BS無論在高解析度或低解析都有不錯的修正效果。
Since the multi-channel coil of magnetic resonance imaging (MRI) became a mainstream, methods to reduce inhomogeneity in MRI without using the body coil for additional scan have developed. The interference of signals made the appearance of MR image badly. As a result it serious affects the classifications for MR images. In this study we would find the most adaptable method to improve inhomogeneity for MRI and get improvement for brain tissue classification by using independent component analysis (ICA) and support vector machine (SVM) method under multiple-channel phase-array coil. We chose three inhomogeneity correction methods: discrete wavelet transform (DWT), local entropy minimize with B-spline (LEM-BS) and local entropy minimize with cubic spline (LEM-CS). In our experiment, these three methods were used as the pre-processing method before applying ICA + SVM to correct the inhomogeneity of MR image. Web site images are first applied in the experiment and the Tanimoto index was used to measure the performance for the three methods. Real phantom MR images were also applied in this experiment. The results show that the LEM-BS is the best choice. Instead of using the average filter for LEM-BS, we use Gaussian filter to get better classification result. The LEM-BS method can be applied not only in single slice but also in multiple slices and sometimes it shows better result.
Chapter 1. Introduction 9

Chapter 2. The Appearance of Inhomogeneity 10
2.1 Inhomogeneity 10
2.2 Multi Channel Coil 11
2.3 Classification ICA+SVM 11

Chapter 3. Methods of Inhomogeneity Correction 13
3.1 Discrete Wavelet Transform 13
3.2 Local Entropy Minimize with cubic spline 16
3.3 Local Entropy Minimize with B-spline 20

Chapter 4. Experiments and Results 26
4.1 Web Images Classification Experiments 26
4.1.1 Simulated Brain Database 26
4.1.2 Quantitative measurement 28
4.1.3 Web Site Brain Image Experiments 30
Experiments 1 – Inhomogeneity Correction 30
Experiments 2 – LEM-BS Edited With Gaussian Filter 49
Experiments 3 – LEM-BS In 3D 57
4.2 Real Image of Phantom Classification Experiments 63
Phantoms 63
Experiments 4 – Phantom 01 of Inhomogeneity Correction 63
Experiments 5 – Phantom 02 in 3D LEM-BS 69
Experiments 6 – Phantom 03 in 3D LEM-BS 73
Experiments 7 –Phantom 03 in LEM-BS correction in different dpi 76
Experiments 8 – LEM-BS in real head images 77

Chapter 5. Conclusions 82
Reference 83
[1] www.mr-tip.com/serv1.php?type=db1&dbs=Field%20Inhomogeneity%20Artifact
[2] Pruessmann KP, Weiger M, Scheidegger MB, Boesiger P SENSE: sensitivity encoding for fast MRI. (1999):
[3] Fa-Hsuan Lin 1 2 3 *, Ying-Jui Chen 4, John W. Belliveau 2 3, Lawrence L. Wald 2 3.A wavelet-based approximation of surface coil sensitivity profiles for correction of image intensity inhomogeneity and parallel imaging reconstruction, Human Brain Mapping 19:96–111(2003)
[4] Daubechies : Ten lectures on wavelets, Society for Industrial and Applied Mathematics, Philadelphia, PA. (1992):
[5] J. G. Sled and G. B. Pike, “Standing-wave and RF penetration artifacts caused by elliptic geometry: an electrodynamic analysis of MRI,” IEEE Trans. Med. Imag., vol. 17, no. 4, pp. 653–662, Aug. (1998).
[6] A. Simmons, P. S. Tofts, G. J. Barker, and S. R. Arridge, “Sources of intensity nonuniformity in spin-echo images at 1.5T,” Magn. Reson. Med., vol. 32, no. 1, pp. 121–128, (1994).
[7] Olivier Salvado, Claudia Hillenbrand, Shaoxiang Zhang, and David L. Wilson*, Member, IEEE, Method to Correct Intensity Inhomogeneity in MR Images for Atherosclerosis Characterization, ieee transactions on medicalimaging, vol. 25, no. 5, May (2006)
[8] P. Perona and J. Malik, “Scale-space and edge detection using anisotropic diffusion,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 12, no. 7, pp. 629–639, Jul. (1990)
[9] M. J. Black, G. Sapiro, D. H. Marimont, and D. Heeger, “Robust anisotropic diffusion,” IEEE Trans. Image Process., vol. 7, no. 3, pp. 421–432, Mar. 1998.
[10] O. Salvado, C.Hillenbrand, S. Zhang, J. S. Suri, and D. L.Wilson, “MR signal inhomogeneity correction for visual and computerized atherosclerosis lesion assessment,” Proceeding of 2004 IEEE International Symposium on Biomedical Imaging pp. 1143–1146,(2004).
[11] mathworld.wolfram.com/CubicSpline.html
[12] Axel, L., Constantini, J., Listerud, J.,. Intensity correction in surfacecoil MR imaging. Am. J. Roentgenol. 148, 418–420.(1987)
[13] Dawant, B., Zijdenbos, A., Margolin, R.,. Correction of intensity variations inMR images for computer-aided tissue classication. IEEE Trans. Med. Imaging 12 (4), 770–781.( 1993)


[14] Meyer, C., Bland, P., Pipe, J., Retrospective correction of intensity inhomogeneities in MRI. IEEE Trans. Med. Imaging 14 (1), 36–41.(1995)

[15] Wells III, W., Grimson, W., Kikinis, R., Jolesz, F., Adaptative segmentation of MRI data. IEEE Trans. Med. Imaging 15 (4), 429–442 (1996)
[16] Shannon, C., A mathematical theory of communication. Bell Syst. Tech. J. 27, 623–656.(1948)
[17] Likar, B., Maintz, J., Viergever, M., Pernus, F.,. Retrospective Shading correction based on entropy minimization. J.Microsc. 197 (3), 285–295.(2000)
[18] Likar, B., Viergever,M., Pernus, F., Retrospective correction of MR intensity inhomogeneity by information minimization. IEEE Trans. Med. Imaging 20 (12), 1398–1410. (2001)
[19] Press, W., Flannery, B., Teukolsky, S., Vetterling, W.,. Numerical Recipes in C: The Art of Scientic Computing, second ed. Cambridge University Press, UK. (2002)
[20] Otsu, N.,. A threshold selection method from gray-level histograms. IEEE Trans. Syst. Man Cybernet. 9 (1), 62–69.(1979)
[21] Jose ´ V. Manjo ´n a, *, Juan J. Lulla, Jose ´ Carbonell-Caballero a, Gracia ´n Garcı ´a-Martı ´a Luı ´s Martı ´-Bonmatı ´b, Montserrat Robles, A nonparametric MRI inhomogeneity correction method, Medical Image Analysis 11 (2007) 336–345
[22] Olivier Salvado, Claudia Hillenbrand, Shaoxiang Zhang, and David L. Wilson*, Member, IEEE, Method to Correct Intensity Inhomogeneity in MR Images for Atherosclerosis Characterization, IEEE TRANSACTIONS ON MEDICAL IMAGING, VOL. 25, NO. 5, (2006)
[23] Fa-Hsuan Lin, * Ying-Jui Chen, John W. Belliveau, and Lawrence L. Wald, A Wavelet-Based Approximation of Surface Coil Sensitivity Proles for Correction of Image Intensity Inhomogeneity and Parallel Imaging Reconstruction, Human Brain Mapping 19:96–111(2003)
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊