簡易檢索 / 詳目顯示

回結果列表
研究生： 劉彥良
Liu, Yen-Liang
論文名稱： 三維腦部磁振造影多發性硬化症自動化評估系統
Automated System for Multiple Sclerosis Lesion Segmentation in 3D Brain MRI
指導教授： 孫永年
Sun, Yung-Nien
林宙晴
Lin, Chou-Ching
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 資訊工程學系
Department of Computer Science and Information Engineering
論文出版年： 2017
畢業學年度： 105
語文別： 英文
論文頁數： 91
中文關鍵詞： 多發性硬化症 、病灶 、自動分割 、對位 、磁振造影 、核磁共振
外文關鍵詞： Multiple Sclerosis, Lesions, Segmentation, Registration, FCM, MRI
相關次數： 點閱：66  下載：3 
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報

    • 多發性硬化症為一種炎症性中樞神經系統的慢性疾病。髓鞘受到破壞後在腦中產生大小不一的塊狀硬化組織，透過磁振造影的檢測可以發現這些病灶。然而隨著時間的進展，這些病灶有可能繼續擴大，抑或是在其他地方產生新的病灶，故名為多發性硬化症。這些病灶的大小量測與數量評估對於醫師判斷此疾病的進展很有幫助。而在磁振造影影像中，病灶的特徵在某些加權下很容易被觀察出來。因此本篇論文建立了基於磁振造影影像應用之自動化系統，包括腦部擷取與對位之影像前處理、腦平均模型之變形與對位、以及腦組織分群與病灶分割的完整流程，最終計算病灶的數量與體積大小提供給醫師作評估。
    本篇延伸了以模糊C群分群法(Fuzzy C-Means)為基底，應用於多個加權磁振造影影像的方法。因應多發性硬化症的特性，其病灶好發於白質區域，我們提出了新的能量方程式，並加入了以腦平均模型為參考所獲得之各群機率參數，用以增強各群與病灶的特性且利於分割。
    最後我們驗證本篇所提出之方法，並與先前方法以及現有開源方法作比較。透過多重數據驗證，我們所提出的方法相較於前方法改善了分割結果；再經過本篇所提出的後處理方法，實驗數據更進一步顯示出改良性。

    Multiple Sclerosis (MS) is a relatively common inflammatory disease involving the central nervous system. MS lesions vary greatly in shape, location, intensity and area, which challenge the automated segmentation methods. Thus, the lesion load and its delineation have established their importance for assessing disease progression. This work built an automated system includes brain extraction, registration, atlas model creation, bias correction and tissue segmentation with MS lesions and other tissues.
    In this work, we further extend Multi-channel MICO (MCMICO) algorithm and modify the energy formulation by introducing the atlas probability model into the MR images. According to the characteristic of MS lesion which primarily affects the white matter, the study enhances MS lesions and also segments other tissues by applying the probability map.
    The proposed method is validated by comparing with the original MCMICO algorithm and an existing toolbox LPA. The measures mostly demonstrate a great improvement of our method. With introducing an atlas probability model as the priori knowledge, the segmentation method effectively rejects the false positives. After post-processing, the proposed method further improves the results.

    摘要 I ABSTRACT II 誌謝 III CONTENTS IV LIST OF TABLES VII LIST OF FIGURES IX CHAPTER 1 INTRODUCTION 1 1.1 Background 1 1.1.1 Multiple Sclerosis 1 1.1.2 Magnetic Resonance Imaging 2 1.2 Related Works 3 1.2.1 Supervised Methods 3 1.2.2 Unsupervised Methods 4 1.3 Contributions 6 1.4 System Overview and Thesis Organization 7 CHAPTER 2 PREPROCESSING 9 2.1 Brain Extraction 9 2.1.1 Estimation of Brain Parameters 10 2.1.2 Surface Initialization 12 2.1.3 Surface Update Iteration 12 2.2 Brain Registration 14 2.2.1 Matching Criterion 15 2.2.2 Coarse-to-fine Strategy 16 CHAPTER 3 ATLAS DEFORMATION 19 3.1 Rigid Transformation 19 3.1.1 Alignment of MSPs 20 3.1.2 Alignment of Images on MSP 22 3.2 Non-rigid Deformation 24 3.2.1 Histogram Matching 25 3.2.2 Hierarchical Structure 26 3.2.3 Similarity Measure 27 3.2.4 Displacement Estimation 28 CHAPTER 4 TISSUE SEGMENTATION 31 4.1 Multiple Intrinsic Component 31 4.1.1 Decomposition of MR image 31 4.1.2 Representations of Multiple Intrinsic Component 32 4.2 Fuzzy C-Means Algorithm 34 4.2.1 Definition 34 4.2.2 Energy Formulation 36 4.2.3 Energy Minimization 37 4.3 Multiple Modalities Extension 39 4.3.1 Definition 40 4.3.2 Energy Formulation and Minimization 40 4.4 Proposed Multi-modality FCM 41 4.5 Post-Processing 43 CHAPTER 5 EXPERIMENTAL MATERIALS 46 5.1 MRI Database 46 5.1.1 Test Database from IBSR 46 5.1.2 Simulated Database from BrainWeb 46 5.1.3 Clinical Database from NCKUH 47 5.2 Atlas Model 48 CHAPTER 6 EXPERIMENTAL RESULTS 50 6.1 Experimental Environment 50 6.2 Validation of Brain Registration 51 6.3 Validation of Atlas Deformation 53 6.4 Validation of Proposed FCM 55 6.4.1 Evaluation of Tissue Classification on IBSR Database 55 6.4.2 Evaluation of Bias Correction on BrainWeb Database 58 6.4.3 Evaluation of Optimal Constants 63 6.4.3.1 Optimal Probability Base 63 6.4.3.2 Optimal Weights for Modalities and Tissues 64 6.4.4 Evaluation of MS Lesion Segmentation on NCKUH Database 68 6.4.4.1 Lesion Prediction Algorithm (LPA) 68 6.4.4.2 Comparison of MS Segmentation Results 69 6.4.4.3 Estimation of Tissue Volume 80 CHAPTER 7 CONCLUSIONS AND FUTURE WORKS 82 7.1 Conclusions 82 7.2 Future Works 84 REFERENCES 85

    [1] NINDS, "National Institute of Neurological Disorders and Stroke: Multiple Sclerosis Information Page," [Online]. Available: https://www.ninds.nih.gov/Disorders/All-Disorders/Multiple-Sclerosis-Information-Page.
    [2] T. Brosch, L. Y. W. Tang, Y. Yoo, D. K. B. Li, A. Traboulsee and R. Tam, "Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation," IEEE Transactions on Medical Imaging, pp. 1229-1239, May 2016.
    [3] J. H. Simon, "Brain atrophy in multiple sclerosis: what we know and would like to know," Mult Scler. , pp. 679-87, 2006.
    [4] A. M. Hedman, N. E. v. Haren, H. G. Schnack, R. S. Kahn and H. E. H. Pol, "Human Brain Changes Across the Life Span: a review of 56 longitudinal magnetic resonance imaging studies," Human Brain Mapping, pp. 1987-2002, 2012.
    [5] H. AL., MRI Physics for Physicians, Springer Science & Business Media, 1989.
    [6] D. García-Lorenzo, S. Francis, S. Narayanan, D. L. Arnold and D. L. Collins, "Review of automatic segmentation methods of multiple sclerosis white matter lesions on conventional magnetic resonance imaging," Medical Image Analysis, pp. 1-18, January 2013.
    [7] YingWu, S. K.Warfield, I. LengTan, W. M. W. III, D. S. Meier, R. A. v. Schijndel, F. Barkhof and C. R. Guttmann, "Automated segmentation of multiple sclerosis lesion subtypes with multichannel MRI," NeuroImage, pp. 1205-1215, September 2006.
    [8] D. Yamamoto, H. Arimura, S. Kakeda, T. Magome, Y. Yamashita, F. Toyofuku, M. Ohki, Y. Higashida and Y. Korogi, "Computer-aided detection of multiple sclerosis lesions in brain magnetic resonance images: False positive reduction scheme consisted of rule-based, level set method, and support vector machine," Computerized Medical Imaging and Graphics, pp. 404-413, 2010.
    [9] B. A. Abdullah, A. A. Younis, P. M. Pattany and E. Saraf-Lavi, "Textural Based SVM for MS Lesion Segmentation in FLAIR MRIs," Open Journal of Medical Imaging, pp. 26-42, 2011.
    [10] P. Schmidt, "Bayesian inference for structured additive regression models for large-scale problems with applications to medical imaging," LMU München: Faculty of Mathematics, Computer Science and Statistics, 2016.
    [11] S. Valverde, M. Cabezas, E. Roura, S. González-Villà, D. Pareto, J. C. Vilanova, L. Ramió-Torrentà, À. Rovira, A. Oliver and X. Lladó, "Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach," NeuroImage, pp. 159-168, 2017.
    [12] D.-J. Kroon, E. v. Oort and K. Slump, "Multiple Sclerosis Detection in Multispectral Magnetic Resonance Images with Principal Components Analysis," in MICCAI 2008 Workshop.
    [13] W. M. Wells, W. E. L. Grimson, R. Kikinis and F. A. Jolesz, "Adaptive Segmentation of MRI Data," IEEE Transactions on Medical Imaging, pp. 429-442, August 1996.
    [14] D. L. Pham and J. L. Prince, "Adaptive Fuzzy Segmentation of Magnetic Resonance Images," IEEE Transactions on Medical Imaging, pp. 737-752, September 1999.
    [15] C. Li, J. C.Gore and C. Davatzikos, "Multiplicative intrinsic component optimization (MICO) for MRI bias field estimation and tissue segmentation," Magnetic Resonance Imaging, pp. 913-923, 2014.
    [16] Y. Zhao, S. Guo, M. Luo, Y. Liu, M. Bilello and C. Li, "An energy minimization method for MS lesion segmentation from T1-w and FLAIR images," Magnetic Resonance Imaging, pp. 1-6, 2017.
    [17] S. M. Smith, "Fast Robust Automated Brain Extraction," Human Brain Mapping, pp. 143-155, 2002.
    [18] S. Ourselin, A. Roche, S. Prima and N. Ayache, "Block Matching: A General Framework to Improve Robustness of Rigid Registration of Medical Images," in Medical Image Computing and Computer-Assisted Intervention, Pittsburgh, Pennsylvania, USA, 2000.
    [19] F. Maes, A. Collignon, D. Vandermeulen, G. Marchal and P. Suetens, "Multimodality image registration by maximization of mutual information," IEEE Transactions on Medical Imaging, pp. 187-198, 1997.
    [20] C. E. Shannon, "A Mathematical Theory of Communication," The Bell System Technical Journal, pp. 379-423/623-656, 1948.
    [21] I. Despotovic, B. Goossens and W. Philips, "MRI Segmentation of the Human Brain: Challenges, Methods, and Applications," Computational and Mathematical Methods in Medicine, 2015.
    [22] J.-X. Liu, Y.-S. Chen and L.-F. Chen, "Fast and Accurate Registration Techniques for Affine and Nonrigid Alignment of MR Brain Images," Annals of Biomedical Engineering, pp. 138-157, 2010.
    [23] Cormen, Leiserson and Rivest, Introduction to Algorithms, 1990, p. 329.
    [24] A. V. Tuzikov, O. Colliot and I. Bloch, "Evaluation of the symmetry plane in 3D MR brain images," Pattern Recognition Letters, pp. 2219-2233, 2003.
    [25] R. C. Gonzalez and R. E. Woods, Digital Image Processing (3rd ed.), Prentice Hall, 2008, p. 128.
    [26] H. Wendland, "Piecewise polynomial, positive definite and compactly supported radial functions of minimal degree," Advances in Computational Mathematics, p. 389–396, 1995.
    [27] W. Cong, J. Song, K. Luan, H. Liang, L. Wang, X. Ma and J. Li, "A Modified Brain MR Image Segmentation and Bias Field Estimation Model Based on Local and Global Information," 2016.
    [28] B. M. Dawant, A. P. Zijdenbos and R. A. Margolin, "Correction of Intensity Variations in MR Images for Computer-Aided Tissue Classification," 1993.
    [29] H. G. Barrow and J. Martin Tenenbaum, "Recovering intrinsic scene characteristics from images," Computer Vision Systems, pp. 3-26, 1978.
    [30] P. MJD., Approximation theory and methods, Cambridge University Press, 1981.
    [31] J. Tohka, "Partial volume effect modeling for segmentation and tissue classification of brain magnetic resonance images: A review," World Journal of Radiology, pp. 855-864, 2014.
    [32] F. Barkhof, M. Filippi, D. H. Miller, P. Scheltens, A. Campi, C. H. Polman, G. Comi, H. J. Adèr, N. Losseff and J. Valk, "Comparison of MRI criteria at first presentation to predict conversion to clinically definite multiple sclerosis.," Brain, pp. 2059-69, 1997.
    [33] D. Garcia-Lorenzo, L. Lecoeur, D. Arnold and D. L. Collins, "Multiple Sclerosis Lesion Segmentation Using an Automatic Multimodal Graph Cuts," Medical Image Computing and Computer Assisted Intervention, pp. 584-591, 2009.
    [34] A. Karimian and S. Jafari, "A New Method to Segment the Multiple Sclerosis Lesions on Brain Magnetic Resonance Images," Journal of Medical Signals and Sensors, pp. 238-244, 2015.
    [35] "Internet Brain Segmentation Repository (IBSR)," Neuroimaging Informatics Tools and Resources Clearinghouse, [Online]. Available: https://www.nitrc.org/projects/ibsr.
    [36] "BrainWeb: Simulated Brain Database," [Online]. Available: http://www.bic.mni.mcgill.ca/brainweb/.
    [37] "International Consortium for Brain Mapping (ICBM)," [Online]. Available: http://www.loni.usc.edu/atlases/.
    [38] NVIDIA, "Programming guide," [Online]. Available: http://docs.nvidia.com/cuda/cuda-c-programming-guide.
    [39] L. R. Dice, "Measures of the Amount of Ecologic Association Between Species," Ecology, pp. 297-302, July 1945.
    [40] "Statistical Parametric Mapping," University College London (UCL), FIL Mehods Group, [Online]. Available: http://www.fil.ion.ucl.ac.uk/spm/.
    [41] "A Lesion Segmentation Tool for SPM," [Online]. Available: www.statistical-modelling.de/lst.html.
    [42] J. P. Rushton and E. W. Rushton, "Brain size, IQ, and racial-group differences: Evidence from musculoskeletal traits," Intelligence, pp. 139-155, 2003.

    下載圖示 校內：2022-09-01公開
    校外：2022-09-01公開
    QR CODE