簡易檢索 / 詳目顯示

回結果列表
研究生： 洪世羽
Hung, Shi-Yu
論文名稱： 基於頻譜圖分群之高效能細胞核分割系統應用於三倍頻顯微影像
High Efficiency Nuclei Segmentation System Based on Spectral Graph Partitioning in Third Harmonic Generation Microscopy Images
指導教授： 李國君
Lee, Gwo Giun (Chris)
學位類別： 碩士
Master
系所名稱： 電機資訊學院 - 電機工程學系
Department of Electrical Engineering
論文出版年： 2016
畢業學年度： 104
語文別： 英文
論文頁數： 144
中文關鍵詞： 細胞核分割演算法 、電腦輔助診斷 、頻譜圖分群演算法 、演算法暨架構共同探索 、資料流 、多核心中央處理器
外文關鍵詞： Nuclei segmentation algorithm, Computer-Aided Diagnosis (CAD), Spectral graph partitioning, Algorithm/Architecture Co-exploration (AAC), dataflow, multi-core CPU
相關次數： 點閱：110  下載：0 
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

    • 本論文介紹基於演算法暨架構共同探索方法進行細胞核分割演算法之系統層級設計與實現。本論文主要貢獻在於提升自動化電腦輔助診斷系統之處理效能。針對系統前半影像預處理之步驟，藉由探索所使用演算法於不同抽象層集之各種資料流及本質複雜度分析並同時考量欲實現平台之硬體資訊選擇最佳解。而針對細胞分割演算法，藉由提出之頻譜圖分群演算法分解從影像建構之圖，以達到平行化處理之目的。而此方法具有能夠將欲處理之資料任務有智慧且彈性地實現於各種平台之能力。
    最後根據設計之演算法實現於多核心中央處理器進行處理時間量測與加速率評估，達到高效能之電腦輔助診斷系統。

    This thesis presents the system level design and implementation of nuclei segmentation algorithm based on Algorithm/Architecture Co-exploration (AAC) design methodology. The major contribution of this thesis is to enhance the processing efficiency of automatic Computer-Aided Diagnosis (CAD). For the design of first half regular pre-processing procedures in algorithm, exploring various dataflow in different abstraction levels also assessed their corresponding intrinsic complexity which considers the architectural information from selected target platform for optimal solution decision. And for the second half segmentation process, formulating the parallel processing as graph partition problem and adopted the spectral graph partitioning approach to partition modeled graph from image. This technique possess the intelligent and flexible ability of mapping partitioned tasks onto various platforms to deal with parallel processing. Eventually, it achieve high efficiency CAD system by processing time measurement and quatified speed up ratio after implementing nuclei segmentation algorithm onto multi-core Central Processing Unit (CPU).

    摘 要 i Abstract ii Table of Contents vi List of Tables ix List of Figures x Chapter 1. Introduction 1 1.1 Introduction of Intelligent Computer-Aided Diagnosis system 1 1.2 Higher Harmonic Generation Microscopy Imaging System 3 1.2.1 Physical Background of Image Acquisition 3 1.2.2 Setup of the Optical Imaging 4 1.2.3 Aquired Image Interpretation 5 1.3 Algorithm/Architecture Co-exploration 7 1.3.1 Design Space Exploration 7 1.3.2 Dataflow Model 9 1.3.3 Intrinsic Complexity Assessment 10 1.3.4 Graph Theory 13 1.4 Motivation 14 1.5 Organization of Thesis 15 Chapter 2. Surveys Related Works of Literatures 16 2.1 Survey Implementation of Filtering 16 2.1.1 Two-Dimensional Filter 16 2.1.2 Separable Filter 18 2.1.3 Fast Fourier Transform based Convolution 19 2.2 Survey Related Works of Partitioning 20 2.2.1 K-means Clustering 20 2.2.2 Agglomerative Hierarchical Clustering 22 2.2.3 Recursive Coordinate Bisection 24 2.2.4 Recursive Graph Bisection 26 2.2.5 Spectral Graph Partitioning 27 2.3 Surveys Platforms 29 2.3.1 ASIC 29 2.3.2 FPGA 29 2.3.3 Multi-core CPU and GPU 30 2.3.4 Cloud 31 Chapter 3. Overview of Nuclei Segmentation Algorithm based on Third Harmonic Generation Microscopy Images 32 3.1 Nuclei Segmentation Algorithm 32 3.1.1 Watershed Transform with Marker-Controlled Stategy 36 3.1.2 Nuclei Initialization 39 3.1.3 Gradient Map Generation 50 3.1.4 Nuclei Detection and Validation 51 Chapter 4. System Level Design of Nuclei Segmentation Based on Algorithm/Architecture Co-Exploration 54 4.1 System Specification and Anaysis 54 4.1.1 Specification 54 4.1.2 System Dependency and Computational Load Analysis 55 4.2 High Efficiency Preprocessing via Dataflow Exploration 56 4.2.1 High-level Dataflow Exploration 58 4.2.2 Design Space Exploration 76 4.2.3 Low-level Dataflow Exploration and System Architecture 83 4.3 Efficient Nuclei Segmentation based on Spectral Graph Partitioning 107 4.3.1 Problems Identification of Parallel Processing 107 4.3.2 Graph Modeling 107 4.3.3 Spectral Graph Partitioning 111 4.3.4 Preprocessing Mechanism 118 Chapter 5. Experimental Results and Discussion 121 5.1 Intrinsic Complexity Assessment of Preprocessing via Dataflow Exploration 121 5.2 Various Graph Partitioning Results for Efficeint Nuclei Segmentation 126 5.3 Performance Analysis of Mapping Nuclei Segmentation Algorithm onto Multi-Core CPU 133 Chapter 6. Conclusion and Future Works 137 6.1 Conclusion 137 6.2 Future Works 139 Reference 141

    [1] S.-Y. Chen, S.-U. Chen, H.-Y. Wu, W.-J. Lee, Y.-H. Liao, and C.-K. Sun, "In vivo virtual biopsy of human skin by using noninvasive higher harmonic generation microscopy," Selected Topics in Quantum Electronics, IEEE Journal of, vol. 16, pp. 478-492, 2010.
    [2] E. Vega‐Memije, N. M. De Larios, L. M. Waxtein, and L. Dominguez‐Soto, "Cytodiagnosis of cutaneous basal and squamous cell carcinoma," International journal of dermatology, vol. 39, pp. 116-120, 2000.
    [3] Y. Oram, O. Turhan, and N. Din, "Diagnostic value of cytology in basal cell and squamous cell carcinomas," International journal of dermatology, vol. 36, pp. 156-157, 1997.
    [4] Y.-H. Liao, S.-Y. Chen, S.-Y. Chou, P.-H. Wang, M.-R. Tsai, and C.-K. Sun, "Determination of chronological aging parameters in epidermal keratinocytes by in vivo harmonic generation microscopy," Biomedical optics express, vol. 4, pp. 77-88, 2013.
    [5] G. G. Lee, Y.-K. Chen, M. Mattavelli, and E. S. Jang, "Algorithm/architecture co-exploration of visual computing on emergent platforms: overview and future prospects," IEEE Transactions on Circuits and Systems for Video Technology, vol. 19, pp. 1576-1587, 2009.
    [6] G. G. Lee, H.-Y. Lin, C.-F. Chen, and T.-Y. Huang, "Quantifying Intrinsic Parallelism Using Linear Algebra for Algorithm/Architecture Coexploration," Parallel and Distributed Systems, IEEE Transactions on, vol. 23, pp. 944-957, 2012.
    [7] D. B. West, Introduction to graph theory vol. 2: Prentice hall Upper Saddle River, 2001.
    [8] E. G. Boman, K. D. Devine, and S. Rajamanickam, "Scalable matrix computations on large scale-free graphs using 2D graph partitioning," in Proceedings of the International Conference on High Performance Computing, Networking, Storage and Analysis, 2013, p. 50.
    [9] A. Mashaghi, A. Ramezanpour, and V. Karimipour, "Investigation of a protein complex network," The European Physical Journal B-Condensed Matter and Complex Systems, vol. 41, pp. 113-121, 2004.
    [10] J. Shi and J. Malik, "Normalized cuts and image segmentation," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 22, pp. 888-905, 2000.
    [11] S. N. Bhatt and F. T. Leighton, "A framework for solving VLSI graph layout problems," Journal of Computer and System Sciences, vol. 28, pp. 300-343, 1984.
    [12] B.-C. C. Lai, K.-C. Li, G.-R. Li, and C.-H. Chiang, "Self adaptable multithreaded object detection on embedded multicore systems," Journal of Parallel and Distributed Computing, vol. 78, pp. 25-38, 2015.
    [13] C. M. Bishop, Pattern recognition and machine learning vol. 1: springer New York, 2006.
    [14] J. MacQueen, "Some methods for classification and analysis of multivariate observations," in Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, 1967, pp. 281-297.
    [15] R. Sibson, "SLINK: an optimally efficient algorithm for the single-link cluster method," The Computer Journal, vol. 16, pp. 30-34, 1973.
    [16] B. W. Kernighan and S. Lin, "An efficient heuristic procedure for partitioning graphs," Bell system technical journal, vol. 49, pp. 291-307, 1970.
    [17] H. D. Simon, "Partitioning of unstructured problems for parallel processing," Computing Systems in Engineering, vol. 2, pp. 135-148, 1991.
    [18] U. Von Luxburg, "A tutorial on spectral clustering," Statistics and computing, vol. 17, pp. 395-416, 2007.
    [19] A. Suleiman and V. Sze, "Energy-efficient HOG-based object detection at 1080HD 60 fps with multi-scale support," in Signal Processing Systems (SiPS), 2014 IEEE Workshop on, 2014, pp. 1-6.
    [20] D. Lee, P. Meng, M. Jacobsen, H. Tse, D. Di Carlo, and R. Kastner, "A hardware accelerated approach for imaging flow cytometry," in Field Programmable Logic and Applications (FPL), 2013 23rd International Conference on, 2013, pp. 1-8.
    [21] B. Prasad and W. Badawy, "Assessment of hardware vs software implementations for video microscopy," in Biomedical Circuits and Systems Conference, 2006. BioCAS 2006. IEEE, 2006, pp. 150-153.
    [22] F. Grützmacher, J.-P. Wolff, and C. Haubelt, "Sensor-based online hand gesture recognition on multi-core dsps," in 2015 IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2015, pp. 898-902.
    [23] B.-W. Shen, B. Nelson, S. Cheung, and W.-K. Tao, "Improving NASA's multiscale modeling framework for tropical cyclone climate study," Computing in Science & Engineering, vol. 15, pp. 56-67, 2013.
    [24] E. Smistad, T. L. Falch, M. Bozorgi, A. C. Elster, and F. Lindseth, "Medical image segmentation on GPUs–A comprehensive review," Medical image analysis, vol. 20, pp. 1-18, 2015.
    [25] G. G. Lee, H.-H. Lin, M.-R. Tsai, S.-Y. Chou, W.-J. Lee, Y.-H. Liao, et al., "Automatic cell segmentation and nuclear-to-cytoplasmic ratio analysis for third harmonic generated microscopy medical images," Biomedical Circuits and Systems, IEEE Transactions on, vol. 7, pp. 158-168, 2013.
    [26] L. Vincent and P. Soille, "Watersheds in digital spaces: an efficient algorithm based on immersion simulations," IEEE Transactions on Pattern Analysis & Machine Intelligence, pp. 583-598, 1991.
    [27] J. M. Gauch, "Image segmentation and analysis via multiscale gradient watershed hierarchies," Image Processing, IEEE Transactions on, vol. 8, pp. 69-79, 1999.
    [28] R. C. Gonzales and R. E. Woods, "Digital Image Processing, 2-nd Edition," ed: Prentice Hall, 2002.
    [29] T. Lindeberg, "Feature detection with automatic scale selection," International journal of computer vision, vol. 30, pp. 79-116, 1998.
    [30] D. W. Paglieroni, "Distance transforms: Properties and machine vision applications," CVGIP: Graphical models and image processing, vol. 54, pp. 56-74, 1992.
    [31] A. M. MacEachren, "Compactness of geographic shape: Comparison and evaluation of measures," Geografiska Annaler. Series B. Human Geography, pp. 53-67, 1985.
    [32] T. Bräunl, S. Feyrer, W. Rapf, and M. Reinhardt, Parallel image processing: Springer Science & Business Media, 2013.
    [33] E. K. Chong and S. H. Zak, An introduction to optimization vol. 76: John Wiley & Sons, 2013.
    [34] M. Fiedler, "A property of eigenvectors of nonnegative symmetric matrices and its application to graph theory," Czechoslovak Mathematical Journal, vol. 25, pp. 619-633, 1975.

    下載圖示
    2026-01-01公開
    QR CODE