使用模擬退火法於腦部磁振造影影像分割之研究 黃文星、葉進儀
E-mail: 9223396@mail.dyu.edu.tw
摘 要
這份研究將探討醫學影像中磁振造影影像之分割方式,使用啟發式演算法中的模擬退火法來搜尋解空間,本研究將使 用K-Mean分類法、模糊理論於學習向量量化法則、學習向量及模糊群聚法四種分類法產生之解當做起始解,配合有效的 移步法則、降溫機制,分別應用在CSA、FSA、GSA、ASA、TSA等五種模擬退火演算法,分割腦膜瘤磁振造影影像。本 研究將評估四種分類方法與五種模擬退火法產生之二十種組合,計算出每一種組合之績效指標,經由績效衡量比較每一種 組合,找出較佳組合方案。 經實驗結果,使用模糊學習向量量化於適應性模擬退火法進行腦膜瘤影像分割,對於腦內組織 成分的分類,能提供比其它模擬退火法之組合有更好的結果。
關鍵詞 : 腦膜瘤,磁振造影,模擬退火法,績效指標,影像分割 目錄
第一章 緒論 1.1 研究背景與動機………...1 1.2 研究目的………
…...2 1.3 研究範圍………...3 1.4 研究流程………...4 1.5 論文章節架構………...7 第二章 文獻探討 2.1 腦膜瘤病理症狀之研究………
………...8 2.2 相關研究文獻探討………...12 2.3 模擬退火法………
…...14 2.4 K平均分類演算法………....19 2.5 模糊分類演算法………
…...19 2.6 模糊理論於學習向量量化演算法……….…..20 2.7 向量量化演算法………
…...20 第三章 研究方法與流程 3.1 研究流程………...21 3.2 研究方法………
………...25 3.2.1 研究架構………...25 3.2.2 模擬退火法………
………...26 3.2.2.1 建立問題模式………..27 3.2.2.2 建立冷卻計劃表………..35 3.2.2.3 進行模 擬退火程序………..37 3.2.3 績效衡量……….…..38 第四章 實驗結果與分析 4.1 實驗相 關資訊………...41 4.2 實驗結果及分析………...43 4.2.1 實驗架構
………...43 4.2.2 實驗內容………...44 4.2.3 實驗設計與結果………
………...44 4.2.4 參數設定………...47 4.2.5 使用模擬退火演算法分類結果………
………...49 4.2.6 組合不同演算法與模擬退火法分類結果….…..52 第五章 結論與建議 5.1 結論………
………...58 5.2 建議………...58 參考文獻 附錄一 附錄二 附錄三 參考文獻
1. 鄭慶明編著,「放射線攝影擺位法與相關解剖學」,合記圖書出版社,90 2. 鄭慶明編著,「實用影像診斷學」,國立編譯館主編
,2001 3. 柯惠雯, 「結合模擬退火法與禁忌搜尋法在流程式生產排程之應用」, 大葉大學工業工程研究所碩士論文, 2001 4. 黃玟錫, 「不 規則物件排列問題解法之研究」, 大葉大學工業工程研究所碩士論文, 2001 5. 王誌偉, 「使用模糊分類演算法及遺傳基因演算法於核磁共 振造影影像分割之研究」, 大葉大學工業工程研究所碩士論文, 2002 6. 楊順欽, 「二維影像資訊於時間序列中訊號細微變化之檢測-以功 能性磁振造影為案例」, 大葉大學工業工程研究所碩士論文, 2002 7. 陳隆熙, 「一個解決TSP問題最佳解的穩定方法-以TA演算法為例」, 大葉大學工業工程研究所碩士論文, 2002 8. 田邦廷,「長方體物件堆疊問題解法之研究」,大葉大學工業工程研究所碩士論文,2002 9.
Rita Carter著, 洪蘭譯,「大腦的秘密檔案」, 遠流出版社, 2002. 10. Aarts, E. H. L., De Bont, F. M. J., Habers, E. H. A., and Van Laarhoven, P. J. M., "Statistical cooling: a general approach to combinatorial optimizations", Philips Journal of Research, 4, pp. 193-226, 1985. 11. Albrecht, A., Hein, E., Steinhofel, K., Taupitz, M., Wong, C. K., "Bounded-depth threshold circuits for computer-assisted CT image classification", Artificial Intelligence in Medicine, 24, pp.179-192, 2002. 12. Bezdek, J. C., "Pattern Recognition with Fuzzy Objective Function Algo-rithms". NY: Plenum, 1981. 13. Baumgartner, R., Somorjai, R., Summers, R., Ricchter, W., "Ranking fMRI Time-Courses by Minimum Spanning Trees(MSTs
):Assessing Coactivation in fMRI", NeuroImage in press, pp.1-25. 14. Banerjee, S., Mukherjee, D. Dutta Majumdar, P., D., "Fuzzy c-means approach to tissue classification in multimodal medical imaging", Information Sciences 115, pp.261-279, 1999. 15. David GiBon, PH. D., Jean Rousseau, PH. D., Bernard Castelain, M. D., Serge Blond, M. D., Christian Vasseur, PH. D. and Xavier Marchandise, M. D. "Treatment Planning Optimization by Conjugate Gradients and Simulated Annealing methods in stereotactic radiosurgery", Int. J. Radiation Oncology Biol.
Phys., Vol. 33. No. 1. pp.201-210, 1995. 16. Hyvarinen A.,"Survey on independent component analysis", Neural Computing Surveys 2, pp.94-128,
1999. 17. Hall, L. O., Bensaid, A. M., Clarke, L. P., Velthuizen, R. P., Silbiger, M. S., and Bezdek, J. C., "A Comparison of Neural Network and Fuzzy Clustering Techniques in Segmenting Magnetic Resonance Images of the Brain," IEEE Transactions on Neural Networks, Vol. 3, No. 5, pp.
672-682, Sep. 1992. 18. Karayiammis, N. B., and Pin-I Pai., "A Fuzzy Algorithms for Learning Vector Quantization," in Intelligent Engineering Systems Through Artificial Neural Networks, vol.4, C. H. Dagli et al., Eds. New York:ASME Press,pp.219-224, 1994. 19. Karayiammis, N. B. and Pai, P., "Segmentation of Magnetic Resonance Images Using Fuzzy Algorithms for Learning Vector Quantization," IEEE Transactions on Medical Imaging, Vol. 18, No. 2, pp. 172-180, Feb. 1999. 20. Kirkpatrick, S., Gelatt, C. D., and Vecchi, M.P., "Optimization by simulated annealing", Science, 200(4956), pp.671-680, 1983. 21. Kirkpatrick, S., Gelatt, C. D., and Vecchi, M. P., "Optimization by simulated annealing", Science, 200
(4598), pp.671-680, 1983. 22. Kohonen, T., "Self-organization and associate memory", Sprnger-Verlag, London, 1984. 23. Kohonen, T., "The neural phonetic typerwriter", Computer, 21(3):11-22, 1988. 24. Kohonen, T., "Self-organization and associate memory", Springer-Velag, London, 3rd edition,1989 25. Lundy, M., and Mees, A., "Convergence of an annealing algorithm", Mathematical Programming, Vol. 34, pp.111-124, 1986.
26. Ozkan, M., Dawant, B. M., and Maciunas, R. J., "Neural-network-based segmentation of multi-modal medical images: A comparative and prospective study", IEEE Transactions on Medical Imaging, Vol. 12, No. 3, pp.534-544, Sep. 1993. 27. Sanghamitra Bandyopadhyay, Ujjwal Maulik, "An evolutionary technique based on K-Mean algorithm for optimal clustering", Information Sciences 146, pp.221-237, 2002. 28.
Sanghamitra Bandyopadhyay a,*, Ujjwal Maulik, "Genetic algorithm-based clustering technique",Pattern Recognition 33, pp.1455-1465, 2000.
29. Simonen C.Z., Ostergaard, L., and Smith D.F., et al. "Comparison of Gradient Echo and Spin Echo Imaging:CBF、 CBV and MTT
Measurements by Bolus Tracking", Journal of Magnetic Resonance Imaging 12, pp. 411-416, 2000. 30. Schnack, H. G., Hulshoff Pol, H. E., Barre, W. F. C., Viergever, M. A., and Kahn, R. S., "Automatic Segmentation of the Ventricular System from MR Images of the Human Brain", NeuroImage, 14, pp.95-104, 2001. 31. Sven, L. and Zoran, M., "Multiresolution CT Head Image Analysis using Simulted Annealing", Proceedings of the 20th Int Conference Information Technology Interfaces, pp. 257-262, Pula, Croatia, 1998. 32. Shang, H. L. and Baba, C. V., "Efficient hybrid search for visual reconstruction problems", Image and Vision Computing 17 (1999) 37-49. 33. Worsley, K. J., Liao, C. H., Aston, J., Petre, V., Duncan, G. H., Morales, F., and Evans, A. C., "A General Statistical Analysis for fMRI Data", NeuroImage, 15, pp.1-15, 2002. 34. Yen, j., and Langari R., Fuzzy Logic: Intelligence, Control, and Information, Prentice Hall, Upper Saddle River, New Jersey, 1999. 35.
http://www.nsshu.com.tw/腦膜瘤.htm 36. http://www.geocities.com/~dr_ericlin/cases.htm 台中澄清醫院腦神經外科教學資料