(3.237.20.246) 您好!臺灣時間:2021/04/16 08:12
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:李岳峰
研究生(外文):Yue-Fong Lei
論文名稱:超音波影像中甲狀腺區域切割及體積估計
論文名稱(外文):Thyroid Segmentation and Volume Estimation in Ultrasound Images
指導教授:張傳育
指導教授(外文):Chuan-Yu Chang
學位類別:碩士
校院名稱:國立雲林科技大學
系所名稱:資訊工程研究所
學門:工程學門
學類:電資工程學類
論文種類:學術論文
論文出版年:2008
畢業學年度:96
語文別:中文
論文頁數:87
中文關鍵詞:粒子群最佳化區域成長半徑基底函數甲狀腺切割類神經網路
外文關鍵詞:Radial basis functionNeural networkThyroid segmentationParticle swarm optimizationRegion growing
相關次數:
  • 被引用被引用:1
  • 點閱點閱:194
  • 評分評分:系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔系統版面圖檔
  • 下載下載:50
  • 收藏至我的研究室書目清單書目收藏:1
超音波影像(Ultrasound image)是時下臨床診斷上一個普遍利用的輔助工具。醫師通常利用甲狀腺的體積來診斷病人甲狀腺是否發生病變。雖然甲狀腺區域形狀可從超音波影像中手動標記出來,但這個方法需依賴醫師們多年的經驗及寶貴的時間成本。如果醫師要獲得到較精確的甲狀腺體積時,當前仍仰賴電腦斷層(Computed Tomography, CT)影像的資訊來估計,不但影像成本昂貴,病人還需承擔處於強大輻射環境中的潛在風險。相對的,在取得超音波影像的過程中,病人不需經歷游離輻射的潛在危害,且所需的影像成本亦便宜許多。十分仰賴醫師經驗標記的超音波影像及拍攝電腦斷層影像時輻射的潛在危害,使得能在超音波影像中自動地估計甲狀腺體積的需求產生。為了滿足這項需要,本文提出一套能從一系列的超音波影像中直接估計甲狀腺體積的完整解決方案。在本文中,半徑基底函數(Radial Basis Function, RBF)類神經網路被應用來粗略地切割甲狀腺區域,而完整甲狀腺區域則進一步地應用特殊的區域成長方法取得,而甲狀腺體積估計法則的參數則是藉由粒子群最佳化(Particle Swarm Optimization, PSO)演算法訓練得到。實驗結果顯示我們提出的方法在超音波影像中甲狀腺區域切割及體積估計具有相當大的潛力。
Ultrasound (US) image is one of the most common auxiliary tools utilized in clinical diagnosis nowadays. The physician usually diagnoses the pathology of the thyroid gland by its volume. Nevertheless, even if the thyroid glands are acquired and the shapes are hand-marked from US images. Most of the physicians still depend on computed tomography (CT) images for precise volume of the thyroid gland. This approach relies heavily on the experiences of the physicians and costs much precious time of the physicians. In addition, patients have to suffer high radiation exposures to obtain the US images and the imaging costs incurred are quite high. In contrast, US imaging dose not require ionizing radiation, and the imaging cost incurred is much lower. These properties have made that the automatic volume estimation of thyroid glands using US images more and more important. Therefore, the objective of this paper is providing a complete solution to estimate the volume of the thyroid gland directly from US images. In this paper, the Radial Basis Function (RBF) neural network is used to classify blocks of the thyroid gland; the integral region is further acquired by applying a specific region growing method to potential points. The parameters for evaluating the thyroid volume is estimated by a particle swarm optimization (PSO) algorithm. Experimental results for the thyroid region segmentation and volume estimation in US images show high potential of our proposed approach.
摘要 ------------------------------------------------------------------------- i
ABSTRACT ------------------------------------------------------------------------- ii
誌謝 ------------------------------------------------------------------------- iii
目錄 ------------------------------------------------------------------------- iv
圖例索引 ------------------------------------------------------------------------- vi
表格索引 ------------------------------------------------------------------------- viii
第一章 緒論------------------------------------------------------------------- 1
1.1 研究動機------------------------------------------------------------- 1
1.2 甲狀腺超音波影像簡介------------------------------------------- 2
1.3 相關文獻------------------------------------------------------------- 4
1.4 研究方法------------------------------------------------------------- 6
1.5 章節大綱------------------------------------------------------------- 9
第二章 甲狀腺區域切割方法---------------------------------------------- 10
2.1 可疑甲狀腺區域的定位和影像增強---------------------------- 10
2.1.1 可疑甲狀腺區域的定位------------------------------------------- 11
2.1.2 適應性權重中值濾波器------------------------------------------- 12
2.1.3 形態學運算子------------------------------------------------------- 13
2.1.4 灰階強度校正------------------------------------------------------- 14
2.2 特徵擷取------------------------------------------------------------- 17
2.3 半徑基底函數類神經網路---------------------------------------- 20
2.3.1 RBF類神經網路訓練---------------------------------------------- 22
2.3.2 RBF類神經網路測試---------------------------------------------- 24
2.3.3 RBF類神經網路測試結果補償---------------------------------- 24
2.4 甲狀腺區域形狀之重建------------------------------------------- 26
2.4.1 濾除區域鋸齒------------------------------------------------------- 27
2.4.2 區域成長------------------------------------------------------------- 30
2.4.3 區域填充與閉合形態學運算------------------------------------- 31
第三章 甲狀腺體積估計方法---------------------------------------------- 34
3.1 2D甲狀腺區域資訊------------------------------------------------ 34
3.2 甲狀腺體積估測公式---------------------------------------------- 35
3.3 粒子群最佳化演算法---------------------------------------------- 36
第四章 實驗結果與討論---------------------------------------------------- 39
4.1 影像資料與實驗環境---------------------------------------------- 39
4.2 各實驗步驟之結果------------------------------------------------- 41
4.2.1 可疑甲狀腺區域的定位和影像增強---------------------------- 41
4.2.1.1 可疑甲狀腺區域的定位------------------------------------------- 41
4.2.1.2 適應性權重中值濾波器------------------------------------------- 42
4.2.1.3 形態學運算子------------------------------------------------------- 43
4.2.1.4 灰階強度校正------------------------------------------------------- 43
4.2.2 半徑基底函數類神經網路---------------------------------------- 44
4.2.2.1 訓練階段------------------------------------------------------------- 44
4.2.2.2 測試階段------------------------------------------------------------- 46
4.2.3 甲狀腺區域形狀之重建------------------------------------------- 46
4.2.3.1 濾除區域鋸齒結果------------------------------------------------- 46
4.2.3.2 區域成長結果------------------------------------------------------- 47
4.2.3.3 區域填充與閉合形態學運算結果------------------------------- 48
4.3 甲狀腺切割準確性評估------------------------------------------- 49
4.4 Leave-one-out 交叉驗證法評估系統切割效能--------------- 52
4.5 甲狀腺切割方法與其他方法比較------------------------------- 53
4.6 甲狀腺體積估計準確性評估------------------------------------- 56
4.7 灰階強度校正探討------------------------------------------------- 58
4.8 特徵選取探討------------------------------------------------------- 59
4.9 區域成長門檻值探討---------------------------------------------- 62
第五章 結論與未來發展方向---------------------------------------------- 63
5.1 結論------------------------------------------------------------------- 63
5.2 未來發展方向------------------------------------------------------- 64
參考文獻 ------------------------------------------------------------------------- 65
附錄 Thyroid Segmentation and Volume Estimation in Ultrasound Images---------------------------------------------------------------- 69
[1]Brunn J, Block U, Ruf G, Bos I, Kunze WP, Scriba PC. Volumetric analysis of thyroid lobes by real-time ultrasound (author’s translation) [in German]. Dtsch Med Wochenschr, 106, pp.1338-1340, Oct. 1981.
[2]N. Hu, D. B. Downey, A. Fenster, and H. M. Ladak, “Prostate boundary segmentation from 3d ultrasound images,” Medical Physics, vol. 30, no. 7, pp. 1648-1659, July 2003.
[3]B. Chiu, G. H. Freeman, M. M. A. Salama, and A. Fenster, “Prostate segmentation algorithm using dyadic wavelet transform and discrete dynamic contour,” Physics in Medicine and Biology, vol. 49, no. 21, pp. 4943-4960, Nov. 2004.
[4]D.-R. Chen, R.-F. Chang, W.-J. Wu, W. K. Moon, and W.-L. Wu, “3-D breast ultrasound segmentation using active contour model,” Ultrasound in Medicine and Biology, vol. 29, no. 7, pp. 1017-1026, July 2003.
[5]C. Baillard, C. Barillot, and P. Bouthemy, “Robust adaptive segmentation of 3d medical images with level sets,” Institut national de recherche en informatique et en automatique (INRIA), Le Chesnay Cedex, France, Tech. Rep. 4071, Nov. 2000.
[6]D.E. Maroulis, M.A. Savelonas, D.K. Iakovidis, S.A. Karkanis, and N. Dimitropoulos, “Variable Background Active Contour Model for Computer-Aided Delineation of Nodules in Thyroid Ultrasound Images”, IEEE Transactions on Information Technology in Biomedicine, vol. 11, no. 5, pp. 537-543, 2007.
[7]M. Kass, A. Witkin, and D. Terzopoulos, “Snakes: Active contour models.” International Journal of Computer Vision, vol. 1, no. 4, pp. 321-331, 1987.
[8]L. Vincent, P. Soille, “Watersheds in Digital Spaces: An Efficient Algorithm based on Immersion Simulation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 13, no. 6, pp. 583-598, 1991.
[9]FM Ham and I. Kostanic, “Principles of Neurocomputing for Science and Engineering,” McGraw-Hill, New York, 2001.
[10]R.C. Eberhart and J. Kennedy, “A new optimizer using particle swarm theory,” in Proceedings of the 6th IEEE International Symposium on Micro Machine and Human Science, pp. 39-43, Oct. 1995.
[11]J. Kennedy and R.C. Eberhart, “Particle Swarm Optimization,” IEEE International Conference on Neural Networks, vol. 4, pp. 1942-1948, 1995.
[12]M. Clerc, “Standard PSO version 2006,” http://www.particleswarm.info/ Standard_PSO_2006.c, 2006.
[13]張斐章, 張麗秋, “類神經網路, ” 東華書局, 民94年.
[14]T. Loupas, W.N. McDicken, and P.L. Allan, “An adaptive weighted median filter for speckle suppression in medical ultrasonic images,” IEEE Transactions on Circuits and Systems, vol. 36, pp. 129-135, Jan. 1989.
[15]Y. Chen, R. Yin, P. Flynn, and S.Broschat, “Aggressive region growing for speckle reduction in ultrasound images,” Pattern Recognition Letters, vol. 24, pp. 677-691, Feb. 2003.
[16]Rafael C. Gonzalez, Richard E. Woods, “Digital Image Processing,” 2nd ed., Prentice-Hall International Edition, 2002.
[17]Rein-Lien Hsu, Mohamed Abdel-Mottaleb, Anil K. Jain, “Face Detection in Color Image”, IEEE Transactions on Patten Analysis and Machine Intelligence, vol. 24, No. 5, May 2002.
[18]Y. D. Chum, S. Y. Seo, “Image Retrieval using BDIP and BVLC Moments,” IEEE Transactions on Circuits and Systems for Video Tech., vol. 13, no. 9, pp. 951-957, Sept. 2003.
[19]Chen EL, Chung PC, Chen CL, Tsai HM, Chang CI. “An automatic diagnostic system for CT liver image classification,” IEEE Transactions on Biomedical Engineering, vol. 45, no. 6, pp. 783-794, 1998.
[20]Chung-Ming Wu, Yung-Chang Chen, Kai-Sheng Hsieh. “Texture features for classification of ultrasonic liver images,” IEEE Transactions on Medical Imaging, vol. 11, no. 2, pp. 141-152, June 1992.
[21]L.D. Stefano and A. Bulgarelli, “A Simple and Efficient Connected Components Labeling Algorithm,” in Proceedings of the 10th International Conference on Image Analysis, pp. 322-327, 1999.
[22]張傳育,整合類神經網路及影像處理技術在鼻咽疾病診斷之應用,國立成功大學電機工程學系博士論文,民88。
[23]莊達峰,使用模糊化學習向量量化神經網路於鼻咽部復發腫瘤之偵測,國立雲林科技大學資訊工程研究所碩士論文,民93。
[24]Chuan-Yu Chang, Pau-Choo Chung, and Ping- Hong Lai, “Using a Spatiotemporal Neural Network on Dynamic Gadolinium-enhanced MR Images for Diagnosing Recurrent Nasal Papilloma,” IEEE Transactions Nuclear Science, vol. 49, pp. 225-238, Feb. 2002.
[25]Chuan-Yu Chang, Pau-Choo Chung, Wen-Chen Huang, and Ping-Hong Lai, “An Eigen-support Difference Operator to Fuse CT and MR Images for Nasopharyngeal Carcinoma Diagnosis,” Biomedical engineering appl., Basis & Comm., vol. 12, pp. 101-109, 2000.
[26]Chuan-Yu Chang and Da-Feng Zhuang, “A Fuzzy-Based Learning Vector Quantization Neural Network for Recurrent Nasal Papilloma Detection,” IEEE Transactions on Circuits and Systems, vol. 54, No.12, pp. 2619-2627, Dec. 2007.
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊
 
系統版面圖檔 系統版面圖檔