跳到主要內容

臺灣博碩士論文加值系統

(18.205.192.201) 您好!臺灣時間:2021/08/05 09:22
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

: 
twitterline
研究生:石慧萱
研究生(外文):Hui-HsuanShih
論文名稱:以模型為基礎的三維超音波影像分割於胎兒頭部與軀幹之量測
論文名稱(外文):Model-based Segmentation for Measurement of Head and Trunk Structures from 3D Fetal Ultrasound Images
指導教授:孫永年孫永年引用關係
指導教授(外文):Yung-Nien Sun
學位類別:碩士
校院名稱:國立成功大學
系所名稱:資訊工程學系碩博士班
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:2012
畢業學年度:100
語文別:英文
論文頁數:78
中文關鍵詞:三維超音波胎兒影像對位Active Shape Model以模型為基礎之分割
外文關鍵詞:3Dfetal ultrasound imagesActive Shape modelregistrationmodel-based segmentation
相關次數:
  • 被引用被引用:0
  • 點閱點閱:266
  • 評分評分:
  • 下載下載:3
  • 收藏至我的研究室書目清單書目收藏:0
超音波具有即時、低成本、容易使用以及非侵入性的優點,因此,在臨床上評估子宮內胎兒的生長情形大部分都使用超音波影像來進行產前檢查。透過觀察三維超音波影像中的胎兒之頭部以及軀幹整體結構,醫師可看到胎兒目前的整體成長狀態以及位於子宮內的姿態,並估測出對於此孕期重要的成長參數。然而,此孕期的超音波影像常因為胎兒的發育程度尚不完整,以及胎兒本身與子宮內膜的大量相連等問題,易造成醫師量測參數產生人為誤差以及相當大的變異;而一般胎兒超音波共通的缺陷如:訊號雜訊比太低、解剖構造不明顯等缺陷更是加大了量測上的難度。本論文為發展一套自動化三維超音波影像胎兒頭部與軀幹結構分割系統,提出一個以模型為基礎之分割方法,完成自動化的胎兒頭部與軀幹結構分割,來輔助醫師量測三項具臨床意義之外觀成長參數。
在本論文所提出以模型為基礎的分割方法,首先我們藉由實際影像資料分別建立出胎兒頭部與軀幹之統計性模型,再由專家定義所要量測的標記點。接著,我們利用特徵點建立出座標系,以進行模型與影像的對位,完成模型之位置與方向的初始化。然後我們利用Active Shape Model的限制讓模型形變至一個靠近影像中目標邊界的合理的形狀後,再設計一個根據模型附近的影像環境變化的幾何形狀限制與影像特性之能量函數,來補償模型因Active Shape Model限制而無法貼合到的部份目標邊緣。我們利用三維模型的形變,克服了上述複雜之超音波影像缺陷並完成胎兒頭部與軀幹分割,並且將自動化量測之結果與專家手動量測之結果進行比較,從實驗當中可得到令人滿意的結果 (影像分割平均誤差小於2個像素)。
Ultrasound image (US) has been widely used for the diagnosis in clinical of gynecology. As the US image is inexpensive, easy to use, non-invasive real time and without radiation hazards, it has become the most popular imaging modality in recent years. More specifically, doctors can observe the real-time posture of fetus and evaluate the fetal growth in the uterus by using 3D ultrasound images during prenatal care. However, due to the difficulties in treating highly-noise US images, the fully automatic image segmentation tool for the fetal ultrasound is still lack. Different to previous studies in US image segmentations for the second or the third trimester, we focus on the analysis of fetus image of the first trimester. In addition to the speckle noise and fuzzy boundaries, there are other important artifacts in the first-trimester fetal US image; such as the blurred image boundaries due to poor fetal development, or the weak edges due to the attachment of endometrium to fetus. Thus, we proposed a model-based segmentation method to automatically segment the fetal head and trunk structures, which assist doctors to measure the fetal parameters for clinical evaluations. First, we construct the statistical shape models of both fetal head and trunk by using the expert-adjusted mesh shapes from training volume images. Second, by using some anatomical feature points in target volume image, we define the local coordinate system to initially align the shape model and image data. Third, we apply the Active Shape Model (ASM) mechanism to adjust the shape model with a limited number of shape components. Thus, the global shape of the deformed model can mostly fit to the fetal boundaries. However, some local shape deviations still exist between the deformed shape and the actual image boundaries. Consequently, we design a 3D freeform deformation by using snake algorithm to improve the fitness between model and image. The experimental results show that the proposed method overcomes the difficulties and achieves good consistency between the automatic and manual measurements.
CHAPTER 1 INTRODUCTION...1
1.1 Motivation...1
1.2 Related Work...3
1.3 Thesis Organization and System Flow Chart...7
CHAPTER 2 EXPERIMENTAL MATERIAL...9
CHAPTER 3 CONSTRUCTION OF STATISTICAL SHAPE MODEL...11
3.1 Initial manually-segmented mesh model construction...12
3.2 Adaptation of Training Shapes...15
3.2.1 Image Preprocessing...19
3.2.2 Anatomical Feature-based Registration...22
3.2.3 Position Correction of the prototype models...30
3.2.4 Model Scaling...33
3.2.5 3D Deformation with Manual Adjustment...35
3.3 Statistics of the training set...38
CHAPTER 4 MODEL BASED SEGMENTAION...42
4.1 Active Shape Model Adaptation...43
4.2 Local freeform Deformations...47
4.2.1 Image feature classification according to the environments...49
4.2.2 3D Dynamic Deformation...52
CHAPTER 5 EXPERIMENTAL RESULT...58
5.1 Accuracy Evaluation of Segmentation Results...58
5.2 Clinical Parameters Measurement...61
5.3 The Result of Segmentation...64
5.3.1 Segmentation result of 2D planes...64
5.3.2 Appearance of 3D deformable model...67
CHAPTER 6 CONLUSION AND FUTURE WORK...71
6.1 Conclusion...71
6.2 Future Work...73
REFERENCES...75
VITA...78
[1]Hsin-Chen Chen, Pei-Yin Tsai, Hsiao-Han Huang, Hui-Hsuan Shih, Yi-Yang Wang, Chiung-Hsin Chang, and Yung-Nien Sun “Registration-Based Segmentation of Three-Dimensional Ultrasound Images For Quantitative Measurement of Fetal Craniofacial Structure, Ultrasound in Med. & Biol. Vol. 22, No. 8, pp. 1005 - 1013, August 2012
[2]T.F. Cootes, C.J.Taylor, D.H.Cooper, and J.Graham, “Active Shape Models—Their Training and Application, Computer vision and Image Understanding, Vol. 61, No. 1, pp. 38 - 59, January 1995.
[3]T.F.Cootes, and C.J.Taylor,“Active Shape Models—Smart Snake.
[4]Olivier Ecabert, Jochen Peters, Hauke Schramm, Cristian Lorenz, Jens von Berg, Matthew J. Walker, Mani Vembar, Mark E. Olszewski, Krishna Subramanyan, Guy Lavi, and Jürgen Weese, “Automatic model-based segmentation of the heart in CT images, IEEE Transactions on Medical Imaging, Vol. 27, No. 9, pp. 1189 - 1201, September 2008.
[5]Shyh-Roei Wang, Yung-Nien Sun, and Fong-Ming Chang, “Artifact removal and texture-based rendering for visualization of 3D fetal ultrasound images, Med Biol Eng Comput., Vol. 46, pp. 575 - 588, 2008.
[6]Ruey-Feng Chang, Wen-Jie Wu, Woo Kyung Moon,Wei-Ming Chen, Wei Lee and Dar-Ren Chen, “Segmentation of Breast Tumor In Three-Dimensional Ultrasound Images Using Three-Dimensional Discrete Active Contour Model, Ultrasound in Med. & Biol., Vol. 29, No. 11, pp. 1571 - 1581, April 2003.
[7]Dinggang Shen, Yiqiang Zhan, and Christos Davatzikos, “Segmentation of prostate boundaries from ultrasound images using statistical shape model, IEEE Transactions on Medical Imaging, Vol. 22, No. 4, pp. 539 - 551, April 2003.
[8]Jinhua Yu,Yuanyuan Wang, Ping Chen, and Yuzhong Shen, “Fetal abdominal contour extraction and measurement in ultrasound images, Ultrasound in Med. & Biol., Vol. 34, No. 2, pp. 169 - 182, 2008.
[9]http://www.gehealthcare.com/
[10]http://www.cirsinc.com/065_20_ultra.html
[11]Qingling Sun, John A. Hossack, Jinshan Tang, and Scott T. Acton, Speckle reducing anisotropic diffusion for 3D ultrasound images, Computerized Medical Imaging and Graphics 28 (2004), pp. 461 - 470.
[12]William E. Lorensen and Harvey E. Cline, “Marching cubes: a high resolution 3D surface construction algorithm, Computer Graphics, Vol. 21, No. 4, pp. 163 - 169, July 1987.
[13]Michael Garland and Paul S. Heckbert, “Surface simplification using quadric error metrics, SIGGRAPH, pp. 209 - 216, 1997.
[14]http://meshlab.sourceforge.net/
[15]Chenyang Xu and Jerry L. Prince, “Snakes, shapes, and gradient vector flow, IEEE Transactions on Image Processing, Vol. 7, No. 3, pp. 359 - 369, March 1998.
[16]Maurizio Pilu, Andrew W. Fitzgibbon, and Robert B. Fisher, “Ellipse-specific direct least-square fitting, IEEE International Conference on Image Processing, Lausanne, pp. 599 - 602, September 1996.
[17]Robert W. Sumner and Jovan Popovi´c, “Deformation transfer for triangle meshes, SIGGRAPH, pp. 399 - 405, 2004
[18]B.S. Manjunath and W.Y. Ma, “Texture features for browsing and retrieval of image data, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 18, No. 8, pp. 837 - 842, August 1996.
[19]Wei Lu, Jinglu Tan, and Randall Floyd, “Automated fetal head detection and measurement in ultrasound images by iterative randomized Hough transform, Ultrasound in Med. & Biol., Vol. 31, No. 7, pp. 929 - 936, 2005.
[20]Abele H, Wagner N, Hoopmann M, Grishke EM, Wallwiener D, Kagan KO, “Effect of deviation from the mid-sagittal plane on the measurement of fetal nuchal translucency, Ultrasound Obstet Gynecol, Vol. 35, pp. 525 - 529, 2010.
[21]Anquez J, Angelini ED, Bloch I, “Automatic segmentation of head structures on fetal MRI, Proc IEEE ISBI (Boston, MA) 2009;109–112.
[22]Becker BG, Cosio FA, Huerta MEG, Benavides-Serralde JA, “Automatic Segmentation of the cerebellum of fetuses on 3-D ultrasound images using 3-D point distribution model, Conf IEEE EMBS (Buenos Aires, Argentina) 2010;4731–4734.
[23]Ning Hu, Do´ nal B. Downey, Aaron Fenster, Hanif M. Ladak., “Prostate boundary segmentation from 3D ultrasound images, Medical Physics, Vol. 30, pp. 1649 - 1659, July 2003.
[24]Jérémie Anquez, Elsa D. Angelini, Isabelle Bloch, “Segmentation of Fetal 3D Ultrasound Based on Statistical Prior and Deformable Model, Biomedical Imaging: From Nano to Macro, 14-17May 2008.
[25]JYu-Bu Lee, Min-Jeong Kim, Myoung-Hee Kim, “Robust border enhancement and detection for measurement of fetal nuchal translucency in ultrasound images, Med Bio Eng Comput, Vol. 45, pp. 1143 - 1152, 2007.
[26]F P Hadlock, R L Deter, R B Harrist and S K Park, “Estimating fetal age: computer-assisted analysis of multiple fetal growth parameters, Radiology, Vol. 152, pp. 497-501, 1984.
[27]Michael R. Kaus, Vladimir Pekar, Christian Lorenz, Roel Truyen, Steven Lobregt, and Jürgen Weese, “Automated 3-D PDM construction from segmented images using deformable models, IEEE Transactions on Medical Imaging, Vol. 22, No. 8, pp. 1005 - 1013,August 2003.
連結至畢業學校之論文網頁點我開啟連結
註: 此連結為研究生畢業學校所提供,不一定有電子全文可供下載,若連結有誤,請點選上方之〝勘誤回報〞功能,我們會盡快修正,謝謝!
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top