進階搜尋


下載電子全文  
系統識別號 U0026-1708201306354100
論文名稱(中文) 四維超音波影像之肌肉組織運動量測研究
論文名稱(英文) A Study on Motion Estimation of Muscular Structure from 4-D Ultrasound Image
校院名稱 成功大學
系所名稱(中) 資訊工程學系碩博士班
系所名稱(英) Institute of Computer Science and Information Engineering
學年度 101
學期 2
出版年 102
研究生(中文) 蔡季紘
研究生(英文) Chi-Hung Tsai
學號 P76004512
學位類別 碩士
語文別 英文
論文頁數 74頁
口試委員 指導教授-孫永年
口試委員-蘇芳慶
口試委員-李同益
口試委員-李建德
口試委員-蔡清欉
中文關鍵字 運動預測  四維超音波影像  旋轉不變性特徵  卡爾曼濾波器 
英文關鍵字 motion estimation  4-D ultrasound  rotation invariant feature  Kalman filter 
學科別分類
中文摘要 利用超音波量測肌肉組織運動可以幫助調查骨骼肌肉的病理原因,然而超音波影像品質容易受到斑點雜訊的影響,造成組織運動量測的困難。為解決上述提及之問題,本論文提出基於模型之利用卡爾曼濾波器與旋轉不變特徵的追蹤演算法,用以追蹤四維超音波影像中的肌束膜。本方法於超音波序列影像中,自訂初始時間點的肌束膜模型,利用旋轉不變特徵定義肌束膜模型邊界,使模型具有該組織之結構與特性,接著卡爾曼濾波器估計下一個時間點該組織模型的預測運動狀態,即下個時間點的預測位置,並利用旋轉不辨特徵於預測位置附近找出最佳特徵匹配位置,即下個時間點的測量位置;最後卡爾曼濾波器會給予預測位置與測量位置權重值,於其中取得一平衡值,即為下個時間點的組織位置;卡爾曼濾波器會持續將計算出來的組織位置作為下一個時間點之先驗運動狀態,持續更新下一個時間點的運動狀態,直至影像序列中最後一張影像。
本論文所提出的方法有效地結合的影像組織結構和運動先驗概率,可以克服前述之困難,並且經由實驗可得知本方法能夠可靠並準確的估計組織運動狀況。
英文摘要 Muscular motion estimation in ultrasound images is of great importance for investigating causes of musculoskeletal conditions in pathological examinations. However, the quality of ultrasound images is usually depressed due to temporal decorrelation of speckle patterns, making certain difficulties in motion estimation. To resolve the problem, this study presents a new model-based tracking method for estimating the perimysium motion from 4-D ultrasound images. From the first frame of the given motion images, the proposed method builds a perimysium model, which consists of 3-D surface and rotation-invariant feature descriptor (RIFD) to characterize its structural and image appearances. Then, the model is applied to the next frame using Kalman filter for estimating the best matching position with the highest similarity of RIFD. The estimation is used to update the motion state for predicting and refining the model position in the next frame. The Kalman filtering is iteratively performed until the entire image sequence is processed. Overall, the proposed method efficiently combines the structure, image and motion priors, so it can overcome the aforementioned difficulties. Experimental results showed that the proposed method can provide reliable and accurate estimation of perimysium motion from 4-D ultrasound volumes.
論文目次 CHAPTER 1 INTRODUCTION ........... 1
1.1 Motivation ............. 1
1.2 Related Works ............. 2
1.3 Overview of the Proposed Method and Thesis Organization.... 5
CHAPTER 2 MATERIALS ........... 8
2.1 4-D Ultrasonography........... 8
2.2 4-D Ultrasonographic Properties......... 10
CHAPTER 3 4-D MOTION ESTIMATION SYSTEM....... 17
3.1 System Architecture ............ 17
3.2 Perimysium Model Construction .......... 17
3.2.1 Double-Mesh Surface......... 18
3.2.2 Rotation-Invariant Feature Descriptor ....... 21
3.3 Kalman Filtering ........... 24
3.3.1 Motion State Prediction.......... 25
3.3.2 RIFD Matching .......... 27
3.3.3 Measurement Updating .......... 27
3.4 Perimysium Model Updating .......... 28
CHAPTER 4 EXPERIMENTAL RESULTS AND DISCUSSION ..... 31
4.1 Experiment Description........... 31
4.2 Results of in vivo Musculoskeletal Ultrasonography...... 32
4.2.1 Experiments on proposed motion estimation algorithm .... 32
4.2.2 Comparison proposed method between model and point .... 56
4.2.3 Comparison proposed method with and without Kalman filter ... 59
4.3 Validation............. 61
CHAPTER 5 CONCLUSIONS AND FUTURE WORK....... 70
5.1 Conclusions ............. 70
5.2 Future Work............. 71
REFERENCES.............. 72
參考文獻 [1] C. Nofsinger and J. G. Konin, "Diagnostic ultrasound in sports medicine current concepts and advances," Sports Med Arthrosc, vol. 17, pp. 25-30, 2009.
[2] A. W. Clarke, M. Ahmad, M. Curtis, and D. A. Connell, "Lateral elbow tendinopathy : Correlation of ultrasound findings with pain and functional disability," Am J Sports Med, vol. 38, pp. 1209-14, 2010.
[3] T. D. Zordo, S. R. Lill, C. Fink, G. M. Feuchtner, W. Jaschke, R. Bellmann-Weiler, et al., "Real-Time Sonoelastography of Lateral Epicondylitis: Comparison of Findings Between Patients and Healthy Volunteers," American Journal of Roentgenology, vol. 193, pp. 180-185, 2009.
[4] Y. Yoshii, H. R. Villarraga, J. Henderson, C. Zhao, K.-N. An, and P. C. Amadio, "Speckle tracking ultrasound for assessment of the relative motion of flexor tendon and subsynovial connective tissue in the human carpal tunnel," Ultrasound in Med. & Biol., vol. 35, pp. 1973-81, 2009.
[5] P. Brown, J. Alsousou, M. Thompson, and A. Noble, "Controlled motion strain measurement using lateral speckle tracking in Achilles tendons during healing," in Biomedical Imaging (ISBI), 2012 9th IEEE International Symposium on, 2012, pp. 1104-1107.
[6] H.-H. Nagel and W. Enkelmann, "An Investigation of Smoothness Constraints for the Estimation of Displacement Vector Fields from Image Sequences," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. PAMI-8, pp. 565-593, 1986.
[7] R. E. Kalman, "A New Approach to Linear Filtering and Prediction Problems," Transactions of the ASME - Journal of Basic Engineering, vol. 82, pp. 35-45, 1960.
[8] L. Yuh-Hwan, C. Shu-Min, L. Chi-Yi, H. Chung-l, and S. Yung-Nien, "Motion Tracking on Elbow Tissue from Ultrasonic Image Sequence for Patients with Lateral Epicondylitis," in Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE, 2007, pp. 95-98.
[9] T. Zakaria, Q. Zhao, and R. L. Maurice, "Optical-Flow-Based B-Mode Elastography: Application in the Hypertensive Rat Carotid," Medical Imaging, IEEE Transactions on, vol. 29, pp. 570-578, 2010.
[10] E. Soleimani, M. M. Dizaji, and H. Saberi, "Carotid artery wall motion estimation from consecutive ultrasonic images: Comparison between block-matching and maximum-gradient algorithms," J Tehran Heart Cent., vol. 6, pp. 72-78, 2011.
[11] M. G. Danilouchkine, F. Mastik, and A. F. W. Van der Steen, "Improving IVUS
73
palpography by incorporation of motion compensation based on block matching and optical flow," Ultrasonics, Ferroelectrics and Frequency Control, IEEE Transactions on, vol. 55, pp. 2392-2404, 2008.
[12] K. A. Patwardhan, Y. Yongjian, S. Gupta, A. Dentinger, and D. Mills, "4D vessel segmentation and tracking in Ultrasound," in Image Processing (ICIP), 2012 19th IEEE International Conference on, 2012, pp. 2317-2320.
[13] A. Gastounioti, S. Golemati, J. Stoitsis, and K. S. Nikita, "Kalman-filter-based block matching for arterial wall motion estimation from B-mode ultrasound," in Imaging Systems and Techniques (IST), 2010 IEEE International Conference on, 2010, pp. 234-239.
[14] D. G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," International Journal of Computer Vision, vol. 60, pp. 91-110, 2004.
[15] W. M. Hafizah, E. Supriyanto, and J. Yunus, "Feature Extraction of Kidney Ultrasound Images Based on Intensity Histogram and Gray Level Co-occurrence Matrix," in Modelling Symposium (AMS), 2012 Sixth Asia, 2012, pp. 115-120.
[16] Y. Wentao, Q. Ming, L. Niu, and Z. Hairong, "An Image-Based Method for Real Time Ultrasonic Microbubble Concentration and Velocimetry Quality Evaluation in Echo PIV Technique," in Bioinformatics and Biomedical Engineering (iCBBE), 2010 4th International Conference on, 2010, pp. 1-4.
[17] W. Gomez, W. C. A. Pereira, and A. F. C. Infantosi, "Analysis of Co-Occurrence Texture Statistics as a Function of Gray-Level Quantization for Classifying Breast Ultrasound," Medical Imaging, IEEE Transactions on, vol. 31, pp. 1889-1899, 2012.
[18] F. R. Mauldin, F. Viola, and W. F. Walker, "Complex principal components for robust motion estimation," Ultrasonics, Ferroelectrics and Frequency Control, IEEE Transactions on, vol. 57, pp. 2437-2449, 2010.
[19] B. D. de Senneville, M. Ries, G. Maclair, and C. Moonen, "MR-Guided Thermotherapy of Abdominal Organs Using a Robust PCA-Based Motion Descriptor," Medical Imaging, IEEE Transactions on, vol. 30, pp. 1987-1995, 2011.
[20] R. J. Schneider, D. P. Perrin, N. V. Vasilyev, G. R. Marx, P. J. del Nido, and R. D. Howe, "Real-time image-based rigid registration of three-dimensional ultrasound," Medical Image Analysis, vol. 16, pp. 402-414, 2// 2012.
[21] X. Lu, S. Zhang, W. Yang, and Y. Chen, "SIFT and shape information incorporated into fluid model for non-rigid registration of ultrasound images," Computer Methods and Programs in Biomedicine, vol. 100, pp. 123-131, 11// 2010.
[22] Available: http://www.gehealthcare.com/euen/ultrasound/flash/voluson-e8/v2.html
[23] J. C. Thompson, Netter's Concise Atlas of Orthopaedic Anatomy: Saunders, 2001.
74
[24] E. N. Marieb, Human Anatomy & Physiology: Benjamin Cummings, 2003.
[25] M. Sakalli, L. Kin-Man, and Y. Hong, "A faster converging snake algorithm to locate object boundaries," Image Processing, IEEE Transactions on, vol. 15, pp. 1182-1191, 2006.
[26] P. Scovanner, S. Ali, and M. Shah, "A 3-dimensional sift descriptor and its application to action recognition," presented at the Proceedings of the 15th international conference on Multimedia, Augsburg, Germany, 2007.
[27] G. Welch and G. Bishop, "An Introduction to the Kalman Filter," Department of Computer Science, University of North Carolina at Chapel Hill, Chapel Hil2006.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2016-09-05起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2016-09-05起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw