腕隧道症候群是因為腕隧道內的正中神經受到壓迫造成手部麻痺，為一種臨床上常見的上肢神經病變。傳統診斷的方式是利用電刺激的診斷法，而這種方式的缺點在於診斷時間過長且會對病人造成負擔，超音波影像系統相較之下便有著影像擷取容易、非侵入式且可以減低診斷時間。從臨床的影像中我們經由手指帶動肌腱，使得影像中的正中神經相較於其他組織有著較為一致性的位移向量，因此我們的演算法便對兩張時間間隔約0.1秒的影像作影像追蹤來得到影像間各像素的位移量，並且使用兩組影像追蹤後的結果，取交集來減低背景雜訊造成的誤差，從位移向量分析加以得到正中神經的位置，並且使用圓盤擴張法和橢圓修正的方式來得到最後的圈選結果。從橢圓的參數中我們可以計算正中神經經過圈選後的扁平率(長短軸比例)與面積，且研究中考量到受測者與環境的因素，所以我們將受測者前手臂正中神經當作標準化的因子，並使用雙重參數來診斷腕隧道症候群，而最後的分析中可以使得準確率達到83%且特異性達到75%(第三層面積與第二層和第四層的扁平率比例)。研究中還利用這種一致性位移的特性來對影像作複合技術的處理，這種複合影像的技術使得我們的影像品質得到改善，並且把原始影像與複合影像給受測者們圈選，和臨床醫師所判定的標準輪廓比較，從重疊區域的分析方式中得知受測者判斷正中神經位置的正確率從0.2提昇至0.8，而從邊緣輪廓的分析下得知邊緣並未因為模糊化而使得圈選結果失真，也證明了此種複合技術得到的影像對於受測者判斷正中神經上有所幫助。

[1] R. Beekman, and L. H. Visser, “Sonography in The Diagnosis of Carpal Tunnel Syndrome: A Critical Review of The Literature,” Muscle & Nerve, vol. 27, pp. 26-33, 2003.
[2] E. Pascarelli, and D. Quilter, 電腦族 小心RSI，林瑞瑛譯，台北市，培根文化, 1998.
[3] S. M. Fried, 電腦族症候群，婁愛蓮譯，台中市，晨星，2002.
[4] K. Col., 電腦族手腕症候群，台北市，文萱坊，1999.
[5] J. A. Delisa, K. MacKenzie, E. M. Baran, Manual of Nerve Conduction Velocity and Somatosensory Evoked Potentials, pp. 1-5, 1987.
[6] J. D. P. Bland, “A Neurophysiological Grading Scale for Carpal Tunnel Syndrome,” Muscle & Nerve, vol. 23, pp. 1280-1283, 2000.
[7] W. H. Cheng, S. T. Shie, 當代醫學, vol. 26, pp. 94-100, 1999.
[8] K. I. Nakamichi, “Enlarged Median Nerve in Idiopathic Carpal Tunnel Syndrome”, Muscle & Nerve, vol. 23, pp. 1713-1718, 2000.
[9] E. R. Wiesler, “The Use of Diagnostic Ultrasound in Carpal Tunnel Syndrome,” J Hand Surgery, vol. 31A, pp. 726-732, 2006.
[10] W. Buchberger, “High-Resolution Ultrasonography of the Carpal Tunnel,” J Ultrasound in Medicine, vol. 10, pp. 531-537, 1991.
[11] I. Duncan, “Sonography in the Diagnosis of Carpal Tunnel Syndorme,” AM J Roentgenol, vol. 173, pp. 681-684, 1999.
[12] M. Keberle, “Technical Advances in Ultrasound and MR Imaging of Carpal Tunnel Syndrome,” European Radiology, vol. 10, pp. 1043-1050, 2000.
[13] 李維寧, “Efficient Speckle Tracking Technique and Its Applications in Ultrasonic Breast Imaging,” 碩士論文, 國立台灣大學電機工程研究所, 2003.
[14] D. P. Shattuck, and O. T. von Ramm, “Compound Scanning with a Phased Array,” Ultrasonic Imaging, vol. 4, pp. 93-107, 1982.
[15] P. C. Li and M. O’Donnell, “Eleveational Spatial Compounding,” Ultrasonic Imaging, vol. 16, pp. 176-189, 1994.
[16] P. C. Li, and M. J. Chen, “Strain Compounding: A New Approach for Speckle Reduction,” IEEE Trans. Ultrasonics Ferroelectrics and Frequency Control, vol. 49, pp. 39-46, 2002.
[17] F. Yeung, “Multilevel and Motion Model-Based Ultrasonic Speckle Tracking Algorithms,” Ultrasound in Medicine & Biology, vol. 24, No.3, pp. 427-441, 1998.
[18] C. H. Li, and L. H. Chen, “A Fast Motion Estimation Algorithm Based on the Block Sum Pyramid,” IEEE Trans. Image Processing. vol. 6, pp. 1587-1591, 1997.
[19] Y. S. Chen, T. D. Lin, “An Iterative Approach to Removing the Closure Noise Using Disk Expansion Method,” IEEE Signal Processing Letters, vol. 2, pp. 105-107, 1995.
[20] C. B., Burckhardt, “Speckle in Ultrasound B-mode Scans,” IEEE Trans. Sonics & Ultrasonics, vol. 25, pp.1-6, 1978.
[21] R. F. Wagner, et al., “Statistics of Speckle in Ultrasound B-Scans,” IEEE Trans. Sonics & Ultrasonics, vol. 30, pp.156-163, 1983.
[22] A. Madabhushi, and D. N. Metaxas, “Combining low-. High-level and Empirical Domain Knowledge for Automated Segmentation of Ultrasonic Breast Lesions,” IEEE Trans. Medical Imaging, vol. 22, pp.155-169, 2003.
[23] J. C. Bezdek, “Fuzzy Mathematics in Pattern Classification,” PhD thesis, Applied Math. Center, Cornell University, Ithaca, 1973.
[24] Y. S Cheng, Y C Hsu, “Image Segmentation of a Color-Blindness Plate,” Applied Optics, vol. 33, pp.6818-6822, 1994.