在現今的社會環境不斷地快速變遷之下，人們的生活形態也不斷地在改變，最直接的影響就是人們罹患疾病的情況增加了，其中以慢性病和骨科疾病為大宗。在骨科疾病當中又以關節和脊椎的病變占最大多數，脊椎的病變所引起的症狀輕則四肢麻痺，重則導致肌肉萎縮、局部癱瘓和大小便失禁等。因此，此類病患就必須要施行脊椎融合術等手術來改善身體的疾病。在手術後醫生觀測復原的程度是依據骨頭融合的面積，但是以往都是醫生用手描繪出融合的輪廓，這個部份不夠客觀。
因此本論文發展了一套系統，希望能達到自動擷取輪廓，並且計算骨頭融合面積的目的。由於X光影像特性的關係，其對比度不夠清晰，因此本論文使用了形態學的影像強化技術來增加影像的對比度加強輪廓的資訊。接著再利用等位函數法找輪廓的優點就可以精確的找到融合後的輪廓並且加以計算其面積，如此便能減少人為介入的因素，手術成果及數據將更為客觀。

Nowadays, the life style of people keeps changing. The most direct effect is that situations of suffering from the disease increase. Among them, the most serious diseases are chronic and orthopedic diseases. Many cases of orthopedic diseases were joint and spinal diseases. Spinal disease may cause your hands and feet paralysed, even lead muscle atrophy and incontinence. Therefore, patients need Spinal Fusion Surgery to cure the disease. After performing surgery, the doctor will observe the recovery according to the fusion area. But the fusion area was draw manual on the X-ray imaging in the past, it depend on doctors' experiences. For this reason, the result of fusion area was not objective.
In this thesis, we develop a system which can capture the fusion area automatically. Because of the characteristic of X-ray imaging, its contrast is not clear. We use the morphological image enhance technical and Level Set Method in order to capture the fusion area accurately and measure the fusion area. So we can reduce the errors of people’s intervention, the result of surgery and data will be more objective.

目錄
指導教授推薦書
口試委員審定書
長庚大學博碩士論文著作授權書......iii
誌謝......iv
摘要......v
Abstract......vi
目錄......vii
圖目錄......x
表格目錄......xii
第一章 緒論......1
1-1 前言......1
1-2 動機及目的......1
2-1 背景 ......4
2-2脊椎結構......6
2-2-1脊椎的組成......6
2-2-2 脊椎融合術......7
2-3 文獻探討......9
2-3-1 X光影像的對比度強化......10
2-3-2 X光影像的分割......11
2-3-3 自動化的影像處理系統 ......12
2-4 影像處理技術......14
2-4-1 直方圖均衡化......15
2-4-2 形態學影像處理(Morphological Image Processing)......18
2-4-3 形態學影像強化......20
2-4-4 等位函數法......22
第三章 研究方法與流程......25
3-1 影像取得......25
3-2 實驗流程......27
第四章 結果與討論......37
4-1 評估指標......38
4-2 等位函數法執行結果......41
4-3 融合面積的計算......45
4-4 實驗結果評估......45
第五章 結論......48
參考文獻......50
圖目錄
圖1、脊椎融合術X光影像......9
圖2、暗的影像經過直方圖均衡化處理結果......16
圖3、亮的影像經過直方圖均衡化處理結果......17
圖4、低對比度影像經過直方圖均衡化處理結果......17
圖5、高對比度影像經過直方圖均衡化處理結果......18
圖6、影像膨脹與影像侵蝕結果...... 19
圖7、影像斷開與影像閉合結果 ......20
圖8、形態學影像強化結果......21
圖9、等位函數法示意圖......23
圖10、手術前影像......25
圖11、手術後影像......26
圖12、醫生手繪輪廓影像......26
圖13、實驗流程圖......27
圖14、步驟(一)流程圖......28
圖15、校正後影像......29
圖16、手術前影像強化結果......30
圖17、脊椎的二值化影像......30
圖18、脊椎的線段......31
圖19、初始輪廓......31
圖20、步驟(二)流程圖......32
圖21、手術後影像之強化結果 ......33
圖22、利用二值化方法處理強化過後的影像結果......34
圖23、利用形態學影像處理填滿輪廓內部結果......34
圖24、加入脊椎線段結果......35
圖25、步驟(三)流程圖......35
圖26、執行等位函數法結果......36
圖27、脊椎融合術X光影像......37
圖28、自動化切割與醫生手動切割輪廓重疊示意圖...... 38
圖29、影像類型一實驗結果......41
圖30、影像類型一實驗結果比較......41
圖31、影像類型二實驗結果......42
圖32、影像類型二實驗結果比較......42
圖33、影像類型三實驗結果......43
圖34、影像類型三實驗結果比較......43
圖35、影像類型四實驗結果......44
圖36、影像類型四實驗結果比較......44
表格目錄
表格1、面積計算結果......45
表格2、左邊輪廓比較結果......46
表格3、右邊輪廓比較結果......46
表格4、整張影像比較結果......46

參考文獻
英文部分
[1]A. S. Issever, et al., “Local differences in the trabecular bone structure of the proximal femur depicted with high-spatial resolution MR imaging and multisection CT,” Academic Radiology, vol. 9, no. 12, pp. 1395-1406, 2002
[2]C. M. Chen, et al., “Breast lesions on sonograms: Computer-aided diagnosis with nearly setting-independent features and artificial neural networks,” Radiology, vol. 226, no. 2, pp. 504-514, 2003.
[3]Y. L. Huang, et al., “Diagnosis of Hepatic Tumors with Texture Analysis in Non-enhanced CT Images,” Academic Radiology, vol. 13, no. 6, pp. 713-720, 2006.
[4]W. J. Chen, et al., “The fusion Rate of Calcium Sulfate with Local Autograft Bone Compared with autologous Iliac Bone Graft for Instrumented short-Segment Spinal fusion,” Spine, vol. 30, no. 20, pp. 2293-2297, 2005.
[5]Cowan, et al., “Changes in the utilization of spinal fusion in the United. States,” Neurosurgery, vol. 59, no. 1, pp. 15-20, 2006.
[6]R. A. Hibbs, “An operation for progressive spinal deformity,” NY MedJ, vol. 21, pp. 1013-1016, 1911.
[7]F. H. Albee, “Transplantation of a portion of the tibia into the spine for Pott’s disease,” J Am Med Assoc, vol. 57, pp. 855-858, 1911.
[8]R. F. Closkey, et al., “Mechanics of Interbody spinal Fusion,” Spine, vol. 18, no. 8, pp. 1011-1015, 1993.
[9]J. A. Goulet, et al., “Autogenous Iliac crest bone graft,” Clin Orthop Relat R, vol. 339, pp. 76-81, 1997.
[10]H. Nakamura, et al., “Use of folded vascularized rib graft in anterior fusion after treatment of thoracic and upper lumbar lesion,” J Nerosurg, vol. 94, no. 2, pp. 323-327, 2001.
[11]P. H. Liu, et al., “Integration of CAD and FE method to simulate the pedicle screw within the vertebra,” J Med Biol Eng, vol. 21, no. 3, pp. 175-182, 2001.
[12]M. R. Sarkar, et al., ”Defect Reconstruction in Articular Calcaneous Fractures with a Novel Calcium Phosphate Cement,” European Journal of Trauma, vol. 28, no. 6, pp. 340-348, 2002.
[13]M. Kass, et al., “Snake: Active Contour Models,” International Journal of Computer Vision, vol. 1, no. 4, pp.321-331, 1988.
[14]Y. Jianga, and P. Babynb, “X-ray bone fracture segmentation by incorporating global shape model priors into geodesic active contours,” International Congress Series, vol. 1268, pp. 219-224, 2004
[15]J. Zhou and M. Abdel-Mottaleb, “A content-based system for human identification based on bitewing dental X-ray images,” Pattern Recognition, vol. 38, no. 11, pp. 2132-2142, 2005.
[16]R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2/e, Princeton, pp. 92~98, 2006.
[17]R. C. Gonzalez and R. E. Woods, Digital Image Processing, 2/e, Princeton, pp. 555~604, 2006.
[18]A. K. Jain, et al., “Dental Biometrics: Human Identification Using Dental Radiographs,” Fourth International Conference on Audio- and Video-Based Biometric Person Authentication, pp. 429-437, 2003.
[19]D. P. Huttenlocher, et al., “Comparing images using the Hausdorff distance,” IEEE Transactions on PAMI vol. 15, no 9, pp. 850-863, 1993.
[20]D. C. Chang and W. R. Wu, “Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation,” IEEE Transactions On Medical Imaging, vol. 17, no. 4, pp. 518-531, 1998.
[21]I. Frosio, et al., “Enhancing Digital Cephalic Radiography With Mixture Models and Local Gamma Correation,” IEEE Transaction On Medical Imaging, vol. 25, no.1, pp. 113-120, 2006.
[22]C. C. Han, et al., “Hand radiograph image segmentation using a coarse-to-fine strategy,” Pattern Recognition, vol. 40, no. 11, pp. 2994-3004, 2007.
[23]S. Osher and J. Sethian, “Fronts propagating with curvature-dependent speed Algorithms based on Hamilton-Jacobi Equations,” J. Comput. Phys., vol. 79, no. 1, pp. 12-49, 1998.
中文部分
[24]2006年5月工研院產業經濟與趨勢研究中心報告。
網頁部分
[25]http://zh.wikipedia.org/，Wikipedia 維基百科。