本論文實現一套自動針對三維椎節模型進行特徵擷取的演算法。首先對人體電腦斷層掃描影像先進行椎節的三維脊椎建模與分節，接著對結構分析後的三維椎節進行擷取特徵點。論文擷取出來的特徵點可提升應用於脊椎側彎之椎弓根釘導版的安全性。此基於三維椎節資料設計出來的特徵點，包含了椎弓根釘導版的鑽孔位置、入射角以及深度。智慧三維模型建構、設計和驗證的軟件系統有望為未來的骨科脊柱外科手術和康復的應用。本系統可實現商業化，並促進全球衛生保健系統。

This paper presents an algorithm to extract 3D feature points of the 3D vertebrae model. First, the system will model and segmentation the 3D Vertebral from the medical CT images. Second, the structure analyzed Vertebra will use to extract 3D feature points. These feature points aim at enhancing the safety of transpedicular drill guide (TDG) in the posterior spinal fusion. The designed parameters of the drill, including inserted position, angle, and depth, are generated to construct the dill template based on a spinal 3D structure database. An intelligent 3D model construction, design, and verification software system is expected for future orthopaedics spinal surgery and rehabilitation applications. Furthermore, this system can be commercialized and promoted to global healthcare systems.

目錄
中文審定書……………………………………………………ii
英文審定書……………………………………………………iii
公開授權書……………………………………………………iii
致謝……………………………………………………iv
中文摘要……………………………………………………v
英文摘要……………………………………………………vi
目錄……………………………………………………vii
圖次……………………………………………………viii
表次……………………………………………………x
第一章 導論……………………………………………………1
1.1 概論……………………………………………………1
1.2 動機及目的……………………………………………………3
1.3 貢獻……………………………………………………4
1.4 章節提要……………………………………………………5
第二章 相關技術……………………………………………………7
2.1主動形狀模型……………………………………………………7
2.2區域成長……………………………………………………10
2.3迭代最近點演算法……………………………………………………11
第三章 3D列印椎節導版之自動路徑規劃系統 ……………………………………………………13
3.1脊柱分節……………………………………………………14
3.2路徑規劃系統……………………………………………………20
第四章 實驗結果……………………………………………………23
第五章 結論……………………………………………………28
參考文獻……………………………………………………29

[1] Kabins, Mark B., and James N. Weinstein, “The history of vertebral screw and pedicle screw fixation,” The Iowa Orthopaedic Journal, pp. 127-136, 1991.
[2] A. L. Carl, H. S. Khanuja, C. A. Gatto, M. Matsumoto, J. VomLehn, J. Schenck, K. Rohling, W. Lorensen, and K. Vosburgh, “In vivo pedicle screw placement: image-guided virtual vision,” Journal of Spinal Disorders, vol.13, no. 3, pp.225-229, 2000.
[3] J. M. Mac-Thiong, H. Labelle, and C. E. Aubin, “Thoracic pedicle screw insertion using a transpedicular drill guide: a preliminary study,” Spinal Disord Tech, vol.17, no. 1, pp.29-32, 2004.S
[4] R. J. Mobbs, P. Sivabalan, and J. Li, “Technique, challenges and indications for percutaneous pedicle screw fixation,” Journal of Clinical Neuroscience, vol. 18, no. 6, pp. 741-749, 2011.
[5] T. F. Cootes, C. J. Taylor, D. H. Cooper, and J. Graha, "Active shape models-their training and application." Computer vision and image understanding, 1995.
[6] M. Mancas, B. Gosselin, and B. Macq, “Segmentation using a region-growing thresholding,” Proc. of SPIE, vol. 5672, pp. 388-398, 2005.
[7] J. Tang. “A color image segmentation algorithm based on region growing,” Proc. of IEEE 2nd international conference on computer engineering and technology, pp. 634-637, 2010.
[8] Y. J. Kim, L. G. Lenke, K. H. Bridwell, Y. S. Cho, and K. D. Riew, “Free hand pedicle screw placement in the thoracic spine: is it safe?” Spine, vol. 29, no. 3, pp. 333-342, 2004.
[9] T. H. Kuo, C. Y. Ho, J. J. Fang, and R. M. Lin, “Development of guiding templates for pedicle screws insertion in spinal surgery,” Proc. of The 8th Combined Congress of the Spine and Pediatric Sections, June 2011.
[10] V. S. Fennel, S. Palejwala, J. Skoch, and D. A. Stidd, and A. A. Baaj, “Freehand thoracic pedicle screw technique using a uniform entry point and sagittal trajectory for all levels: preliminary clinical experience: Clinical article.” Journal of Neurosurgery: Spine, vol. 21, no. 5, pp. 778-784, 2014.
[11] J. Yao, S. D. O'Connor, and R. M. Summers, “Automated spinal column extraction and partitioning,” Proc. of the 3rd IEEE International Symposium on Biomedical Imaging: Nano to Macro, pp. 390-393, 2006.