近年來，伴隨著科技日新月異地快速發展，全球在未來數十年也即將面對一個共同難題-人口老化速度加劇，造成各國逐漸邁向高齡化社會結構，而此趨勢同時也導致全球對於醫療產業發展和病患照護品質在市場面和技術面上越發重視。像中華民國經濟部 (Ministry of Economic Affairs, R. O. C.) 曾在2017年4月投入約20億元新台幣於高階影像醫療器材領域，試圖在2020年推動產值2000億元的生醫產業創新推動方案。在完善的醫療過程中，除了先進的儀器、專業的醫療人員外，各種含病患資訊影像的即時產生和應用也是不可或缺的一環，其中像電腦輔助診斷系統 (Computer aided detection/diagnosis, CAD) 透過對病患影像的重建和結合，提供更全面的醫療資訊來提高醫生對病灶的判讀和疾病監測的效率，或像是手術導航系統 (Surgical navigation system) 和微創手術系統 (Minimally invasive surgery, MIS) 的結合，以提升醫師的手術品質和操作容易度。在上述的應用中，醫學影像註冊技術都在其中擁有舉足輕重的影響，透過對多張相同或不同型態影像的空間定位和影像對位，建構多樣化的整合資訊，提供醫師在病患術前、中、後時期不同的醫療協助。

本論文開發一套針對2D胸腔X光影像的全自動影像註冊系統，可將病患在不同治療階段的X光影像進行精準對位產生差異分析結果。其中胸腔區域的特徵點是透過六個機器學習L-SVM (Linear support vector machine) 模組針對肺、肋骨、鎖骨部位組成的混合模型進行偵測，並透過新開發的演算法ADMA (Absolute Distance Matching Algorithm) 來匹配混合模組在不同影像所偵測到的特徵點。篩選出的特徵點分別作為三種變形技術的對位標準，產生不同特性的變形結果，最後針對原始目標和變形後的影像之間進行差異分析，產生融合影像用於協助後續的醫學療程。在實際應用中，由於胸腔X光的影像品質會受到拍攝儀器、人員校準、病患姿勢、骨骼差異等變因所影響，因此本系統的研發挑戰在於如何使系統針對各種不同條件的胸腔X光影像上，都能穩定且準確的偵測以及匹配特徵點來達成精確的影像註冊。

在驗證階段，本系統和現有的兩種影像註冊技術BunwarpJ 和 Fully Automatic Elastic Registration (FAER) 進行成對樣本T檢定精確度比較，透過15個手動標記在胸腔X光影像的驗證標點計算出的平均誤差，證明本系統在針對胸腔X光影像的註冊精確度相較於既有技術有顯著差異(P ≤ 0.001)。同時也將系統應用在多組被診斷感染胸腔疾病的病患影像上，結果表示，註冊完的融合影像能顯現出病患在治療期間的病灶變化。本研究期望能透過全自動且精確的胸腔X光影像註冊技術協助醫生對胸腔疾病的診斷和治療期間的療效評估。

Image registration is important in medical applications accomplished with the advance of healthcare technology in recent years. Through the image registration task of finding the spatial relationship between input images, various studies have been proposed in the medical applications, including clinical track of events, updating the treatment plan for radiotherapy and surgery. This study presents a fully automatic registration system for chest X-ray images to generate fusion results for difference analysis. Through the accurate alignment of the proposed system, the fusion result indicates the difference of thoracic area during the treatment process. Registration of chest X-ray images is a challenging task due to variations on data appearance, imaging artifacts and complex data deformation problems, making existing registration approaches unstable and performs poor. The proposed method consists of a data normalization method, a hybrid L-SVM model to detect lungs, ribs and clavicles for object recognition, a landmark matching algorithm, two-stage transformation approaches, and a fusion method for difference analysis to highlight the difference of thoracic area. In evaluation, a preliminary test to compare three transformation models in the proposed system and a full evaluation process to compare the proposed method with two existing elastic registration methods for medical images have been conducted. The results show that the proposed method performs significantly better result than two benchmark methods (P value ≤ 0.001). The proposed system achieves the lowest mean registration error distance (MRED) (8.99 mm, 23.55 pixel) and the lowest mean registration error ratio (MRER) w.r.t. the length of image diagonal (1.61%) compared to the two benchmark approaches with MRED (15.64 mm, 40.97 pixel) and (180.5 mm, 472.69 pixel) and MRER (2.81%) and (32.51%), respectively.

1. Derek LGH, Philipp GB, Mark H, David JH. Medical image registration. Physics in Medicine & Biology. 2001;46(3):R1.

2. Comeau RM, Fenster A, Peters TM. Intraoperative US in interactive image-guided neurosurgery. RadioGraphics. 1998;18(4):1019-27.

3. Weese J, Penney GP, Desmedt P, Buzug TM, Hill DLG, Hawkes DJ. Voxel-based 2-D/3-D registration of fluoroscopy images and CT scans for image-guided surgery. IEEE Transactions on Information Technology in Biomedicine. 1997;1(4):284-93.

4. Khamene A, Bloch P, Wein W, Svatos M, Sauer F. Automatic registration of portal images and volumetric CT for patient positioning in radiation therapy. Medical Image Analysis. 2006;10(1):96-112.

5. Hill DL, Hawkes DJ, Gleeson MJ, et al. Accurate frameless registration of MR and CT images of the head: applications in planning surgery and radiation therapy. Radiology. 1994;191(2):447-54.

6. Maintz JBA, Viergever MA. A survey of medical image registration. Medical Image Analysis. 1998;2(1):1-36.

7. Zitová B, Flusser J. Image registration methods: a survey. Image and Vision Computing. 2003;21(11):977-1000.

8. Markelj P, Tomazevic D, Pernus F, Likar B. Robust Gradient-Based 3-D/2-D Registration of CT and MR to X-Ray Images. IEEE Transactions on Medical Imaging. 2008;27(12):1704-14.

9. Dean CJ, Sykes JR, Cooper RA, et al. An evaluation of four CT–MRI co-registration techniques for radiotherapy treatment planning of prone rectal cancer patients. The British Journal of Radiology. 2012;85(1009):61-8.

10. Seldin DW, Esser PD, Nichols AB, Ratner SJ, Alderson PO. Left ventricular volume determined from scintigraphy and digital angiography by a semi-automated geometric method. Radiology. 1983;149(3):809-13.

11. Carrillo A, Duerk JL, Lewin JS, Wilson DL. Semiautomatic 3-D image registration as applied to interventional MRI liver cancer treatment. IEEE Transactions on Medical Imaging. 2000;19(3):175-85.

12. Panigrahy A, Caruthers SD, Krejza J, et al. Registration of Three-Dimensional MR and CT Studies of the Cervical Spine. American Journal of Neuroradiology. 2000;21(2):282.

13. Rohr K, Stiehl HS, Sprengel R, Buzug TM, Weese J, Kuhn MH. Landmark-based elastic registration using approximating thin-plate splines. IEEE Transactions on Medical Imaging. 2001;20(6):526-34.

14. Shi J, Zhang W, Tang M, Caselli RJ, Wang Y. Conformal invariants for multiply connected surfaces: Application to landmark curve-based brain morphometry analysis. Medical Image Analysis;35:517-29.

15. Lowe DG. Object recognition from local scale-invariant features. Proceedings of the Seventh IEEE International Conference on Computer Vision1999; p. 1150-7 vol.2.

16. Bay H, Ess A, Tuytelaars T, Van Gool L. Speeded-Up Robust Features (SURF). Computer Vision and Image Understanding. 2008;110(3):346-59.

17. Lukashevich PV, Zalesky BA, Ablameyko SV. Medical image registration based on SURF detector. Pattern Recognition and Image Analysis. 2011;21(3):519.

18. Teke M, Temizel A. Multi-spectral Satellite Image Registration Using Scale-Restricted SURF. 2010 20th International Conference on Pattern Recognition2010; p. 2310-3.

19. Zhu Y, Cheng S, Stanković V, Stanković L. Image registration using BP-SIFT. Journal of Visual Communication and Image Representation. 2013;24(4):448-57.

20. Yi Z, Zhiguo C, Yang X. Multi-spectral remote image registration based on SIFT. Electronics Letters. 2008;44(2):107-8.

21. Gong M, Zhao S, Jiao L, Tian D, Wang S. A Novel Coarse-to-Fine Scheme for Automatic Image Registration Based on SIFT and Mutual Information. IEEE Transactions on Geoscience and Remote Sensing. 2014;52(7):4328-38.

22. Kaur A, Kaur L. Concealed weapon detection from images using SIFT and SURF. 2016 Online International Conference on Green Engineering and Technologies (IC-GET)2016; p. 1-8.

23. Wang C-W, Chen H-C. Improved image alignment method in application to X-ray images and biological images. Bioinformatics. 2013;29(15):1879-87.

24. Felzenszwalb PF, Girshick RB, McAllester D, Ramanan D. Object Detection with Discriminatively Trained Part-Based Models. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2010;32(9):1627-45.

25. Oktay AB, Akgul YS. Simultaneous Localization of Lumbar Vertebrae and Intervertebral Discs With SVM-Based MRF. IEEE Transactions on Biomedical Engineering. 2013;60(9):2375-83.

26. Dalal N, Triggs B. Histograms of oriented gradients for human detection. 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05)2005; p. 886-93 vol. 1.

27. Cao X, Wu C, Yan P, Li X. Linear SVM classification using boosting HOG features for vehicle detection in low-altitude airborne videos. 2011 18th IEEE International Conference on Image Processing2011; p. 2421-4.

28. Kalavagunta C, Zhou X, Schmechel Stephen C, Metzger Gregory J. Registration of in vivo prostate MRI and pseudo‐whole mount histology using Local Affine Transformations guided by Internal Structures (LATIS). Journal of Magnetic Resonance Imaging. 2015;41(4):1104-14.

29. Rivest-Hénault D, Dowson N, Greer PB, Fripp J, Dowling JA. Robust inverse-consistent affine CT-MR registration in MRI-assisted and MRI-alone prostate radiation therapy. Medical Image Analysis. 2015;23(1):56-69.

30. Roche A, Pennec X, Malandain G, Ayache N. Rigid registration of 3-D ultrasound with MR images: a new approach combining intensity and gradient information. IEEE Transactions on Medical Imaging. 2001;20(10):1038-49.

31. Gu S, Meng X, Sciurba FC, et al. Bidirectional elastic image registration using B-spline affine transformation. Computerized Medical Imaging and Graphics. 2014;38(4):306-14.

32. Thirion JP. Image matching as a diffusion process: an analogy with Maxwell's demons. Medical Image Analysis;2(3):243-60.

33. Szeliski R, Coughlan J. Spline-Based Image Registration. International Journal of Computer Vision. 1997;22(3):199-218.

34. Srinivasan S, Hargreaves Brian A, Daniel Bruce L. Fat‐based registration of breast dynamic contrast enhanced water images. Magnetic Resonance in Medicine. 2017;79(4):2408-14.

35. Shen D. Image registration by local histogram matching. Pattern Recognition. 2007;40(4):1161-72.

36. Zhang KYJ, Main P. Histogram matching as a new density modification technique for phase refinement and extension of protein molecules. Acta Crystallographica Section A. 1990;46(1):41-6.

37. Helmer EH, Ruefenacht B. Cloud-Free Satellite Image Mosaics with Regression Trees and Histogram Matching. Photogrammetric Engineering & Remote Sensing. 2005;71(9):1079-89.

38. Li B, Cheng K, Yu Z. Histogram of Oriented Gradient Based Gist Feature for Building Recognition. Intell Neuroscience. 2016;2016:10.

39. Arun KS, Huang TS, Blostein SD. Least-Squares Fitting of Two 3-D Point Sets. IEEE Transactions on Pattern Analysis and Machine Intelligence. 1987;PAMI-9(5):698-700.

40. Shinji U. Least-Squares Estimation of Transformation Parameters Between Two Point Patterns. IEEE Trans Pattern Anal Mach Intell. 1991;13:376-80.

41. Horn BKP. Closed-form solution of absolute orientation using unit quaternions. J Opt Soc Am A. 1987;4(4):629-42.

42. Arun KS, Huang, T.S., Blostein, S.D.,. Least-squares tting of two 3-d point. IEEE Transactions on pattern analysis and machine intelligence. 1987.

43. Klein S, Staring M, Murphy K, Viergever MA, Pluim JPW. Elastix: A Toolbox for Intensity-Based Medical Image Registration. IEEE Transactions on Medical Imaging. 2010;29(1):196-205.

44. Shamonin D, Bron E, Lelieveldt B, Smits M, Klein S, Staring M. Fast Parallel Image Registration on CPU and GPU for Diagnostic Classification of Alzheimer's Disease. Frontiers in Neuroinformatics. 2014;7(50).

45. Sorzano COS, Thevenaz P, Unser M. Elastic registration of biological images using vector-spline regularization. IEEE Transactions on Biomedical Engineering. 2005;52(4):652-63.

46. Rohr K, Stiehl HS, Sprengel R, et al. Point-based elastic registration of medical image data using approximating thin-plate splines. In: Höhne KH, Kikinis R, eds. Visualization in Biomedical Computing. Berlin, Heidelberg: Springer Berlin Heidelberg, 1996; p. 297-306.

47. Thevenaz P, Unser MA. Spline pyramids for intermodal image registration using mutual information Proc SPIE 3169, Wavelet Applications in Signal and Image Processing V. 1997.

48. Klein S, Staring M, Pluim JPW. Evaluation of Optimization Methods for Nonrigid Medical Image Registration Using Mutual Information and B-Splines. IEEE Transactions on Image Processing. 2007;16(12):2879-90.

49. Th´evenaz, Unser M. Halton sampling for image registration based on mutual information. Sampling Theory in Signal and Image Processing. 2008;7(2):141-71.

50. Klein S, Pluim JPW, Staring M, Viergever MA. Adaptive Stochastic Gradient Descent Optimisation for Image Registration. International Journal of Computer Vision. 2008;81(3):227.

51. Unser M. Splines: a perfect fit for signal and image processing. IEEE Signal Processing Magazine. 1999;16(6):22-38.

52. Openi - an open access biomedical image search engine. http://openi.nlm.nih.gov. Lister Hill National Center for Biomedical Communications, U.S. National Library of Medicine.

53. Wang X, Peng Y, Lu L, Lu Z, Bagheri M, Summers R. ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017:3462-71.

54. Arganda-Carreras I, Sorzano COS, Marabini R, Carazo J-M, Solorzano CO-d, Kybic J. Consistent and Elastic Registration of Histological Sections using Vector-Spline Regularization. CVAMIA: Computer Vision Approaches to Medical Image Analysis. 2006;4241:85-95.

55. Wang C-W, Ka S-M, Chen A. Robust image registration of biological microscopic images. Scientific Reports. 2014;4:6050.

56. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521:436-44.