随著科技不斷的進步，醫學診斷技術也不斷的提升。目前醫學影像電腦輔助診斷技術(Computer-aided diagnosis on medical imaging)已廣泛應用在臨床醫學診斷上，運用資訊技術幫助醫生在最有效時間掌握病人的病徵，協助醫生快速正確診斷病灶。影像註冊在臨床醫學上的應用是相當重要的，透過電子顯微影像、病理切片組織重組、跨染色病理切片註冊、3D重建…等，使醫生獲得病人更完整的病灶資訊。
　　建立一個強健且全自動的3D影像註冊系統是非常困難的，尤其在醫學顯微影像，生物影像資訊常有複雜的變形、染色不均勻、數據資訊變化大等問題，導致影像註冊過程中失敗無法完成對位，如：神經組織影像的重建等，因此在大型生物檢體的細節解剖重建是非常關鍵的。本研究主要使用非剛性註冊技術，並加入3D影像註冊驗證方法與現有的技術Least squares、bUnwarpJ、UnwarpJ、Elastic和CwR等方法比較，實驗將測試目前現有的影像註冊方法，並使用不同的參數設定，然後比較3D影像重建任意切面側視圖連續性表現的差異。
　　多蛋白跨染色切片影像註冊在疾病診斷、藥物開發和生物研究是非常重要的，但由於染色切片影像有複雜的變形問題，包括形態變形、染熱變形、旋轉、組織破損等，使得單細胞解析的跨染色切片顯微影像對位艱鉅挑戰性。此部份本研究針對先前研究影像註冊方法進行改良，改良資料正規化和特徵擷取方法，實驗部分使用90對跨染色切片影像進行影像註冊，並與現有影像註冊方法實驗比較結果註冊準確率。兩種註冊方法改良如下：
1. 3D影像註冊
 改良3D影像註冊框架
 適用於各類顯微影像
 提升3D重建連續性表現
2. 跨染色影像註冊
 改良正規化和特徵擷取方法
 評估跨染色註冊方法成效
　　3D影像註冊改良現有影像註冊方法，提升影像3D重建後連續性的表現。而在跨染色影像註冊方面，將註冊準確率提升至97.56%。此技術的改良提供給醫生更完整的病患資訊，使醫生能監測腫瘤的增長及治療驗證等，減少人力、提升醫療品質。

關鍵字: 影像註冊、顯微影像、bUnwarpJ、UnwarpJ、CwR

Robust and fully automatic 3D registration of serial-section microscopic images is critical for detailed anatomical reconstruction of large biological specimens, such as reconstructions of dense neuronal tissues or 3D histology reconstruction to gain new structural insights. However, robust and fully automatic 3D image registration for biological data is difficult due to complex deformations, unbalanced staining and variations on data appearance. This study presents a fully automatic and robust 3D registration technique for microscopic image reconstruction, and we demonstrate our method on two ssTEM datasets of drosophila brain neural tissues, serial confocal laser scanning microscopic images of a drosophila brain and serial histopathological images of renal cortical tissues. The results show that the presented fully automatic method is promising to reassemble continuous volumes and minimize artificial deformations for all data and outperforms four state-of-the-art 3D registration techniques to consistently produce solid 3D reconstructed anatomies with less discontinuities and deformations.
Multi-modal protein mapping is important for disease diagnosis, drug development and biological research, requiring joint analysis of multiple protein expression maps (obtained from　immunohistochemistry) and cellular morphology maps (from histopathology) at single-cell resolution. However, cross-staining alignment of biological images at single cell resolution is difficult because not only complex data deformations are introduced during slide preparation but also large variations exist on staining colors, cell appearance and tissue morphology across different slides, which makes existing registration methods tend to fail in crossstaining alignment. In this work, an automatic multi-protein mapping tool, ProteinMapper, is presented, and the method is evaluated with 90 pairs of cross-stained microscopic images, involving two different immunohistochemical stains (HMCK and CK18) and the conventional histopathological stain (H&E). The presented approach is tested and compared with six state-of-the-art image registration techniques, and the results show that ProteinMapper consistently performs well in alignment of multiple protein maps, achieving 97.56% averaged registration accuracies, outperforms the benchmark methods and is significantly better than the benchmark methods (p < 0:01).

1. ME, N. and M.G. Jr, QSH: a minimal but highly portable image display and handling toolkit. Comput Methods Programs Biomed, 1988. 27(3): p. 229-240.
2. Maurer CR., F.J., A Review of Medical Image Registration. American Association of Neurological, 1993: p. 17-44.
3. Hui, L., B.S. Manjunath, and S.K. Mitra, A contour-based approach to multisensor image registration. Image Processing, IEEE Transactions on, 1995. 4(3): p. 320-334.
4. McInerney, T. and D. Terzopoulos, Deformable models in medical image analysis: a survey. Medical Image Analysis, 1996. 1(2): p. 91-108.
5. al., D.e., Image registration based on boundary mapping. IEEE Transactions Medical Image, 1996. 15(1): p. 112-115.
6. Anuta, P.E., Spatial Registration of Multispectral and Multitemporal Digital Imagery Using Fast Fourier Transform Techniques. Geoscience Electronics, IEEE Transactions on, 1970. 8(4): p. 353-368.
7. Brown, L.G., A survey of image registration techniques. ACM Comput. Surv., 1992. 24(4): p. 325-376.
8. Sorzano, I.A.-C.C.O.S., et al., Consistent and Elastic Registration of Histological Sections using Vector-Spline Regularization. LNCS, Comput. Vis. Approaches to Med. Imag. Anal., 2006. 4241: p. 85-95.
9. Chakravarty, M.M., et al., The creation of a brain atlas for image guided neurosurgery using serial histological data. NeuroImage, 2006. 30(2): p. 359-376.
10. Dauguet, J., et al., Three-dimensional reconstruction of stained histological slices and 3D non-linear registration with in-vivo MRI for whole baboon brain. Journal of Neuroscience Methods, 2007. 164(1): p. 191-204.
11. Zitová, B. and J. Flusser, Image registration methods: a survey. Image and Vision Computing, 2003. 21(11): p. 977-1000.
12. Myasnikova, E., et al., Registration of the expression patterns of Drosophila segmentation genes by two independent methods. Bioinformatics, 2001. 17(1): p. 3-12.
13. Hess, K.R., et al., Microarrays: handling the deluge of data and extracting reliable information. Trends in Biotechnology, 2001. 19(11): p. 463-468.
14. Pennec, X. and N. Ayache, A geometric algorithm to find small but highly similar 3D substructures in proteins. Bioinformatics, 1998. 14(6): p. 516-522.
15. Dowsey, A.W., Dunn, M. J. and Yang, G.-Z., The role of bioinformatics in two-dimensional gel electrophoresis. Proteomics, 2003. 3(8): p. 1567-1596.
16. Akutsu, T., et al., Point matching under non-uniform distortions. Discrete Applied Mathematics, 2003. 127(1): p. 5-21.
17. Bazen, A.M. and S.H. Gerez, Fingerprint matching by thin-plate spline modelling of elastic deformations. Pattern Recognition, 2003. 36(8): p. 1859-1867.
18. Rohr, K., et al., Landmark-based elastic registration using approximating thin-plate splines. Medical Imaging, IEEE Transactions on, 2001. 20(6): p. 526-534.
19. Suter, D. and F. Chen, Left ventricular motion reconstruction based on elastic vector splines. Medical Imaging, IEEE Transactions on, 2000. 19(4): p. 295-305.
20. J, P.J.V., Point pattern matching in the analysis of two-dimensional gel electropherograms. Electrophoresis, 1999. 20(18): p. 3483-3491.
21. Kybic, J. and M. Unser, Fast parametric elastic image registration. Image Processing, IEEE Transactions on, 2003. 12(11): p. 1427-1442.
22. Mattes, D., et al., PET-CT image registration in the chest using free-form deformations. Medical Imaging, IEEE Transactions on, 2003. 22(1): p. 120-128.
23. Musse, O., F. Heitz, and J.-P. Armspach, Fast deformable matching of 3D images over multiscale nested subspaces. Application to atlas-based MRI segmentation. Pattern Recognition, 2003. 36(8): p. 1881-1899.
24. Unser, M., A. Aldroubi, and M. Eden, Fast B-spline transforms for continuous image representation and interpolation. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 1991. 13(3): p. 277-285.
25. Unser, M., Splines: a perfect fit for signal and image processing. Signal Processing Magazine, IEEE, 1999. 16(6): p. 22-38.
26. Thévenaz, P., T. Blu, and M. Unser, Interpolation Revisited. Med. Imag., 2000. 19(7): p. 739-858.
27. Szeliski, R. and J. Coughlan, Spline-based image registration. International J. Comput. Vis., 1997. 22(3): p. 199-218.
28. Christensen, G.E., et al., Individualizing Neuroanatomical Atlases Using a Massively Parallel Computer. Computer, 1996. 29(1): p. 32-38.
29. Maintz, J.B.A. and M.A. Viergever, A survey of medical image registration. Medical Image Analysis, 1998. 2(1): p. 1-36.
30. Arganda-Carreras, I., R. Fernandez-Gonzalez, and C. Ortiz-de-Solorzano. Automatic registration of serial mammary gland sections. in Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE. 2004.
31. Radeva, P., et al., Deformable B-Solids and Implicit Snakes for 3D Localization and Tracking of SPAMM MRI-Data. Computer Vision and
Image Understanding, 1997. 66(2): p. 163-178.
32. Christensen, G.E. and J. He. Consistent nonlinear elastic image registration. in Mathematical Methods in Biomedical Image Analysis, 2001. MMBIA 2001. IEEE Workshop on. 2001.
33. Avants, B.B., P.T. Schoenemann, and J.C. Gee, Lagrangian frame diffeomorphic image registration: Morphometric comparison of human and chimpanzee cortex. Medical Image Analysis, 2006. 10(3): p. 397-412.
34. Sorzano, C.O.S., P. Thevenaz, and M. Unser, Elastic registration of biological images using vector-spline regularization. Biomedical Engineering, IEEE Transactions on, 2005. 52(4): p. 652-663.
35. Shum, H.-Y. and R. Szeliski, Construction of panoramic mosaics with global and local alignment. International Journal of Computer Vision, 2000. 36(3): p. 101-130.
36. Ph.D., C.E.H.B., et al., Color Separation in Forensic Image Processing. Journal of Forensic Sciences, 2006. 51(1): p. 100-102.
37. Ruifrok, A.C. and D.A. Johnston, Quantification of histochemical staining by color deconvolution. Anal. Quant. Cytol. Histol., 2001. 23: p. 291-299.
38. !!! INVALID CITATION !!!
39. Lowe, D., Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision, 2004. 60(2): p. 91-110.
40. Fischler, M.A. and R.C. Bolles, Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM, 1981. 24(6): p. 381-395.
41. Amodei, L. and M.N. Benbourhim, A vector spline approximation. Journal of Approximation Theory, 1991. 67(1): p. 51-79.
42. Wang, C.-W. and H.-C. Chen, Improved image alignment method in application to X-ray images and biological images. Bioinformatics, 2013. 29(15): p. 1879-1887.
43. Wang, C.-W., S.-M. Ka, and A. Chen, Robust image registration of biological microscopic images. Sci. Rep., 2014. 4.
44. Wang, C.-W. and C.-P. Yu, Automated morphological classification of lung cancer subtypes using H&E tissue images. Mach. Vision Appl., 2013. 24(7): p. 1383-1391.
45. Wang, C., Fast automatic quantitative cell replication with fluorescent live cell imaging. BMC Bioinformatics, 2012. 13: p. 1-10.
46. Gerhard, S., et al., Segmented anisotropic ssTEM dataset of neural tissue. 2013.
47. Cardona, A., et al., An Integrated Micro- and Macroarchitectural Analysis of the Drosophila Brain by Computer-Assisted Serial Section Electron Microscopy. PLoS Biol, 2010. 8(10): p. e1000502.
48. Peng, H., et al., V3D enables real-time 3D visualization and quantitative analysis of large-scale biological image data sets. Nat Biotech, 2010. 28(4): p. 348-353.
49. Saalfeld, S., et al., Elastic volume reconstruction from series of ultra-thin microscopy sections. Nat Meth, 2012. 9(7): p. 717-720.
50. Saalfeld, S., et al., As-rigid-as-possible mosaicking and serial section registration of large ssTEM datasets. Bioinformatics, 2010. 26(12): p. i57-63.
51. Cardona, A., et al., TrakEM2 Software for Neural Circuit Reconstruction. PLoS ONE, 2012. 7(6): p. e38011.
52. Schindelin, J., et al., Fiji: an open-source platform for biological-image analysis. Nat Methods, 2012. 9(7): p. 676-82.
53. Pluim, J.P.W., J.B.A. Maintz, and M.A. Viergever, Mutual-information-based registration of medical images: a survey. Medical Imaging, IEEE Transactions on, 2003. 22(8): p. 986-1004.
54. MathWorks: R2013a imregister. http://www.mathworks.com/help/images/ref/imregister.html].
55. SPSS Inc. SPSS for Windows, Rel.17.0.1. 2008. Chicago: SPSS Inc.