我們使用磁振造影(MRI)來觀測患者的手術前後的差異，以及在第一次的檢查和第二次的復檢，可知病患是否有改善。但在觀測的過程中，會有些問題：由於患者在手術前所掃描的影像，以及在手術後所掃描的影像，兩次所掃描的位置會有偏差，甚至在同一次掃描時，作多次的影像掃描，病人也有可能頭部轉動的狀況。這些狀況都會影響我們分析訊號的結果，造成一些誤差。假使在造影掃描過程中，手術前後的切面選擇需要利用到人為的操作，手動選擇切面時，如果角度以及位置在前後兩次的觀測影像不相符合時，會影響醫生評估，這對病患會造成非常的不利影響。
所以，我們須要有一套系統，可以自動切面定位前後兩次觀測影像，來得到可靠的數據結果。在兩次掃描，我們各掃出一組三維的影像，藉由我們使用的一些影像分析方法，去作定位，在分析過程中，也利用NVIDIA CUDA 作一個加速運算的動作，這可以大幅的縮短我們分析計算影像所需的時間。既而可算出兩次影像的偏移參數，使兩張影像達到最相近的位置。
因此，可更加確定手術前後切面位置的一致性，得到我們所希望觀察到手術前後的差異，提高了數據分析的可靠度。

Optimal registration position is important for MRI scan, especially lesion observation in clinical use which analyzes pathology or tumor in pre-treatment or post-treatment, it needs an accurate estimation and contrast. In order to attend the accuracy of medical image in different times of scan, it must rely on effective image registration technique with Powell’s method or Brent’s method. In our study, we proposed a calculation method which with mutual information and Brent’s method, can improve the scan time of 3D MR image registration. The efficiency of the CUDA system calculation effectively accelerated the data analysis time and the result of registration was practically to compare between the different positions due to misregistration by many factors. Nevertheless, we improved the analyze time with a calculation technique which may help the application of clinical operations.

1.Hashemi, Ray H., W.G. Bradley, and C.J. Lisanti, MRI the basics, 2nd edition. 1997.
2.Viola, P.A., W.M., Wells Alignment by maximisation of mutual information. Proc. 5th Int. Conf. on Computer Vision. 1995: p. 15D23.
3.Collignon, A., D.V., P. Suetens, G. Marchal, 3D multi-modality medical image registration using feature space clustering. Proc. 1st Int. Conf. on Computer Vision, Virtual Reality and Robotics in Medicine, Nice, France, Spinger. 1995: p. 195D204.
4.Studholme, C., D.L.G.H., D.J., Hawkes, Multiresolution voxel similarity measures for MR-PET registration, in Y. Bizais, C. Barillot, R. Di Paola, (Eds.), Proc. of Information Processing in Medical Imaging, Brest, France, Kluwer Academic Publishers, Dordrecht. 1995: p. 287D298.
5.Viola, P., W.M.W.I., Alignment by Maximization of Mutual Information, PhD thesis, Massachusetts Institute of Technology. 1995.
6.Ardekani, B.A., A.H. Bachman, S.C. Strother, Y. Fujibayashi, and Y. Yonekura, Impact of inter-subject image registration on group analysis of fMRI data. International Congress Series, 2004. 1265: p. 49-59.
7.Brown, L.G., "A survey of image registration techniques". 1992. 24, no. 4: p. 325-376.
8.Shams, R., P. Sadeghi, R. Kennedy, and R. Hartley, A Survey of Medical Image Registration on Multicore and the GPU. Signal Processing Magazine, IEEE, 2010. 27(2): p. 50-60.
9.Maes, F., A. Collignon, D. Vandermeulen, G. Marchal, and P. Suetens, Multimodality image registration by maximization of mutual information. IEEE Trans Med Imaging, 1997. 16(2): p. 187-98.
10.Maes, F., D. Vandermeulen, and P. Suetens, Comparative evaluation of multiresolution optimization strategies for multimodality image registration by maximization of mutual information. Medical Image Analysis, 1999. 3(4): p. 373-386.
11.Palos, G., N. Betrouni, M. Coulanges, M. Vermandel, V. Devlaminck, and J. Rousseau, Multimodal matching by maximization of mutual information and optical flow technique. Conf Proc IEEE Eng Med Biol Soc, 2004. 3: p. 1679-82.
12.Matsopoulos, G.K., K.K. Delibasis, N.A. Mouravliansky, P.A. Asvestas, K.S. Nikita, V.E. Kouloulias, and N.K. Uzunoglu, CT-MRI automatic surface-based registration schemes combining global and local optimization techniques. Technol Health Care, 2003. 11(4): p. 219-32.
13.Press, W. H., W.T.V., S. A. Teukolsky and B. P. Flannery, Numerical Recipes in C, 2nd Edition,Cambridge University Press,Cambridge, England. 1992.
14.Atkin, D., Computer Shopper: The Right GPU for You.
15.Thomas, T.M.C.a.J.A., Elements of Information Theory. New York: Wiley. 1991.
16.Vajda, I., Theory of Statistical Inference and Information. Dordrecht, The Netherlands: Kluwer. 1989.
17.Studholme, C., Pattern Recognition 1999.
18.Viola, P., and W.M. Wells, I., Alignment by maximization of mutual information,in Proc. Int. Conf. Computer Vision (ICCV). June 1995: p. 16–23.
19.D.W. Eggert, A.L., R.B. Fisher, Estimating 3-D rigid body transformations: a comparison of four major algorithms, Machine Vision and Applications. 1997: p. 272-290.
20.Brent, R.P., Algorithms for Minimization without Derivatives,Prentice-Hall, Englewood Cliffs, New Jersey. 1973.