北京生物醫(yī)學工程

基于Contourlet變換的CT和錐形束CT圖像配準算法

Image registration algorithm in CT and cone beam CT based on Contourlet transform

作者：岳海振李海云劉迪

單位：首都醫(yī)科大學生物醫(yī)學工程學院（北京 100069）

分類號：

出版年·卷·期（頁碼）：2012·31·2（140-145）

摘要：

目的提出一種基于Contourlet變換，用于放射治療定位的CT與錐形束CT(cone beam CT,CBCT)圖像配準的方法。方法利用Contourlet變換多尺度多方向的分辨特性，將待配準圖像進行Contourlet變換分解，分解后的高頻方向子帶合成梯度圖像，采用歸一化互信息作為相似性測度，把梯度圖像與低頻方向子帶以加權函數(shù)結合，進行臨床醫(yī)學圖像的剛性配準，有效彌補了互信息配準中缺少空間信息的不足。結果通過已知空間變換參數(shù)圖像的配準結果驗證了算法的準確性。配準后10幅圖像變換參數(shù)的誤差極小，且均方根誤差接近于0。結論該圖像配準算法精確度高，并具有很好的魯棒性，有助于提高圖像引導放射治療(image guided radiation therapy,IGRT)中解剖組織結構和靶區(qū)的定位精度。

Objective A novel image registration algorithm in CT and cone beam CT (CBCT) is proposed for the localization in radiotherapy based on Contourlet transform. Methods The multi-directional and multi-resolution Contourlet transform is applied to decompose the original image. The gradient image is constructed from the high frequency directional subbands,and normalized mutual informaion (NMI) is used as the similarity measures to calculate the mutual information of the gradient image and low frequency directional subband ,respectively.Then the synthesis similarity measure is the combination of mutual information for two images with a specific weight function The proposed approach can compensate for the lack of spatial information in the mutual information based on image registration.Results The algorithm accuracy is verified by comparing the registration results of ten medical images with specific spatial transformation parameters. The errors of the spatial transformation parameters after registration are small,and the mean squared error (MSE) is close to zero. Conclusions The experimental results are accurate and the algorithm is robust. This method improves the localization accuracy of anatomical structures and targets in the applications of image guided radiation therapy (IGRT).

參考文獻：

［1］殷蔚伯，胡逸民.腫瘤放射治療學［M］.北京：中國協(xié)和醫(yī)科大學出版社，2008：1-5.
Yin Weibo,Hu Yinmin. Radiation therapy oncology［M］. Beijing:Peking Union Medical College press,2008:1-5.
［2］Pluim J,Maintz J,Viergever MA. Mutual information-based registration of medical images:a survey［J］. IEEE Transaction on Medical Imaging,2003,22(8):986-1004.
［3］Hong G,Zhang Y.Wavelet-based image registration technique for high-resolution remote sensing images［J］. Computers & Geosciences,2008,34(12):1708-1720.
［4］Huang XS,Zhang F.Multi-modal medical image registration based on gradient of mutual information and morphological haar wavelet［C］// Proceedings of 2010 International Conference on e-Education,e-Business,e-Management and e-Learning,Sanya. China:IEEE Computer Society Press,2010:39-42.
［5］Mallat SG,Hwang WH. Singularity detection and processing with wavelets［J］. IEEE Transactions on In formation Theory,1992,38(2):617-643.
［6］Mallat S,Zhong S. Characterization of signals from multiscale edges［J］. IEEE Transactions on Pattern Analysis and Machine Intelligence,1992,14(7) :710-732.
［7］Pluim JPW,Maintz JBA,Viergever MA. Interpolation artefacts in mutual information-based image registration［J］. Computer Vision and Image Understanding,2000,77(2):211-232.
［8］Tsao J. Interpolation artifacts in multimodality image registration based on maximization of mutual information［J］. IEEE Transactions on Medical Imaging,2003,22(7):235-260.
［9］Pluim JPW,Maintz JBA,Viergever MA. Image registration by maximization of combined mutual information and gradient information［J］. IEEE Transactions on Medical Imaging,2000,19(2):809–814.
［10］Wang XX,Tian J. Image registration based on maximization of gradient code mutual information［J］. Image Anal Stereol,2005,24:1–7.
［11］Duncan DYP,Minh ND. Directional multiscale modeling of images using the contourlet transform［J］. IEEE Transaction on Medical Imaging,2006,15(6):1610-1620.
［12］Minh ND,Martin V. The Contourlet transform:an efficient directional multiresolution image representation［J］. IEEE Transactions on Image Processing,2005,14(12):2091-2106.
［13］Long ZL,Younan NH.Statistical image modeling in the Contourlet domain using contextual hidden Markov models［J］. Signal Processing,2009,89:946-951.
［14］陳志剛，尹福昌，孫孚.基于非采樣Contourlet 變換高分辨率遙感圖像配準［J］.光學學報，2009,29（10）:108-114.
Chen ZG,Yin FC,Sun F. Registration technique for high resolution remote sensing images based on nonsubsampled contourlet transform［J］. Acta Optica Sinica, 2009,29(10):108-114.
［15］羅述謙，周果宏.醫(yī)學圖像處理與分析［M］.北京：科學出版社,2010：164-165.
Luo SQ,Zhou GH. Medical image processing and analysis. ［M］. Beijing:Science Press，2010:164-165.
［16］Liu JG,Tian J. Multi-modal Medical Image Registration Based on Adaptive Combination of Intensity and Gradient Field Mutual Information［C］// Proceedings of the 28th IEEE EMBS Annual International Conference,New York City,USA:IEEE Computer Society Press,2006:1429-1432.
［17］Hart PE,Duda RO,Stork DG. Pattern Classification Second Edition ［M］. Beijing:China Machine Press,2004:359-363.

服務與反饋：

【文章下載】【加入收藏】

提示：您還未登錄，請登錄！點此登錄

51黑料吃瓜在线观看,51黑料官网|51黑料捷克街头搭讪_51黑料入口最新视频