基于内容的医学图像检索
|
摘要
基于内容的图像检索(CBIR),近十年来一直是研究的热点,但一直都未有重大的突破。本文从CBIR的概述入手,概述了CBIR系统的组成和所涉及的关键技术,回顾了目前的研究进展和主流的研究方法及已完成的各种系统,同时分析了医学图像的特点,最后,本文围绕CBIR在医学中的应用,研究了以下问题:
(1)基于GAUSS-MARKOV随机场模型的MR图像分割(对应于本文第二章)。图像分割是图像关键内容区域的选取及量化的基础,利于用图像的关键内容信息进行检索。高斯—马尔可夫随机场模型既利用了图像像素的灰度信息,又通过像素类别标记的Gibbs光滑先验概率引入了图像的空间信息,是能较好地分割含有噪声的图像的模型。然而,Gibbs惩罚因子的确定却一直是个难点,为获得好的分割效果,通常用多个值人工尝试。本文针对此问题,提出了一种新的、简单的、类自适应的惩罚因子,其利用后验概率来自动计算,并具有各类各向异性。再将模型利用EM-MAP算法来迭代求解。最后,将本文算法应用于MR图像的分割,实验表明该算法能自适应地、有效地分割噪声图像,并具有较高的正确分类率和类正确分类率。
(2)基于弹性配准的图像感兴趣区域定位(对应于本文第三章)。疾病的诊断,主要是依据病变区域的形状,大小,及其所在的解剖位置,因而病变区域为感兴趣区域。感兴趣区域的确定有利于在CBIR中只关注医学图像信息的主要部分,得出利于检索的关键信息,使用于检索的特征量显著减少。目前,众多的CBIR都提供了ROI确定的方法,但往往是采用人工交互的方式。如Blobworld中,则先采用图像分割的方法,据待检索图像的多种性质,如纹理,色彩,极性,将待检索图像分割为多个区域,然后通过交互的方式,手工确定一个ROI。本文则尝试使用弹性配准的方法来自动的确定ROI。
(3)图像特征提取(对应于本文第四章)。图像特征提取是图像检索的基础与关键。常用的特征提取方法有:用傅立叶描述符和不变矩表示的形状特征,小波纹理特征,Gabor小波纹理特征。但传统小波变换具有的两大缺点:平移变化性,缺乏方向性。Gabor小波具有方向选择性,但Gabor小波由于非正交性具有大量的数据冗余且不可逆向重构,并具有较高的计算代价。在仔细分析了以上小波变换的缺点后,本文重点介绍了能克服以上小波缺点的双树复数小波变换(DT-CWT)及其原理,并将以此作为图像特征提取的方法。
(4)基于DT-CWT和K-L距离(Kullback-leibler distance)相似性测度的脑部MR图像检索(对应于本文第五章)。对各图像进行二阶DT-CWT后,每级分解得到6个方向的小波子带系数,再利用广义高斯密度(Generalized GaussianDensity)函数来逼近各子带系数的直方图,即使用最大似然估计法得出与各直方图相近的广义高斯密度函数的参数,用矩匹配法得出参数,以这12组特征值来表示该图像特征。提取出图像特征后,本文则基于最大似然规则的图像检索理论,使用基于链式规则的K-L相似性测度来进行特征匹配。
最后,本文对以上研究进行了总结,并对医学CBIR研究进行了展望,讨论了未来的研究方向和目标。
A content-based image retrieval system in medical applications has always been the most vivid research areas in recent ten years, but no general breakthrough has been achieved. This thesis aims to bring some highlight in this field. First, it presents a brief introduction of CBIR system and its key techniques, reviews the current research development, the main research methods and the existed CBIR system, and analyzes the features of medical image. And then, centered on the medical application of CBIR, it mainly does some research about the following issues:
(1) Segmentation of brain MR images based on GAUSS-MARKOV random field model, (see chapter 2). Image segmentation lays foundation for selecting and measuring the key region of content information, which is advantageous for image retrieval to use key information. Gauss-Markov random field model is the often used image segmentation model, taking advantage of both image intensity and spatial information imposed by Gibbs prior. It can be used to effectively segment the images with high levels of noise. However it is always difficult to confirm the Gibbs penalty factor. As usual, it requires a tedious trial-and-error process. So to solve this problem, this paper defines a class-adaptive penalty factor. It is automatically estimated from the posterior probability and is anisotropic for each class. Furthermore the model iteratively gets their parameters estimation in the EM-MAP algorithm. Finally, by application of this algorithm to medical image segmentation, it is proved effective.
(2) Locating region of interest of images based on elastic registration, (see chapter 3). Diagnosing diseases is usually on the basis of the form and size of pathological regions and its anatomic parts. Therefore, the pathological region is also defined as region of interest. To delimit the region of interest is beneficial to CBIR for the purpose of narrowing down information area and getting key retrieval information. By this way, the image information characters for retrieval are tremendously decreased. At present, many CBIRs are capable of offering the method of confirming ROI, but all are realized by hand. For instance, in Blobworld system, firstly, the image to be retrieved is segmented into several areas according to image's various features, such as veins, colors and polarity, and then by the way of interaction, the ROI is determined by hand. This thesis, however, tries to adopt the method based on electric registration to automatically determine it.
(3) Features extraction of images based on DT-CWT (see chapter 4). Feature extraction is critical and fundamental to CBIR. The most used methods for feature extraction are: fourier descriptors, moment invariants used to express the shape features, the wavelet and Gabor wavelet used to express the texture feature. But the traditional wavelet bears two deficiencies: shift variance and lack of directionality. Though Gabor wavelet has the excellent directionality, a typical Gabor image analysis is not only expensive to compute and noninvertible, but also yields a great deal of redundant information because of its nonorthogonality. DT-CWT can overcome these deficiencies. It is a good way to abstract image features. Therefore,this thesis analyzes its theory and will adopt it in abstracting image features.
(4) Brain MR images retrieval based on DT-CWT and Kullback-leibler distance similarity measure (see chapter 5). After two stages DT-CWT, an image can get 6 sub-band coefficients in 6 directions for every stage, and then each sub-band coefficient histogram is fitted with Generalized Gaussian Density function. Based on matching moment, this thesis tries to estimate parameters under the maximized likelihood rule. By means of it, 12 pairs of parameters which are image characters are abstracted from each image. After getting the features, measuring the similarity of these features is a critical problem. Grounded on the maximized likelihood selective rule, this thesis applies the Kullback-leibler distance using the chain rule to fulfilling it.
(1)基于GAUSS-MARKOV随机场模型的MR图像分割(对应于本文第二章)。图像分割是图像关键内容区域的选取及量化的基础,利于用图像的关键内容信息进行检索。高斯—马尔可夫随机场模型既利用了图像像素的灰度信息,又通过像素类别标记的Gibbs光滑先验概率引入了图像的空间信息,是能较好地分割含有噪声的图像的模型。然而,Gibbs惩罚因子的确定却一直是个难点,为获得好的分割效果,通常用多个值人工尝试。本文针对此问题,提出了一种新的、简单的、类自适应的惩罚因子,其利用后验概率来自动计算,并具有各类各向异性。再将模型利用EM-MAP算法来迭代求解。最后,将本文算法应用于MR图像的分割,实验表明该算法能自适应地、有效地分割噪声图像,并具有较高的正确分类率和类正确分类率。
(2)基于弹性配准的图像感兴趣区域定位(对应于本文第三章)。疾病的诊断,主要是依据病变区域的形状,大小,及其所在的解剖位置,因而病变区域为感兴趣区域。感兴趣区域的确定有利于在CBIR中只关注医学图像信息的主要部分,得出利于检索的关键信息,使用于检索的特征量显著减少。目前,众多的CBIR都提供了ROI确定的方法,但往往是采用人工交互的方式。如Blobworld中,则先采用图像分割的方法,据待检索图像的多种性质,如纹理,色彩,极性,将待检索图像分割为多个区域,然后通过交互的方式,手工确定一个ROI。本文则尝试使用弹性配准的方法来自动的确定ROI。
(3)图像特征提取(对应于本文第四章)。图像特征提取是图像检索的基础与关键。常用的特征提取方法有:用傅立叶描述符和不变矩表示的形状特征,小波纹理特征,Gabor小波纹理特征。但传统小波变换具有的两大缺点:平移变化性,缺乏方向性。Gabor小波具有方向选择性,但Gabor小波由于非正交性具有大量的数据冗余且不可逆向重构,并具有较高的计算代价。在仔细分析了以上小波变换的缺点后,本文重点介绍了能克服以上小波缺点的双树复数小波变换(DT-CWT)及其原理,并将以此作为图像特征提取的方法。
(4)基于DT-CWT和K-L距离(Kullback-leibler distance)相似性测度的脑部MR图像检索(对应于本文第五章)。对各图像进行二阶DT-CWT后,每级分解得到6个方向的小波子带系数,再利用广义高斯密度(Generalized GaussianDensity)函数来逼近各子带系数的直方图,即使用最大似然估计法得出与各直方图相近的广义高斯密度函数的参数,用矩匹配法得出参数,以这12组特征值来表示该图像特征。提取出图像特征后,本文则基于最大似然规则的图像检索理论,使用基于链式规则的K-L相似性测度来进行特征匹配。
最后,本文对以上研究进行了总结,并对医学CBIR研究进行了展望,讨论了未来的研究方向和目标。
A content-based image retrieval system in medical applications has always been the most vivid research areas in recent ten years, but no general breakthrough has been achieved. This thesis aims to bring some highlight in this field. First, it presents a brief introduction of CBIR system and its key techniques, reviews the current research development, the main research methods and the existed CBIR system, and analyzes the features of medical image. And then, centered on the medical application of CBIR, it mainly does some research about the following issues:
(1) Segmentation of brain MR images based on GAUSS-MARKOV random field model, (see chapter 2). Image segmentation lays foundation for selecting and measuring the key region of content information, which is advantageous for image retrieval to use key information. Gauss-Markov random field model is the often used image segmentation model, taking advantage of both image intensity and spatial information imposed by Gibbs prior. It can be used to effectively segment the images with high levels of noise. However it is always difficult to confirm the Gibbs penalty factor. As usual, it requires a tedious trial-and-error process. So to solve this problem, this paper defines a class-adaptive penalty factor. It is automatically estimated from the posterior probability and is anisotropic for each class. Furthermore the model iteratively gets their parameters estimation in the EM-MAP algorithm. Finally, by application of this algorithm to medical image segmentation, it is proved effective.
(2) Locating region of interest of images based on elastic registration, (see chapter 3). Diagnosing diseases is usually on the basis of the form and size of pathological regions and its anatomic parts. Therefore, the pathological region is also defined as region of interest. To delimit the region of interest is beneficial to CBIR for the purpose of narrowing down information area and getting key retrieval information. By this way, the image information characters for retrieval are tremendously decreased. At present, many CBIRs are capable of offering the method of confirming ROI, but all are realized by hand. For instance, in Blobworld system, firstly, the image to be retrieved is segmented into several areas according to image's various features, such as veins, colors and polarity, and then by the way of interaction, the ROI is determined by hand. This thesis, however, tries to adopt the method based on electric registration to automatically determine it.
(3) Features extraction of images based on DT-CWT (see chapter 4). Feature extraction is critical and fundamental to CBIR. The most used methods for feature extraction are: fourier descriptors, moment invariants used to express the shape features, the wavelet and Gabor wavelet used to express the texture feature. But the traditional wavelet bears two deficiencies: shift variance and lack of directionality. Though Gabor wavelet has the excellent directionality, a typical Gabor image analysis is not only expensive to compute and noninvertible, but also yields a great deal of redundant information because of its nonorthogonality. DT-CWT can overcome these deficiencies. It is a good way to abstract image features. Therefore,this thesis analyzes its theory and will adopt it in abstracting image features.
(4) Brain MR images retrieval based on DT-CWT and Kullback-leibler distance similarity measure (see chapter 5). After two stages DT-CWT, an image can get 6 sub-band coefficients in 6 directions for every stage, and then each sub-band coefficient histogram is fitted with Generalized Gaussian Density function. Based on matching moment, this thesis tries to estimate parameters under the maximized likelihood rule. By means of it, 12 pairs of parameters which are image characters are abstracted from each image. After getting the features, measuring the similarity of these features is a critical problem. Grounded on the maximized likelihood selective rule, this thesis applies the Kullback-leibler distance using the chain rule to fulfilling it.
引文
[1]Cai W,Feng D and Fulton R.Content-based retrieval of dynamic pet functional images.IEEE Transactions on Information Technology in Biomedicine[J].2000,4(2):152-158.
[2]Chu WW,Hsu CC,Cardenas AF,et al.Knowledge-based image retrieval with spatial and temporal constructs[J].IEEE Transactions on Knowledge and Data Engineering,1998,10(6):872-888.
[3]Cox IJ,Miller ML,Minka TP,et al.The Bayesian image retrieval system,PicHunter:Theory,implementation,and psychophysical experiments.IEEE Trans.on Image Processing[J],2000,9(1):20-37.
[4]Gevers T,and Smeulders AWM.Pictoseek:Combining color and shape invariant features for image retrieval[J].IEEE Trans.on image processing,2000,9(1):102-119.
[5]G(u|¨)ld MO,Thies C,Fischer B,Keysers D,Wein BB,Lehmann TM.A platform for distributed image processing and image retrieval[J].Proceedings SPIE 2003,5150:1109-1120.
[6]Henning M,Antoine R,Jean-Paul V,et al.Comparing feature set s for content—based image retrieval in a medical case database[C],SPIE Conference on Medical Imaging,2004,99-109.
[7]Hsu CC,Chu WW and Taira RK.A knowledge-based approach for retrieving images by content[J].IEEE Trans.on Knowledge and Data Engineering,1996,8(4):522-532.
[8]Jing F,Li MJ,etc.An Efficient and Effective Region-Based Image Retrieval Framework[J].IEEE Transactions on Images Processing,2004,13(5):699-710.
[9]Jones1 BF,Schaefer G and Zhu SY.Content-based image retrieval for medical infrared images[C].Proceedings of the 26th Annual International Conference of the IEEE EMBS, 2004, 1186-1187.
[10]Keysers D, Dahmen J, Ney H, et al. A statistical framework for model based image retrieval in medical applications [J]. Journal of Electronic Imaging, 2003,12(1): 59-68.
[11]Korn P, Sidiropoulos N, Faloutsos C, et al. Fast and effective retrieval of medical tumor shapes [J]. IEEE Transactions on Knowledge and Data Engineering, 1998, 10(6): 889-904.
[12]Lehmann TM, Wein B, Dahmen J, et al. Content-based image retrieval in medical applications: A novel multi-step approach [J]. Proceedings SPIE, 2000,3972:312-320.
[13] LI Shunshan ,ZHUANG Tiange . Content-based medical image retrieval. Chinese Journal of Medical Instrumentation [J], 2001, 25(2): 95-98.
[14] Long LR, Antania S, Leeb DJ, Krainakc DM, Thomaa GR. Biomedical information from a national collection of spine x-rays - Film to content-based retrieval [J]. Proceedings SPIE 2003, 5033: 70-84.
[15] Ma WY, Zhang HJ. Bench marking of image features for content-based retrieval [C]. The Thirty-Second Asilomar Conference on Signals, System & Computers,California, USA: 1998, 1: 253 - 257.
[16]Muller H, Michoux N, Bandon D, et al. A review of content-based image retrieval systems in medical applications-clinical benefits and future directions [J]. International Journal of Medical Informatiocits, 2004, 73 (1):1-23.
[17]Nappi M, Polese G,Tortora G FIRST- Fractal indexing and retrieval system for image databases [J]. Image and Vision Computing, 1998, 16: 1019-1031.
[18]Niblack W, Barber R, Equitz W, Flickner M, Yanker P, Ashley J.The QBIC-project - Querying images by content using color, texture and shape [J].Proceedings SPIE, 1993, 19(8): 173-187.
[19]Rui Y, Huang TS, and Chang SF. Image retrieval: current techniques, promising directions and open issues [J]. Journal of Visual Communication and Image Representation, 1999, 10: 39-62.
[20]Shyu CR, Brodley CE, Kak AC, et al. ASSERT: A Physician-in-the-Loop Content-Based Retrieval System for HRCT Image Databases [J]. Computer Vision and Image Understanding, 1999, 75(1/2): 111-132.
[21]Smeulders AWM, Worring M, Santint S, et al. Content-based image retrieval at the end of the early years [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22 (12): 1349-1380.
[22]Tagare HD, Jaffe CC, Dungan J. Medical image databases - A content-based retrieval approach [J]. Journal of the American Medical Informatics Association,1997,4: 184-198.
[23] Wong STC and Tjandra DA. A Digital Library for Biomedical Imaging on the Internet [J]. IEEE Communications Magazine, 1999, 1: 84-91.
[24] Wu JK, Narasimhalu AD, Mehtre BM, et al. CORE: A Content-Based Retrieval Engine for Multimedia Information Systems [J]. Multimedia Systems, 1995, (3):25-41.
[25]Yoshitaka A, Ichikawa T. A survey on content-based retrieval for multimedia databases [J]. IEEE Transaction on Knowledge and Data Engineering, 1999,11(1):81-93.
[26] Lee DD, Seung HS. Learning the parts of objects by non-negative matrix factorization [J]. Nature, 1999, 401, 788-791.
[27]Gunhan Park a, Yunju Baek a, Heung-Kyu Lee b. Re-ranking algorithm using post-retrieval clustering for content-based image retrieval [J]. Information Processing and Management, 2005,41:177-194.
[28]Chiou-Ting Hsu and Chuech-Yu Li. Relevance Feedback Using Generalized Bayesian Framework With Region-Based Optimization Learning [J]. IEEE Transactions on Images Processing,2005, 14(1): 1617-1631.
[29] Thomas M. Lehmanna. Automatic categorization of medical images for content-based retrieval and data mining[J]. Computerized Medical Imaging and Graphics, 2005,29(2): 143-155.
[30] Steven C. H. Hoi, Rong Jin. Batch Mode Active Learning and Its Application to Medical Image Classification [C]. ACM International Conference Proceeding Series; Proceedings of the 23rd international conference on Machine learning,2006.
[31] Wei Jiang. Similarity-Based Online Feature Selection in Content-Based Image Retrieval[J]. IEEE Transaction on Image Processing, 2006, 15(3):702-712.
[32] S. Philipp-Foliguet, J. Gony. FReBIR : Fuzzy Region-Based Image Retrieval[C]. IPMU 06, Paris, 2006.
[33]Sameer Antania, D.J. Leeb and L. Rodney Long. Evaluation of shape similarity measurement methods for spine X-ray images [J]. J. Vis. Commun. Image R.,2004,15:285-302.
[34] Julia Vogela, Bernt Schieleb. Performance evaluation and optimization for content-based image retrieval [J]. Pattern Recognition, 2006, 39: 897-909.
[35] Mohammed Lamine Kherfi and Djemel Ziou. Relevance feedback for CBIR: A new approach based on probabilistic feature weighting with positive and negative Examples[J].IEEE Transaction on Image Processing,2006,15(4):1017-1030
[36]Hong Chang,Dit-Yan Yeung.Kernel-based distance metric learning for content-based image retrieval[J].Image and Vision Computin,2007,25:695-703
[37]周杰.医学图像特征的自动获取与基于内容检索的方法研究.第一军医大学博士学位论文[D].2004
[38]赵晨光,庄天戈.基于内容的医学图像检索[J].国外医学生物医学工程分册.2004,27(2):83-86
[1]Blekas K,Likask A,Galatsanos N P,A spatially constrained mixture model for image segmentation[J].IEEE Transactions on Neural Networks,2005,16(2):494-498.
[2]Wells W M.,Grimson E L,Kikinis R.,etc.Adaptive segmentation of MRI data[J].IEEE Transactions on Med.Image,1996,15(8):429-442.
[3]Guillemaud R,Brady J M.,Estimating the bias field of MR images[J].IEEE Transactions on Medical Imaging,1997,16(7):238-251.
[4]Ruf A,Greenspan H,Goldberger J.Automated tissue classification of noisy MR images of the brain using the constrained multiple multivariate Gaussian mixture model[EB/OL]。http://www.eng.tau.ac.il/～shiri/mip_lab/cgmm.htm。2007-03-28/2007-04-03
[5]Yan Gang,Chen Wu-fan,Feng Yan-qiu.Generalized fuzzy gibbs random field and research on algorithm for MR image segmentation[J].Journal of Image and Graphics,2005,09(10):1082～1088.[颜刚,陈武凡,广义模糊gibbs随机场与MR图像分割算法研究[J],中国图象图形学报.2005,10(9):1082～1088.]
[6]Yan Gang,Chen Wu-fan,Feng Yan-qiu.Improvement of finite mixture model based on gibbs random theory and robust segmentation for brain MR images[J].Chinese Journal of Biomedical Engineering.2003.22(6),193-198.[颜刚,陈武凡,冯衍秋,基于gibbs随机场的有限混合模型改进与脑部MR图像的稳健分割[J],中国生物医学工程学报,2003,22(6):193～198.]
[7]Li Xuchao,Zhu Shan'an.Application of FGMM-MRF hierarchical model to image segmentation[J].Journal of Computer-Aided Dedsign & Computer Graphics,2005,17(12):2660-2664.[李旭超 朱善安,FGMM-MRF层次模型在图像分割中的应用[J].计算机辅助设计与图形学学报,2005,17(12):2660-2664.]
[8]Zhang Yongyue,Brady Michael,Smith Stephen,Segmentation of brain MR images through a hidden markov random field model and the expectation-maximization algorithm[J].IEEE Transactions on Medical Imaging,2001,20(1):45-57.
[9]Sanjay-Gopal S,Thomas J.Hebert,Bayesian Pixel classification using spatially variant finite mixtures and the generalized EM algorithm[J],IEEE Transactions on Image Processing,1998,7(7):1014-1028.
[10] Nikou Christophoros, Galatsanos Nikolaos, Likas Aristidis. A class-adaptive spatially variant mixture model for image segmentation[J]. IEEE Transactions on Image Processing, 2007, 16(4):1121-1130.
[11] Li S Z, Markov random field modeling in image analysis [M].Springer-Verlag ,Tokyo, 2001:19-21.
[12] C Carson, S Belongie, H Greenspan,et al, Blobworld: image segmentation using expectation-maximization and its application to image querying [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(8): 1026 -1038
[1] Senthil Periaswamy and Hany Farid, Elastic Registration in the Presence of Intensity Variations [J], IEEE Transactions on Medical Imaging. 2003. 22(7):865-874.
[2] Hany Farid and Eero P. Simoncelli, Optimally Rotation-Equivariant Directional Derivative Kernels [C]. 7~(th) Int'l Conf Computer Analysis of Image and Patterns,Kiel Germany. September 10-12. 1997.
[3] L. G. Brown. A survey of image registration techniques [J]. ACM Computing Surveys, 1992, 24(4): 325-376.
[4] R.P.Woods. S.T.Grafton, C.J.Holmes. S.R.Chery. and J.C.Mazziotta. Automated image registration: I. general methods and intrasubject. intramodality validation [J], J.Comput.Assist.Tomogr, 1998. 22:141-154.
[5] R.P.Woods. S.T.Grafton. C.J.Holmes, S.R.Chery, and J.C.Mazziotta,Automated image registration: II. intersubject validation of linear and nonlinear models [J], J.Comput.Assist.Tomogr, 1998, 22: 55-165.
[6] J.Shi and C.Tomasi, Good feature to track [J], Computer Vision and Pattern Recognition, June 1994: 593-600.
[7] H.Lester and S.R.Arridge, A survey of hierarchical nonlinear medical image registration [J], Pattern Recogn., 1999, 32(1): 129-149.
[8] O.Nestares and D.J.Heeger, Robust multiresolution alignment of MRI brain volumes [J], Magn.Reson.Med.. 2000, 43: 705-715..
[9] B. K. P. Horn. Robot Vision. Cambridge, MA: MIT Press, 1986.
[10] Zitova B, Flusser J. Image registration methods: a survey[J]. Image and Vision Computing.2003,21:977-1000.
[11] Maintz JBA, Viergever MA. A Survey of Medical Image registration[J].Medical Image Analysis, 1998, 2(1): 1-37.
[1] Persoon E, Fu KS. Shape discrimination using Fourier descriptors [J]. IEEE Trans. System Man Cybernet. 1977, SMC-7 (3): 170-179.
[2] Zhang DS, Lu G A comparison of shape retrieval using Fourier descriptors and short-time Fourier descriptors [C]. In: Proceedings of the Second IEEE Pacilc-Rim Conference on Multimedia (PCM01), Beijing, China, October 24-26,2001:855-860.
[3] Hu M K. Visual pattern recognition by moment invariants [J]. IEEE Transaction on Information Theory, 1962, 8(1): 179-187
[4] Shen L, Rangayyan RM, Desautels JEL. Detection and Classification of Mammographic Calcification [J]. International Journal of Pattern Recognition and Artificial Intelligence, 1993, 7(6) :1403-1416.
[5] Ohm JR, Bunjamin FB, Liebsch W, et al. A set of visual feature descriptors and their combination in a low-level description scheme [J]. Signal Process.Image Commun. 2000, 6: 157-179.
[6] Tieng QM, Boles WW. Recognition of 2D object contours using the wavelet transform zero-crossing representation [J]. IEEE Trans. Pattern Anal. Mach.Intell. 1997, 19 (8): 910-916.
[7] Ahmadian A, Faramarzi E, Sayadian. Image Indexing and Retrieval Using Gabor Wavelet and Legendre Moments [C]. In: Proceedings of the 25th Annual International Conference of the IEEE EMBS Cancun, Mexico September 2003: 17-21.
[8] Manjunath B. S., Ma,W.Y., Texture features for browsing and retrieval of image data [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,. 18(8): 837-42.
[9] Manjunath B,S. Wu P, Newsam S, et al. A texture descriptor for browsing and similarity retrieval [J]. Journal of Signal Processing.Image Communication,2000, 16(1-2): 33-43.
[10] Kingsbury N G.Image processing with complex wavelets[J].Phil. Trans. Roy.Soc.,1999,357(9):2543-2560.
[11]Kingsbury N G.Complex wavelets for shift invariant analysis and filtering of signals[J].Appl.Comp.Harmonic Anal.,2000,10(3):234-253.
[12]Selesnick I W.Hilbert Transform Pairs of Wavelet Bases[J].IEEE Signal Processing Letters,2001,8(6):170-173.
[13]Ozkaramanli H,Yu R.On the phase condition and its solution for Hilbert transform pairs of wavelet bases[J].IEEE Trans.Signal Processing,2003,51(12):3293-3294.
[14]Yu R,Ozkaramanli H.Hilbert transform pairs of orthogonal wavelet bases:necessary and sufficient conditions[J].IEEE Trans.Signal Processing,2005,53(12):4723-4725.
[15]Selesnick I W.The design of approximate Hilbert transform pairs of wavelets bases[J].IEEE Trans.Signal Processing,2002,50(5):1144-1152.
[16]Selesnick I W.Baraniuk R G.The Dual-Tree Complex Wavelets Transform[J].IEEE Trans.Signal Processing,2005,22(6):123-151.
[17]石宏理,胡波,双树复小波变换及其应用综述[J].信息与电子工程,2007,5(3):230:234
[18]吴晓红,罗代升,王正勇,等,基于双树复小波变换的岩心图像去噪[J].西南民族大学报·自然科学版,2007,33(5):1146-1151
[1]K.Sharifi and A.Leon-Garcia,Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video[J].IEEE Trans.Circuits Syst.Video Technol.,1995,5:52-56
[2]G.V.Wouwer,P.Scheunders,and D.V.Dyck,Statistical texture characterization from discrete wavelet representations[J].IEEE rans.Image Processing,1999,8(4):592-598
[3]Minh N.Do,Martin Vetterli,,Wavelet-Based Texture Retrieval Using Generalized Gaussian Density and Kullback-Leibler Distance.[J]IEEE Transactions on Image Processing,2002,11(2):146-158.
[4]T.M.Cover and J.A.Thomas,Elements of Information Theory[M].NewYork:Wiley,1991.
[5]K.Sharifi and A.Leon-Garcia,Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video[J].IEEE Trans.Circuits Syst.Video Technol.,1995.5:52-56,
[6]Daniel D.Lee,H.Sebastian Seung,Learning the parts of objects by non-negative matrix factorization[J],NATURE 1999,401(21):778-791
[7]David Ross,Richard Zemel.Learning Parts-Based Representations of Data[J],Journal of Machine Learning Research,2006,7:2369-2397
[8]江少锋,王文辉,陈武凡,冯前进 基于改进BET算法的MR颅脑图像脑组织自动提取[J],中国图象图形学报(已录用)
[2]Chu WW,Hsu CC,Cardenas AF,et al.Knowledge-based image retrieval with spatial and temporal constructs[J].IEEE Transactions on Knowledge and Data Engineering,1998,10(6):872-888.
[3]Cox IJ,Miller ML,Minka TP,et al.The Bayesian image retrieval system,PicHunter:Theory,implementation,and psychophysical experiments.IEEE Trans.on Image Processing[J],2000,9(1):20-37.
[4]Gevers T,and Smeulders AWM.Pictoseek:Combining color and shape invariant features for image retrieval[J].IEEE Trans.on image processing,2000,9(1):102-119.
[5]G(u|¨)ld MO,Thies C,Fischer B,Keysers D,Wein BB,Lehmann TM.A platform for distributed image processing and image retrieval[J].Proceedings SPIE 2003,5150:1109-1120.
[6]Henning M,Antoine R,Jean-Paul V,et al.Comparing feature set s for content—based image retrieval in a medical case database[C],SPIE Conference on Medical Imaging,2004,99-109.
[7]Hsu CC,Chu WW and Taira RK.A knowledge-based approach for retrieving images by content[J].IEEE Trans.on Knowledge and Data Engineering,1996,8(4):522-532.
[8]Jing F,Li MJ,etc.An Efficient and Effective Region-Based Image Retrieval Framework[J].IEEE Transactions on Images Processing,2004,13(5):699-710.
[9]Jones1 BF,Schaefer G and Zhu SY.Content-based image retrieval for medical infrared images[C].Proceedings of the 26th Annual International Conference of the IEEE EMBS, 2004, 1186-1187.
[10]Keysers D, Dahmen J, Ney H, et al. A statistical framework for model based image retrieval in medical applications [J]. Journal of Electronic Imaging, 2003,12(1): 59-68.
[11]Korn P, Sidiropoulos N, Faloutsos C, et al. Fast and effective retrieval of medical tumor shapes [J]. IEEE Transactions on Knowledge and Data Engineering, 1998, 10(6): 889-904.
[12]Lehmann TM, Wein B, Dahmen J, et al. Content-based image retrieval in medical applications: A novel multi-step approach [J]. Proceedings SPIE, 2000,3972:312-320.
[13] LI Shunshan ,ZHUANG Tiange . Content-based medical image retrieval. Chinese Journal of Medical Instrumentation [J], 2001, 25(2): 95-98.
[14] Long LR, Antania S, Leeb DJ, Krainakc DM, Thomaa GR. Biomedical information from a national collection of spine x-rays - Film to content-based retrieval [J]. Proceedings SPIE 2003, 5033: 70-84.
[15] Ma WY, Zhang HJ. Bench marking of image features for content-based retrieval [C]. The Thirty-Second Asilomar Conference on Signals, System & Computers,California, USA: 1998, 1: 253 - 257.
[16]Muller H, Michoux N, Bandon D, et al. A review of content-based image retrieval systems in medical applications-clinical benefits and future directions [J]. International Journal of Medical Informatiocits, 2004, 73 (1):1-23.
[17]Nappi M, Polese G,Tortora G FIRST- Fractal indexing and retrieval system for image databases [J]. Image and Vision Computing, 1998, 16: 1019-1031.
[18]Niblack W, Barber R, Equitz W, Flickner M, Yanker P, Ashley J.The QBIC-project - Querying images by content using color, texture and shape [J].Proceedings SPIE, 1993, 19(8): 173-187.
[19]Rui Y, Huang TS, and Chang SF. Image retrieval: current techniques, promising directions and open issues [J]. Journal of Visual Communication and Image Representation, 1999, 10: 39-62.
[20]Shyu CR, Brodley CE, Kak AC, et al. ASSERT: A Physician-in-the-Loop Content-Based Retrieval System for HRCT Image Databases [J]. Computer Vision and Image Understanding, 1999, 75(1/2): 111-132.
[21]Smeulders AWM, Worring M, Santint S, et al. Content-based image retrieval at the end of the early years [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22 (12): 1349-1380.
[22]Tagare HD, Jaffe CC, Dungan J. Medical image databases - A content-based retrieval approach [J]. Journal of the American Medical Informatics Association,1997,4: 184-198.
[23] Wong STC and Tjandra DA. A Digital Library for Biomedical Imaging on the Internet [J]. IEEE Communications Magazine, 1999, 1: 84-91.
[24] Wu JK, Narasimhalu AD, Mehtre BM, et al. CORE: A Content-Based Retrieval Engine for Multimedia Information Systems [J]. Multimedia Systems, 1995, (3):25-41.
[25]Yoshitaka A, Ichikawa T. A survey on content-based retrieval for multimedia databases [J]. IEEE Transaction on Knowledge and Data Engineering, 1999,11(1):81-93.
[26] Lee DD, Seung HS. Learning the parts of objects by non-negative matrix factorization [J]. Nature, 1999, 401, 788-791.
[27]Gunhan Park a, Yunju Baek a, Heung-Kyu Lee b. Re-ranking algorithm using post-retrieval clustering for content-based image retrieval [J]. Information Processing and Management, 2005,41:177-194.
[28]Chiou-Ting Hsu and Chuech-Yu Li. Relevance Feedback Using Generalized Bayesian Framework With Region-Based Optimization Learning [J]. IEEE Transactions on Images Processing,2005, 14(1): 1617-1631.
[29] Thomas M. Lehmanna. Automatic categorization of medical images for content-based retrieval and data mining[J]. Computerized Medical Imaging and Graphics, 2005,29(2): 143-155.
[30] Steven C. H. Hoi, Rong Jin. Batch Mode Active Learning and Its Application to Medical Image Classification [C]. ACM International Conference Proceeding Series; Proceedings of the 23rd international conference on Machine learning,2006.
[31] Wei Jiang. Similarity-Based Online Feature Selection in Content-Based Image Retrieval[J]. IEEE Transaction on Image Processing, 2006, 15(3):702-712.
[32] S. Philipp-Foliguet, J. Gony. FReBIR : Fuzzy Region-Based Image Retrieval[C]. IPMU 06, Paris, 2006.
[33]Sameer Antania, D.J. Leeb and L. Rodney Long. Evaluation of shape similarity measurement methods for spine X-ray images [J]. J. Vis. Commun. Image R.,2004,15:285-302.
[34] Julia Vogela, Bernt Schieleb. Performance evaluation and optimization for content-based image retrieval [J]. Pattern Recognition, 2006, 39: 897-909.
[35] Mohammed Lamine Kherfi and Djemel Ziou. Relevance feedback for CBIR: A new approach based on probabilistic feature weighting with positive and negative Examples[J].IEEE Transaction on Image Processing,2006,15(4):1017-1030
[36]Hong Chang,Dit-Yan Yeung.Kernel-based distance metric learning for content-based image retrieval[J].Image and Vision Computin,2007,25:695-703
[37]周杰.医学图像特征的自动获取与基于内容检索的方法研究.第一军医大学博士学位论文[D].2004
[38]赵晨光,庄天戈.基于内容的医学图像检索[J].国外医学生物医学工程分册.2004,27(2):83-86
[1]Blekas K,Likask A,Galatsanos N P,A spatially constrained mixture model for image segmentation[J].IEEE Transactions on Neural Networks,2005,16(2):494-498.
[2]Wells W M.,Grimson E L,Kikinis R.,etc.Adaptive segmentation of MRI data[J].IEEE Transactions on Med.Image,1996,15(8):429-442.
[3]Guillemaud R,Brady J M.,Estimating the bias field of MR images[J].IEEE Transactions on Medical Imaging,1997,16(7):238-251.
[4]Ruf A,Greenspan H,Goldberger J.Automated tissue classification of noisy MR images of the brain using the constrained multiple multivariate Gaussian mixture model[EB/OL]。http://www.eng.tau.ac.il/～shiri/mip_lab/cgmm.htm。2007-03-28/2007-04-03
[5]Yan Gang,Chen Wu-fan,Feng Yan-qiu.Generalized fuzzy gibbs random field and research on algorithm for MR image segmentation[J].Journal of Image and Graphics,2005,09(10):1082～1088.[颜刚,陈武凡,广义模糊gibbs随机场与MR图像分割算法研究[J],中国图象图形学报.2005,10(9):1082～1088.]
[6]Yan Gang,Chen Wu-fan,Feng Yan-qiu.Improvement of finite mixture model based on gibbs random theory and robust segmentation for brain MR images[J].Chinese Journal of Biomedical Engineering.2003.22(6),193-198.[颜刚,陈武凡,冯衍秋,基于gibbs随机场的有限混合模型改进与脑部MR图像的稳健分割[J],中国生物医学工程学报,2003,22(6):193～198.]
[7]Li Xuchao,Zhu Shan'an.Application of FGMM-MRF hierarchical model to image segmentation[J].Journal of Computer-Aided Dedsign & Computer Graphics,2005,17(12):2660-2664.[李旭超 朱善安,FGMM-MRF层次模型在图像分割中的应用[J].计算机辅助设计与图形学学报,2005,17(12):2660-2664.]
[8]Zhang Yongyue,Brady Michael,Smith Stephen,Segmentation of brain MR images through a hidden markov random field model and the expectation-maximization algorithm[J].IEEE Transactions on Medical Imaging,2001,20(1):45-57.
[9]Sanjay-Gopal S,Thomas J.Hebert,Bayesian Pixel classification using spatially variant finite mixtures and the generalized EM algorithm[J],IEEE Transactions on Image Processing,1998,7(7):1014-1028.
[10] Nikou Christophoros, Galatsanos Nikolaos, Likas Aristidis. A class-adaptive spatially variant mixture model for image segmentation[J]. IEEE Transactions on Image Processing, 2007, 16(4):1121-1130.
[11] Li S Z, Markov random field modeling in image analysis [M].Springer-Verlag ,Tokyo, 2001:19-21.
[12] C Carson, S Belongie, H Greenspan,et al, Blobworld: image segmentation using expectation-maximization and its application to image querying [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(8): 1026 -1038
[1] Senthil Periaswamy and Hany Farid, Elastic Registration in the Presence of Intensity Variations [J], IEEE Transactions on Medical Imaging. 2003. 22(7):865-874.
[2] Hany Farid and Eero P. Simoncelli, Optimally Rotation-Equivariant Directional Derivative Kernels [C]. 7~(th) Int'l Conf Computer Analysis of Image and Patterns,Kiel Germany. September 10-12. 1997.
[3] L. G. Brown. A survey of image registration techniques [J]. ACM Computing Surveys, 1992, 24(4): 325-376.
[4] R.P.Woods. S.T.Grafton, C.J.Holmes. S.R.Chery. and J.C.Mazziotta. Automated image registration: I. general methods and intrasubject. intramodality validation [J], J.Comput.Assist.Tomogr, 1998. 22:141-154.
[5] R.P.Woods. S.T.Grafton. C.J.Holmes, S.R.Chery, and J.C.Mazziotta,Automated image registration: II. intersubject validation of linear and nonlinear models [J], J.Comput.Assist.Tomogr, 1998, 22: 55-165.
[6] J.Shi and C.Tomasi, Good feature to track [J], Computer Vision and Pattern Recognition, June 1994: 593-600.
[7] H.Lester and S.R.Arridge, A survey of hierarchical nonlinear medical image registration [J], Pattern Recogn., 1999, 32(1): 129-149.
[8] O.Nestares and D.J.Heeger, Robust multiresolution alignment of MRI brain volumes [J], Magn.Reson.Med.. 2000, 43: 705-715..
[9] B. K. P. Horn. Robot Vision. Cambridge, MA: MIT Press, 1986.
[10] Zitova B, Flusser J. Image registration methods: a survey[J]. Image and Vision Computing.2003,21:977-1000.
[11] Maintz JBA, Viergever MA. A Survey of Medical Image registration[J].Medical Image Analysis, 1998, 2(1): 1-37.
[1] Persoon E, Fu KS. Shape discrimination using Fourier descriptors [J]. IEEE Trans. System Man Cybernet. 1977, SMC-7 (3): 170-179.
[2] Zhang DS, Lu G A comparison of shape retrieval using Fourier descriptors and short-time Fourier descriptors [C]. In: Proceedings of the Second IEEE Pacilc-Rim Conference on Multimedia (PCM01), Beijing, China, October 24-26,2001:855-860.
[3] Hu M K. Visual pattern recognition by moment invariants [J]. IEEE Transaction on Information Theory, 1962, 8(1): 179-187
[4] Shen L, Rangayyan RM, Desautels JEL. Detection and Classification of Mammographic Calcification [J]. International Journal of Pattern Recognition and Artificial Intelligence, 1993, 7(6) :1403-1416.
[5] Ohm JR, Bunjamin FB, Liebsch W, et al. A set of visual feature descriptors and their combination in a low-level description scheme [J]. Signal Process.Image Commun. 2000, 6: 157-179.
[6] Tieng QM, Boles WW. Recognition of 2D object contours using the wavelet transform zero-crossing representation [J]. IEEE Trans. Pattern Anal. Mach.Intell. 1997, 19 (8): 910-916.
[7] Ahmadian A, Faramarzi E, Sayadian. Image Indexing and Retrieval Using Gabor Wavelet and Legendre Moments [C]. In: Proceedings of the 25th Annual International Conference of the IEEE EMBS Cancun, Mexico September 2003: 17-21.
[8] Manjunath B. S., Ma,W.Y., Texture features for browsing and retrieval of image data [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,. 18(8): 837-42.
[9] Manjunath B,S. Wu P, Newsam S, et al. A texture descriptor for browsing and similarity retrieval [J]. Journal of Signal Processing.Image Communication,2000, 16(1-2): 33-43.
[10] Kingsbury N G.Image processing with complex wavelets[J].Phil. Trans. Roy.Soc.,1999,357(9):2543-2560.
[11]Kingsbury N G.Complex wavelets for shift invariant analysis and filtering of signals[J].Appl.Comp.Harmonic Anal.,2000,10(3):234-253.
[12]Selesnick I W.Hilbert Transform Pairs of Wavelet Bases[J].IEEE Signal Processing Letters,2001,8(6):170-173.
[13]Ozkaramanli H,Yu R.On the phase condition and its solution for Hilbert transform pairs of wavelet bases[J].IEEE Trans.Signal Processing,2003,51(12):3293-3294.
[14]Yu R,Ozkaramanli H.Hilbert transform pairs of orthogonal wavelet bases:necessary and sufficient conditions[J].IEEE Trans.Signal Processing,2005,53(12):4723-4725.
[15]Selesnick I W.The design of approximate Hilbert transform pairs of wavelets bases[J].IEEE Trans.Signal Processing,2002,50(5):1144-1152.
[16]Selesnick I W.Baraniuk R G.The Dual-Tree Complex Wavelets Transform[J].IEEE Trans.Signal Processing,2005,22(6):123-151.
[17]石宏理,胡波,双树复小波变换及其应用综述[J].信息与电子工程,2007,5(3):230:234
[18]吴晓红,罗代升,王正勇,等,基于双树复小波变换的岩心图像去噪[J].西南民族大学报·自然科学版,2007,33(5):1146-1151
[1]K.Sharifi and A.Leon-Garcia,Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video[J].IEEE Trans.Circuits Syst.Video Technol.,1995,5:52-56
[2]G.V.Wouwer,P.Scheunders,and D.V.Dyck,Statistical texture characterization from discrete wavelet representations[J].IEEE rans.Image Processing,1999,8(4):592-598
[3]Minh N.Do,Martin Vetterli,,Wavelet-Based Texture Retrieval Using Generalized Gaussian Density and Kullback-Leibler Distance.[J]IEEE Transactions on Image Processing,2002,11(2):146-158.
[4]T.M.Cover and J.A.Thomas,Elements of Information Theory[M].NewYork:Wiley,1991.
[5]K.Sharifi and A.Leon-Garcia,Estimation of shape parameter for generalized Gaussian distributions in subband decompositions of video[J].IEEE Trans.Circuits Syst.Video Technol.,1995.5:52-56,
[6]Daniel D.Lee,H.Sebastian Seung,Learning the parts of objects by non-negative matrix factorization[J],NATURE 1999,401(21):778-791
[7]David Ross,Richard Zemel.Learning Parts-Based Representations of Data[J],Journal of Machine Learning Research,2006,7:2369-2397
[8]江少锋,王文辉,陈武凡,冯前进 基于改进BET算法的MR颅脑图像脑组织自动提取[J],中国图象图形学报(已录用)