A framework for medical image retrieval using merging-based classification with dependency probability-based relevance feedback

Content-based image retrieval (CBIR) systems are used to retrieve relevant images from large-scale databases. In this paper, a framework for the image retrieval of a large-scale database of medical X-ray images is presented. This framework is designed based on query image classification into several prespecified homogeneous classes. Using a merging scheme and an iterative classification, the homogeneous classes are formed from overlapping classes in the database. For this purpose, the shape and texture features, selected using the forward selection algorithm, are optimized by a novel genetic algorithm-based feature reduction and optimization algorithm in the feature space. In this algorithm, using a new fitness function, we try to locate similar images in the database together in the feature space. Using the merging-based classification, the m-nearest classes to the query image are selected as a filtered search space. To increase the retrieval efficiency, we integrate a novel dependency probability-based relevance feedback (RF) approach with the proposed CBIR framework. The proposed RF uses a synthetic distance measure based on the weighted Euclidean distance measure and Gaussian mixture model-based dependency probability similarity measure of the database images to the Gaussian mixture distribution function of the positive images. The experimental results are reported based on a database consisting of 10,000 medical X-ray images of 57 classes (ImageCLEF 2005 database). The provided results show the effectiveness of the proposed framework compared to the approaches presented in the literature.

A framework for medical image retrieval using merging-based classification with dependency probability-based relevance feedback

Content-based image retrieval (CBIR) systems are used to retrieve relevant images from large-scale databases. In this paper, a framework for the image retrieval of a large-scale database of medical X-ray images is presented. This framework is designed based on query image classification into several prespecified homogeneous classes. Using a merging scheme and an iterative classification, the homogeneous classes are formed from overlapping classes in the database. For this purpose, the shape and texture features, selected using the forward selection algorithm, are optimized by a novel genetic algorithm-based feature reduction and optimization algorithm in the feature space. In this algorithm, using a new fitness function, we try to locate similar images in the database together in the feature space. Using the merging-based classification, the m-nearest classes to the query image are selected as a filtered search space. To increase the retrieval efficiency, we integrate a novel dependency probability-based relevance feedback (RF) approach with the proposed CBIR framework. The proposed RF uses a synthetic distance measure based on the weighted Euclidean distance measure and Gaussian mixture model-based dependency probability similarity measure of the database images to the Gaussian mixture distribution function of the positive images. The experimental results are reported based on a database consisting of 10,000 medical X-ray images of 57 classes (ImageCLEF 2005 database). The provided results show the effectiveness of the proposed framework compared to the approaches presented in the literature.

___

  • [1] H. Pourghassem, H. Ghassemian, “Content-based medical image classification using a new hierarchical merging scheme”, Journal of Computerized Medical Imaging and Graphics, Vol. 22, pp. 651–661, 2008.
  • [2] C. Shyu, C. Brodley, A. Kak, A. Kosaka, A. Aisen, L. Broderick, “ASSERT: A physician-in-the-loop content-based image retrieval system for HRCT image databases”, Computer Vision and Image Understanding, Vol. 75, pp. 111–132, 1999.
  • [3] T. Lehmann, M. Guld, C. Thies, B. Fischer, K. Spitzer, D. Keysers, H. Ney, M. Kohnen, H. Schubert, B.B. Wein, “Content-based image retrieval in medical applications”, Methods of Information in Medicine, Vol. 43, pp. 354–361, 2004.
  • [4] S. Antani, D.J. Lee, L.R. Long, G.R. Thoma, “Evaluation of shape similarity measurement methods for spine X-ray images”, Journal of Visual Communication and Image Representation, Vol. 15, pp. 285–302, 2004.
  • [5] J.G. Dy, C.E. Brodley, A. Kak, L.S. Broderick, A.M. Aisen, “Unsupervised feature selection applied to contentbased retrieval of lung images”, IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 25, pp. 373–378, 2003.
  • [6] C.R. Shyu, C.A. Pavlopoulou, C. Kak, C.E. Brodley, “Using human perceptual categories for content-based retrieval from a medical image database”, Computer Vision and Image Understanding, Vol. 88, pp. 119–151, 2002.
  • [7] P. Korn, N. Sidiropoulos, C. Faloutsos, E. Siegel, Z. Protopapas, “Fast and effective retrieval of medical tumor shapes”, IEEE Transactions on Knowledge and Data Engineering, Vol. 10, pp. 889–904, 1998.
  • [8] S.N. Yu, C.T. Chianga, C.C. Hsieh, “A three-object model for the similarity searches of chest CT images”, Computerized Medical Imaging and Graphics, Vol. 29, pp. 617–630, 2005.
  • [9] L.L.G. Oliveira, S.A. Silva, L.H.V. Ribeiro, R.M. Oliveira, C. Coelho, A.S.S. Andrade, “Computer-aided diagnosis in chest radiography for detection of childhood pneumonia”, International Journal of Medical Informatics, Vol. 77, pp. 555–564, 2007.
  • [10] L.R. Long, S. Antania, D.J. Leeb, D.M. Krainakc, G.R. Thoma, “Biomedical information from a national collection of spine X-rays film to content-based retrieval” Proceedings of SPIE, Vol. 5033, pp. 70–84, 2003.
  • [11] L.R. Long, K. Sameer, A. George, R. Thoma, “Image informatics at a national research center”, Computerized Medical Imaging and Graphics, Vol. 29, pp. 171–193, 2005.
  • [12] X. Xu, D.J. Lee, S. Antani, L.R. Long, “A spine X-ray image retrieval system using partial shape matching”, IEEE Transactions on Information Technology in Biomedicine, Vol. 12, pp. 100–108, 2008.
  • [13] O. Nomira, M. Abdel-Mottalebb, “Hierarchical contour matching for dental X-ray radiographs”, Pattern Recognition, Vol. 41, pp. 130–138, 2008.
  • [14] H. M¨uller, A. Rosset, J.P. Vall´ee, A. Geissbuhler, “Comparing feature sets for content-based medical information retrieval”, Proceedings of SPIE Medical Imaging, Vol. 5351, pp. 99–109, 2004.
  • [15] W.W. Chu, C.C. Hsu, A.F. Cardenas, R.K. Taira, “Knowledge-based image retrieval with spatial and temporal constructs”, IEEE Transactions on Knowledge and Data Engineering, Vol. 10, pp. 872–888, 1998.
  • [16] H. Greenspan, A.T. Pinhas, “Medical image categorization and retrieval for PACS using the GMM-KL framework”, IEEE Transactions on Information Technology in Biomedicine, Vol. 11, pp. 190–202, 2007.
  • [17] M.M. Rahman, P. Bhattacharya, B.C. Desai, “A framework for medical image retrieval using machine learning and statistical similarity matching techniques with relevance feedback”, IEEE Transactions on Information Technology in Biomedicine, Vol. 11, pp. 58–69, 2007.
  • [18] M.M. Rahman, B.C. Desai, P. Bhattacharya, “Medical image retrieval with probabilistic multi-class support vector machine classifiers and adaptive similarity fusion”, Computerized Medical Imaging and Graphics, Vol. 32, pp. 95–108, 2008.
  • [19] J. Yao, Z. Zhang, S. Antani, R. Long, G. Thoma, “Automatic medical image annotation and retrieval”, Neurocomputing, Vol. 71, pp. 2012–2022, 2008.
  • [20] L. Yang, F. Algregtsen, “Fast computation of invariant geometric moments: a new method giving correct results”, Proceedings of the 12th IAPR International Conference on Pattern Recognition. Conference A: Computer Vision & Image Processing, Vol. 1, pp. 201–204, 1994.
  • [21] N. Otsu, “A threshold selection method from gray-scale histogram,” IEEE Transactions on Systems, Man, and Cybernetics, Vol. 8, pp. 62–66, 1978.
  • [22] E. Persoon, K. Fu, “Shape discrimination using Fourier descriptors”, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 7, pp. 170–79, 1977.
  • [23] A.K. Jain, Fundamentals of Digital Image Processing, New Jersey, Prentice Hall, 1989.
  • [24] R.M. Haralick, K. Shanmugan, I. Dinstein, “Textural features for image classification”, IEEE Transactions on Systems, Man, and Cybernetics, Vol. 3, pp. 610–621, 1973.
  • [25] A.L. Blum, P. Langley, “Selection of relevant features and examples in machine learning”, Artificial Intelligence, Vol. 97, pp. 245–271, 1997.
  • [26] S.X. Yu, “Feature selection and classifier ensembles: a study on hyperspectral remote sensing data”, PhD, University of Antwerp, 2005.
  • [27] M. Mitchell, An Introduction to Genetic Algorithms, Cambridge, MA, MIT Press, 1996.
  • [28] E. de Ves, J. Domingo, G. Ayala, P. Zuccarello, “A novel Bayesian framework for relevance feedback in image content-based retrieval systems”, Pattern Recognition, Vol. 39, pp. 1622–1632, 2006.
  • [29] P.C. Cheng, B.C. Chien, H.R. Ke, W.P. Yang, “A two-level relevance feedback mechanism for image retrieval”, Expert Systems with Applications, Vol. 34, pp. 2193–2200, 2008.
  • [30] F. Qian, M. Li, L. Zhang, H. Zhang, B. Zhang, “Gaussian mixture model for relevance feedback in image retrieval”, IEEE International Conference on Multimedia and Expo, Vol. 1, pp. 229–232, 2002.
  • [31] A.K. Jain, B. Bhandrasekaran, “Dimensionality and sample size considerations in pattern recognition practice”, in: P.R. Krishnaiah, L.N. Kanal, Eds., Handbook of Statistics, Amsterdam, Elsevier, pp. 835–855, 1987.
  • [32] T. Deselaers, D. Keysers, H. Ney, “Classification error rate for quantitative evaluation of content-based image retrieval systems”, Proceedings of the 17th International Conference on Pattern Recognition, Vol. 2, pp. 505–508, 2004.
  • [33] H. Muller, T. Deselaers, T.M. Lehmann, P. Clough, E. Kim, W. Hersh, “Overview of the ImageCLEFmed 2006 medical retrieval and annotation tasks”, CLEF Proceedings, Lecture Notes in Computer Science, pp. 595–608, 2007.