PCA-Based Feature Selection for MRI Image Retrieval System Using Texture Features

Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 324)


Due to the vast number of medical technologies and equipments, the medical images are growing at a rapid rate. This directs to retrieve efficient medical images based on visual contents. This paper proposed the magnetic resonance imagining (MRI) scan image retrieval system using co-occurrence matrix-based texture features. Here, the principal component analysis (PCA) is applied for optimized feature selection to overcome the difficulties of feature vector creation with Haralick’s texture features. Then, K-means clustering and Euclidean distance measure are used to retrieve best MRI scan images for the query image in medical diagnosis. The experimental results demonstrate the efficiency of this system in clusters accuracy and best MRI scan image retrieval against using all the fourteen familiar Haralick’s texture features.


Co-occurrence matrix Euclidean distance K-means clustering PCA Texture features 


  1. 1.
    H. Muller, N. Michoux, D. Bandon, A. Geissbuhler, A review of content-based image retrieval systems in medical applications: clinical benefits and future directions. Int. J. Med. Inform. 73, 1–23 (2004)CrossRefGoogle Scholar
  2. 2.
    X.S. Zhou, S. Zillner, M. Moeller et al., Semantics and CBIR: a medical imaging perspective, in ACM Conference on Content-based Image and Video Retrieval (2008) pp. 571–580Google Scholar
  3. 3.
    C.B. Akgül, D.L. Rubin, S. Napel, C.F. Beaulieu et al., Content-based image retrieval in radiology: current status and future directions. J. Dig. Imag. 24(2), 208–222 (2011)Google Scholar
  4. 4.
    B. Ramamurthy, K.R. Chandran, Content based medical image retrieval with texture content using gray level co-occurrence matrix and K-means clustering algorithms. J. Comput. Sci. 8(7), 1070–1076 (2012)CrossRefGoogle Scholar
  5. 5.
    U. Sinha, H. Kangarloo, Principal component analysis for content-based image retrieval. Radiographics 22, 1271–1289 (2002)CrossRefGoogle Scholar
  6. 6.
    G.N. Lee, H. Fujita, K-means clustering for classifying unlabelled MRI data, in IEEE Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications (2007) pp. 92–98Google Scholar
  7. 7.
    S. Ayyachamy, V.S. Manivannan, Distance measures for medical image retrieval. Int. J. Imag. Syst. Technol. 23(1), 9–21 (2013)Google Scholar
  8. 8.
    R. Haralick, K. Shanmugam, I. Dinstein, Textural features for image classification. IEEE Trans. Syst. Man. Cybern. 3(6), 610–621 (1973)CrossRefGoogle Scholar
  9. 9.
    H. Shao, W.C. Cui, H. Zhao, Medical image retrieval based on visual contents and text information, in IEEE International Conference on Systems (2004) pp. 1098–1103Google Scholar
  10. 10.
    A.G. Selvarani, S. Annadurai, Medical image retrieval by combining low level features and Dicom features, in IEEE International Conference on Computational Intelligent and Multimedia Applications (2007), pp. 587–589Google Scholar
  11. 11.
    W. Horsthemke, D. Raicu, J. Furst, Task-oriented medical image retrieval, in MICCAI Work Shop Proceedings (2007) pp. 31–44Google Scholar
  12. 12.
    P. Zhang, H. Zhu, Medical image retrieval based on co-occurrence matrix and edge histogram, in IEEE conference on multimedia technology (2011) pp. 5434–5437Google Scholar
  13. 13.
    T.R. Sivapriya, V. Saravanan, P. Ranjit Jeba Thangaiah, Texture analysis of brain MRI and classification with BPN for the diagnosis of dementia. Eng. Inf. Technol. Commun. Comput. Inf. Sci. 20(4), 553–563 (2011)Google Scholar
  14. 14.
    B.G. Prasad, A.N. Krishna, Statistical texture feature-based retrieval and performance evaluation of CT brain images, in IEEE International Conference on Electronics Computer Technology (2011) pp. 1–4Google Scholar
  15. 15.
    N. Kumaran, R. Bhavani, Spine MRI image retrieval using texture features. Int. J. Comput. Appl. 46(24), 1–7 (2012)Google Scholar

Copyright information

© Springer India 2015

Authors and Affiliations

  1. 1.Department of Computer Science and EngineeringAnnamalai UniversityChidambaramIndia

Personalised recommendations