Compression of Medical Images by Using Artificial Neural Networks

  • Zümray Dokur
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4113)


This paper presents a novel lossy compression scheme for medical images by using an incremental self–organized map (ISOM). Three neural networks for lossy compression scheme are comparatively examined: Kohonen map, multi-layer perceptron (MLP) and ISOM. In the compression process of the proposed method, the image is first decomposed into blocks of 8(8 pixels. Two-dimensional discrete cosine transform (2D-DCT) coefficients are computed for each block. The dimension of DCT coefficients vectors (codewords) is reduced by low-pass filtering. Huffman coding is applied to the indexes of codewords obtained by the ISOM. In the decompression process, inverse operations of each stage of the compression are performed in the opposite way. It is observed that the proposed method gives much better compression rates.


Artificial Neural Network Mean Square Error Medical Image Ultrasound Image Image Compression 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Wallace, G.K.: JPEG Still Picture Compression Standard. Comm. ACM 34(4), 32–34 (1991)CrossRefGoogle Scholar
  2. 2.
    Strintzis, M.: Optimal Pyramidal and Subband Decomposition for Hierarchical Coding of Noisy and Quantized Images. IEEE Tran. on Image Pro. 7(2), 155–166 (1998)CrossRefMathSciNetGoogle Scholar
  3. 3.
    Tzovaras, D., Strintzis, M.: Use of Nonlinear Principal Component Analysis and Vector Quantization for Image Coding. IEEE Tran. on Image Pro. 7(8), 1218–1223 (1998)zbMATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Amerijckx, C., Verleysen, M., Thissen, P., Legat, J.D.: Image Compression by Self-Organized Kohonen Map. IEEE Trans. on Neural Networks 9(3), 503–507 (1998)CrossRefGoogle Scholar
  5. 5.
    Pal, S., Ghosh, A., Kundu, M.: Soft Computing for Image Processing. Springer, Heidelberg (2000)zbMATHGoogle Scholar
  6. 6.
    Ahmed, N., Natarajan, T., Rao, K.R.: Discrete Cosine Transform. IEEE Trans. Comput. C-23, 90–93 (1974)zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Mougeot, M., Azencott, R., Angeniol, B.: A Study of Image Compression with Backpropagation. In: Neurocomputing. NATO ASI Series, vol. F-68, pp. 333–336 (1990)Google Scholar
  8. 8.
    Blanchet, P.: Data Compression Using Multilayer Perceptron. In: Neurocomputing. NATO ASI Series, vol. F 68, pp. 237–240 (1990)Google Scholar
  9. 9.
    Kohonen, T.: An Introduction to Neural Computing. Neural Networks 1, 3–16 (1988)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Zümray Dokur
    • 1
  1. 1.Department of Electronics and Communication EngineeringIstanbul Technical UniversityMaslakTurkey

Personalised recommendations