Sequential Analysis of Medical Images Using Neural Networks

  • Marek Czeleń
  • Grzegorz Wojtas
  • Zbigniew Mikrut
Conference paper
Part of the Advances in Soft Computing book series (AINSC, volume 19)


A problem frequently encountered in the analysis of medical images is reaching a correct and reliable diagnosis of the examined organ, particularly by persons with little experience, e.g. first year medical students. That fact has become an inspiration for construction of an assisting program, based on application of three neural networks: 1) moving the attention point along the selected object, 2) elaborating the diagnosis for the area in the current viewport, 3) reporting the end of the examination.

In the present work a summary is done for almost a hundred of experiments, testing the efficiency of all those neural networks in the analysis of raw medical images. The final version of the algorithm uses backpropagation type networks: it operates on square areas which are 31×31 pixels in size for the first and third networks and 91×91 pixels in size for the second (diagnosing) network. The achieved level of correct recognition (about 80%) is a very good result, if one takes into account rather low quality (dynamic range) of the analysed images and the observed natural interferences.


Neural Network Pancreatic Duct Receptor Field Motion Direction Convolutional Neural Network 
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.
    van de Laar P., Heskes T., Gielen S. (1997) Task-Dependent Learning of Attention. Neural Networks vo1.10 no 6, PergamonGoogle Scholar
  2. 2.
    Lindblad T., Lindsey C., Padgett M., Vanyachine A., Zanevsky I. (1998) Digital X-Ray image processing using biologically inspired methods. Proc. IJCNN, Anchorage, Alaska.Google Scholar
  3. 3.
    Mikrut Z., Tadeusiewicz R. (2000) Neural Networks applied to digital image processing and recognition, in: Biocybernetics and Biomedical Engineering, Vol. 6, Ed. Nalgcz M. AOW EXIT, Warsaw (in Polish)Google Scholar
  4. 4.
    Neubauer C. (1998) Evaluation of Convolutional Neural Networks for Visual Recognition. IEEE Trans. Neural Networks, Vol. 9, No. 4Google Scholar
  5. 5.
    Ogiela M., Tadeusiewicz R. (2000) Syntactic Pattern Recognition for X-Ray Diagnosis of Pancreatic Duct. Eng. in Medicine and Biology, IEEE Magazine, 19, 6.Google Scholar
  6. 6.
    Postma E., Herik H., Hudson P. (1997) SCAN: A Scalable Model of Attentional Selection. Neural Networks vol.10 No. 6, PergamonGoogle Scholar
  7. 7.
    Sjostrom P. J., Wahlberd L.U. (1999) Automated cell recognition and counting based on combination of artificial neural networks and standard image analysis methods. Proc. 3rd Int. Conf. Cognitive and Neural Systems, BostonGoogle Scholar
  8. 8.
    Zurada J. M. (1992) Introduction to artificial neural networks. West Publ., St. Paul New York.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Marek Czeleń
    • 1
  • Grzegorz Wojtas
    • 1
  • Zbigniew Mikrut
    • 1
  1. 1.Institute of AutomaticsUniversity of Mining and MetallurgyKrakówPoland

Personalised recommendations