Advertisement

Segmentation of sputum color image for lung cancer diagnosis based on neural networks

  • Sammouda Rachid
  • Noboru Niki
  • Hiromu Nishitani
  • S. Nakamura
  • S. Mori
Poster Session D: Biomedical Applications, Detection, Control & Surveillance, Inspection, Optical Character Recognition
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1311)

Abstract

The paper presents a method for automatic segmentation of sputum cells with color images, to develop an efficient algorithm for lung cancer diagnosis based on a Hopfield neural network. We formulate the segmentation problem as a minimization of an energy function constructed with two terms, the cost-term as a sum of squared errors, and the second term a temporary noise added to the network as an excitation to escape certain local minima with the result of being closer to the global minimum. To increase the accuracy in segmenting the regions of interest, a preclassification technique is used to extract the sputum cell regions within the color image and remove those of the debris cells. The former is then given with the raw image to the input of Hopfield neural network to make a crisp segmentation by assigning each pixel to label such as Background, Cytoplasm, and Nucleus. The proposed technique has yielded correct segmentation of complex scene of sputum prepared by ordinary manual staining method in most of the tested images selected from our database containing thousands of sputum color images.

Keywords

Sputum cells Lung cancer diagnosis RGB images Segmentation Optimization Hopfield neural network 

References

  1. 1.
    J. Mayo, N. L. Muller, and R.M Henkelman “The double-fissure sign: A motion artifact on thin section CT scans”, Radiology 165, 50–581, 1987.Google Scholar
  2. 2.
    R. D. Tarver, D. L. Conces, and J. D. Godwin, “Motion artifacts on CT simulate bronchi ectasis” Am. J. Roentgenol. 151, 1117–1119, 1988.Google Scholar
  3. 3.
    Jiang Hsiel, “A genral approach to the reconstruction of the X-ray Helical Computed Tomography”, Med. Phy. 23 (2), 221–229, February 1996.CrossRefGoogle Scholar
  4. 4.
    Jian king Lin and Yee-Hong, “Multiresolution Color Image Segmentation”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 16 No. 7, 689–700, July 1994.CrossRefGoogle Scholar
  5. 5.
    Papanicalaou GN & Trant HF, “Diagnosis of Uterine Cancer by the Vaginal Smear”. Oxford University press, New York 1943.Google Scholar
  6. 6.
    S. C. Amartur, D. Piraino, and Y. Kakefuji, “Optimization Neural Networks for the Segmentation of Magnetic Resonance Images”, IEEE Transaction on Medical Imaging, vol. 11, No. 2, June 1992.Google Scholar
  7. 7.
    R. Sammouda, N. Niki and H. Nishitani, “Segmentation of Brain MR Images Based on Neural Networks”, IEICE Trans. Inf. & Syst., vol. E79-D, No. 4, 349–356, April 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Sammouda Rachid
    • 1
  • Noboru Niki
    • 2
  • Hiromu Nishitani
    • 2
  • S. Nakamura
    • 3
  • S. Mori
    • 3
  1. 1.Dept. of Optical ScienceUniversity of TokushimaJapan
  2. 2.Medical School of TokushimaJapan
  3. 3.Tokushima Health Screening CenterJapan

Personalised recommendations