Automatic identification of metaphase spreads and nuclei using neural networks

  • F. Arámbula Cosío
  • L. Vega
  • A. Herrera Becerra
  • R. Prieto Meléndez
  • G. Corkidi
Article

Abstract

The mitotic index (MI) is an important measure in cell proliferation studies. Determination of the MI is usually made by light-microscope analysis of slide preparations. The analyst identifies and counts thousands of cells and reports the percentage of mitotic shapes found, among the interphase nuclei. Full automation of this process is an ambitious task, because there can exist very few mitotic shapes among hundreds of nuclei and thousands of artifacts, resulting in a high probability of false positives, i.e. objects erroneously identified as mitosis or nuclei. A semiautomated approach for MI calculation is reported, based on the development of a neural network (NN) for automatic identification of metaphase spreads and stimulated nuclei in digital images of microscope preparations at 10X magnification. After segmentation of the objects on each image, ten different morphometrical, photometrical and textural features are measured on each segmented object. An NN is used to classify the feature vectors into three classes: metaphases, nuclei and artifacts. The system has been able to classify correctly approximately 91% of the objects in each class, in a test set of 191 mitosis, 331 nuclei and 387 artifacts, obtained from 30 different microscope slides. Manual editing of false positives from the metaphase classification results allows the calculation of the MI with an error of 6.5%.

Keywords

Metaphase finder Automatic metaphase counting Mitotic index Neural network classifier 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Barile, F. A. (Ed.) (1994): ‘In vitro cytotoxicology, Mechanisms and methods’ (CRC Press, USA) pp. 1–222Google Scholar
  2. Barnard, E., andCasasent, D. (1989): ‘Image processing for image understanding with neural nets’. Int. Joint Conf. NN, Vol. 1, pp. 111–115Google Scholar
  3. Castleman, K. R. (1992): ‘The PSI automatic metaphase finder’,J. Radiat. Res.,33, pp. 124–128Google Scholar
  4. Castleman, K. R., andWhite, B. S. (1995): ‘Dot count proportion estimation in FISH specimens’,Bioimaging,3, pp. 88–93CrossRefGoogle Scholar
  5. Corkidi, G., Vega, L., Marquez, J., Rojas, E., andOstrosky-Wegman, P. (1998): ‘Roughness feature of metaphase chromosome spreads and nuclei for automated cell proliferation analysis,’Med. Biol. Eng. Comput.,36, pp. 679–685Google Scholar
  6. Garza-Jinich, M., Rodriguez, C., Corkidi, G., Montero, R., Rojas, E., andOstrosky-Wegman, P. (1992): ‘A microcomputer-based supervised system for automatic scoring of mitotic index in citotoxicity studies’ inArchibald, C., andPetriu, E. (Eds): ‘Advances in machine vision, Vol. 32’ (World Scientific Press series on Computer Science), pp. 301–313Google Scholar
  7. Hertz, J., Krog, A., andPalmer, R. G. (1991): ‘Introduction to the theory of neural computation’, Lecture Notes, Santa Fe Institute, Vol. 1 (Addison-Wesley)Google Scholar
  8. Hu, Y., Ashenayi, K., Veltri, R., O'Dowd, G., Miller, G., Hurst, R., andBonner, R. (1994): ‘A comparison of neural network and fuzzy c-means methods in bladder cancer cell classification’, IEEE Inc. Conf. NN, Vol. 6, pp. 3461–3466Google Scholar
  9. McLean, J. R. N., andJohnson, F. (1995): ‘Evaluation of a metaphase chromosome finder: potential application to chromosome-based radiation dosimetry’,Micron,26, pp. 489–492CrossRefGoogle Scholar
  10. Musavi, M. T., Bryant, R. J., Qiao, M., Davisson, M. T., Akeson, E. C., andFrench, B. D. (1998): ‘Mouse chromosome classification by radial basis function network with fast, orthogonal search’,Neural Networks, pp. 769–777Google Scholar
  11. Otsu, N. (1979): ‘A threshold selection method from gray-level histograms’,IEEE Trans. Syst. Man Cybern.,9, pp. 62–66Google Scholar
  12. Rojas, E., Montero, R., Herrera, L. A., Sordo, M., Gonsebatt, M. E., Rodriguez, R., andOstrosky-Wegman, P. (1992): ‘Are mitotic index and lymphocyte kinetic reproducible endpoints in genetic toxicology testing?’,Mutation Res.,282, pp. 283–286Google Scholar
  13. Rosenfeld, A., andTroy, E. (1970): ‘Visual texture analysis’, Technical Report, University of Maryland, College Park, Maryland USA, pp. 70–116Google Scholar
  14. Vrolijk, J., Sloos, W. C., Darroudi, F., Natarajan, A. T., andTanke, H. J. (1994): ‘A system for flourescence metaphase finding and scoring of chromosomal translocations visualized byin situ hybridization’,Int. J. Radiat. Biol.,66, pp. 287–295Google Scholar
  15. Zacknich, A., andAttikiouzel, Y. (1995): ‘Detection of sodium oxalate needles in optical images using neural network classifiers’, IEEE. Int. Conf. NN, Vol. 4, pp. 1699–1702Google Scholar

Copyright information

© IFMBE 2001

Authors and Affiliations

  • F. Arámbula Cosío
    • 1
  • L. Vega
    • 2
  • A. Herrera Becerra
    • 1
  • R. Prieto Meléndez
    • 1
  • G. Corkidi
    • 2
  1. 1.Centro de InstrumentosUNAMMexico
  2. 2.Instituto de BiotecnologíaUNAMCuernavacaMexico

Personalised recommendations