Computerized Cell Image Analysis: Past, Present, and Future

  • Ewert Bengtsson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)


The visual interpretation of images is at the core of most medical diagnostic procedures and the final decision for many diseases is based on microscopic examination of cells and tissues. Through screening of cell samples the incidence and mortality of cervical cancer have been reduced significantly. The visual interpretation is, however, tedious and in many cases error-prone. Therefore many attempts have been made at using the computer to supplement or replace the human visual inspection by computer analysis and to automate some of the more tedious visual screening tasks. In this paper these developments are traced from their very beginning through the present situation and into the future. The paper concludes with a discussion of the possibilities of applying the gained experiences to create the toolbox needed to turn functional genomics from prospect to reality.


Cervical Cancer Computerize Image Analysis Transitional Cell Bladder Carcinoma Conventional Smear Stain Cell Nucleus 
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.


  1. 1.
    Caspersson T: Die Untersuchung der Nukleinsuerferteilung im Zellkern. Z Wiss Mikrosk Technik 53:403, 1936.Google Scholar
  2. 2.
    Papanicolaou GN & Traut HF: Diagnosis of Uterine Cancer by the Vaginal Smear. Oxford University Press, New York, 1943.Google Scholar
  3. 3.
    Stenkvist B, Bergstrm R, Eklund G & Fox C: Papanicolaou Smear Screening and Cervical Cancer. What Can You Expect? JAMA 252:1423–1426, 1984CrossRefGoogle Scholar
  4. 4.
    Christopherson WM, Parker JE, Mendez WM & Lundin FE: Cervix Cancer Rates and Mass Cytologic Screening. Cancer 26:808–811, 1970.CrossRefGoogle Scholar
  5. 5.
    Mellor RC & Silver R: A microfluorometric scanner for the differential detection of cells: application to exfoliate cytology. Science 114: 356–360, 1951.CrossRefGoogle Scholar
  6. 6.
    Tolles WE & Bostrom RC: Automatic Screening of Cytological Smears for Cancer: The Instrumentation. Ann NY Acad Sci 63:1211–1218, 1956.CrossRefGoogle Scholar
  7. 7.
    Spencer CC & Bostrom RC: Performance of the Cytoanalyzer in Recent Clinical Trials. Jour Nat Cancer Inst 29:267, 1962.Google Scholar
  8. 8.
    Spriggs AI, Diamond RA & Meyer EW: A New Principle for AutomatedScreening of Cervical Smears. Lancet 1:359, 1968.CrossRefGoogle Scholar
  9. 9.
    Watanabe S and the CYBEST group: An Automated Apparatus for Cancer Prescreening: CYBEST. Comp Graph Image Proc 3:350–358, 1974CrossRefGoogle Scholar
  10. 10.
    Bostrom RC & Holcomb WG: CYDAC-A Digital Scanning Cytophotometer. IEEE Int Conv Rec 9:110–119, 1963Google Scholar
  11. 11.
    Wied GL, Bartels PH, Bahr GF & Oldfield DB: Taxonomic Intra-cellularAnalytic System (TICAS) for Cell Identification. Acta Cytol 12:180–204, 1968Google Scholar
  12. 12.
    Vrolijk J, Pearson PL & Ploem JS: LEYTAS: A System for the Processing of Microscopic Images. Analyt Quant Cytol 2:41–48, 1980Google Scholar
  13. 13.
    Brugal G, Garbay C, Giroud F & Adelh D: A Double Scanning Microphotometer for Image Analysis: Hardware, Software and Biomedical Applications. J Histochem Cytochem 27:144–153, 1979.Google Scholar
  14. 14.
    Bengtsson E, Eriksson O, Jarkrans T, Nordin B & Stenkvist B: CELLO-An Interactive System for Image Analysis. In Bolc L & Kulpa L (eds.): Digital Image Processing Systems, Lecture Notes in Computer Science 109. Springer Verlag, Berlin, 1981.Google Scholar
  15. 15.
    Zahniser DJ: Automation of Pap Smear Analysis: A Review and Status Report. In Haralick, RM (ed.): Pictorial Data Analysis. Springer, 1983Google Scholar
  16. 16.
    Erhardt R, Reinhardt E, Schlipf W & Bloss WH: FAZYTAN: A System for Fast Automated Cell Segmentation, Cell Image Analysis and Feature Extraction Based on TV-image Pickup and Parallel Processing. Analyt Quant Cytol 2:25–40, 1980.Google Scholar
  17. 17.
    Tucker JH & Husain OAN: Trials with the CERVISCAN Experimental Prescreening Device on Polylysine-prepared Slides. Analyt Quant Cytol 3:117–120, 1981.Google Scholar
  18. 18.
    Ploem JS, van Driel-Kulker AMJ & Verwoerd NP: LEYTAS-A Cytology Screening System Using the New Modular Image Analysis Computer (MIAC) from Leitz. In Burger G, Ploem JS & Goerttler K (eds.): Clinical Cytometry and Histometry: 24–35, Academic Press, London, 1987.Google Scholar
  19. 19.
    Nordin B: The Development of an Automated Prescreener for the Early Detection of Cervical Cancer. Algorithms and Implementation. PhD Thesis, Uppsala Univ., 155 p,1989.Google Scholar
  20. 20.
    Schulerud H,. Kristensen G.B,. Liestøl K, Vlatkovic L., Reith A, Albregtsen., F. Danielsen H.E.. A review of caveats in statistical nuclear image analysis, Analytical Cellular Path., 16:63–82, 1998.Google Scholar
  21. 21.
    Fallenius A, Franzén S & Auer G: Predictive value of nuclear DNA content in breast cancer in relation to clinical and morphologic factors. A retrospective study of 227 consecutive cases. Cancer 62: 521–530, 1988CrossRefGoogle Scholar
  22. 22.
    Koss L G: The Papanicolaou Test for Cervical Cancer Detection-A Triumph and a Tragedy. JAMA 261:737–743, 1989.CrossRefGoogle Scholar
  23. 23.
    Hutchinson ML, Cassin CM & Ball HG: The Efficacy of an Automated Preparation Device for Cervical Cytology. Am J. Clinical Path. 96:300–305, 1991.Google Scholar
  24. 24.
    Howell LP, Davis RL, Belk TI, Agdigos R, Lowe J. The AutoCyte preparation system for gynaecologic cytology. Acta Cytol., 42:171–177, 1998.Google Scholar
  25. 25.
    DeCresce RP & Lifshitz MS: PAPNET Cytological Screening System. Lab Medicine 22:276–280, 1991.Google Scholar
  26. 26.
    Lee J, Nelson A, Wilbur DC, Patten SF. The Development of an Automated Papanicolau Smear Screening System. Cancer, 81: 332–336, 1998.CrossRefGoogle Scholar
  27. 27.
    Ranefall P, Wester K, Bengtsson E. Automatic quantification of immunohistochemically stained cell nuclei using unsupervised image analysis.. Analytical Cellular Path., 58, 1997.Google Scholar
  28. 28.
    Ranefall P, Wester K, Andersson AC, Busch C, Bengtsson E. Automatic quantification of immunohistochemically stained cell nuclei based on standard reference cells. Analytical Cellular Path., 111–123, 1998.Google Scholar
  29. 29.
    Jarkrans T, Vasko J, Bengtsson E, Choi HK, Malmström PU, Wester K, Busch C. Grading of transitional cell bladder carcinoma by image analysis of histological sections: Analytical Cellular Path.. 8:135–158, 1995.Google Scholar
  30. 30.
    Choi HK, Vasko J, Bengtsson E, Jarkrans T, Malmström PU, Wester K, Busch C. Grading of Transitional Cell Bladder Carcinoma by Texture Analysis of Histological Sections.: Analytical Cellular Path. 6:327–343, 1994.Google Scholar
  31. 31.
    Ranefall P, Bengtsson E, Busch C, Malmström PU. Automatic Quantification of Microvessel Density in Urinary Bladder Carcinoma.. British Journal of Cancer, 81,8: 1363–1370, 1999.CrossRefGoogle Scholar
  32. 32.
    Tripath website: Scholar
  33. 33.
    Cytyc website: Scholar
  34. 34.
    Molecular Diagnostics website: Scholar
  35. 35.
    Brugal G., Dye R., Krief B., Chassery J.M., Tanke H., Tucker J.H. HOME: Highly Optimized Microscope Environment. Cytometry, Vol 13, pp 109–116, 1992.CrossRefGoogle Scholar
  36. 36.
    SCIENCE Volume 300, Number 5616, Issue of 4 Apr 2003.Google Scholar
  37. 37.
    First International Cytomics Conference website: Scholar
  38. 38.
    The Open Microscopy Environment website: Scholar
  39. 39.
    Gustavsson T., Althoff K., Degerman J., Olsson T., Thorlin T., Eriksson P., Time-Lapse Microscopy and Image Processing for Stem Cell Research-Modeling Cell Migration, Proceedings of SPIE, Vol. X, San Diego, USA, February 15–20, 2003.Google Scholar
  40. 40.
    Gustavsson T., Althoff K., Degerman J., Olsson T., Thoreson A.C., Thorlin T., Eriksson P., Time-Lapse Microscopy and Hidden Markov Modeling for Applications to Stem Cell Research. The 20th Annual Houston Conference on Biomedical Engineering Research, Houston, USA, April 2003.Google Scholar
  41. 41.
    Lindblad J, Wählby C, Bengtsson E, Zaltsman A. Image Analysis for Automatic Segmentation of Cytoplasms and Classification of Rac1 Activation. Submitted for journal publication, 2003, also in PhD thesis of J Lindblad, Uppsala Univ.2003.Google Scholar
  42. 42.
    Wählby C, Lindblad J, Vondrus M, Bengtsson E, Björkesten L. Algorithms for cytoplasm segmentation of fluorescence labelled cells. Analytical Cellular Path 24:101–111, 2002.Google Scholar
  43. 43.
    Nilsson, M. et al. Padlock probes: Circularizing oligonucleotides for localized DNA detection. Science 265, 2085–2088 (1994).CrossRefGoogle Scholar
  44. 44.
    Nilsson, M., Barbany, G., Antson, D.-O., Gertow, K. & Landegren, U. Enhanced detection and distinction of RNA by enzymatic probe ligation. Nat. Biotechnol. 18, 791–793 (2000).CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Ewert Bengtsson
    • 1
  1. 1.Centre for Image AnalysisUppsala UniversityUppsalaSweden

Personalised recommendations