Download PDF
Methods Inf Med 1988; 27(02): 53-57
DOI: 10.1055/s-0038-1635520
Original Article
Schattauer GmbH

New Trends of Image Analysis in the Medical Field

Neue Entwicklungen der Bildverarbeitung in der Medizin
J. Dengler
1   (From the Department of Medical and Biological Informatics, the German Cancer Research Center, Heidelberg and the Department of Radiology at the Medical Center of the University Hospital of Gießen, F.R.G.)
,
H. Bertsch
1   (From the Department of Medical and Biological Informatics, the German Cancer Research Center, Heidelberg and the Department of Radiology at the Medical Center of the University Hospital of Gießen, F.R.G.)
,
J. F. Desaga
1   (From the Department of Medical and Biological Informatics, the German Cancer Research Center, Heidelberg and the Department of Radiology at the Medical Center of the University Hospital of Gießen, F.R.G.)
,
M. Schmidt
1   (From the Department of Medical and Biological Informatics, the German Cancer Research Center, Heidelberg and the Department of Radiology at the Medical Center of the University Hospital of Gießen, F.R.G.)
› Author Affiliations
Further Information

Publication History

Publication Date:
17 February 2018 (online)

  PDF Download  Permissions and Reprints

Summary

Image analysis with the aid of the computer has rapidly developed over the last few years. There are many possibilities of making use of this development in the medical and biological field. This paper is meant to give a rather general overview of recent systematics regarding the existing methodology in image analysis. Furthermore, some parts of these systematics are illustrated in greater detail by recent research work in the German Cancer Research Center. In particular, two applications are reported where special emphasis is laid on mathematical morphology. This relatively new approach to image analysis finds growing interest in the image processing community and has its strength in bridging the gap between a priori knowledge and image analysis procedures.

Die Bildverarbeitung mit Computern hat sich in den letzten Jahren schnell entwickelt. Davon kann im medizinischen und biologischen Bereich auf vielfältige Weise Gebrauch gemacht werden. Dieser Beitrag entwirft eine allgemeine Systematik der in der Bildverarbeitung angewandten Methoden. Darüber hinaus werden Teile dieser Systematik an neueren Forschungsarbeiten aus dem Deutschen Krebsforschungszentrum illustriert. Insbesondere werden zwei Anwendungen vorgestellt, in denen der Schwerpunkt auf der mathematischen Morphologie liegt, einem noch recht jungen Ansatz, der in der Bildverarbeitung wachsendes Interesse findet. Seine Stärke liegt darin, die Lücke zwischen A-priori-Vorwissen und den Bildverarbeitungsprozeduren zu schließen.

Key-Words:

Image Processing - Mathematical Morphology - Pneumoconiosis - Cell Segmentation

Schlüssel-Wörter:

Bildverarbeitung - mathematische Morphologie - Pneumoconiosis - Zellsegmentierung
 

  • REFERENCES

  • 1 Bertsch H, Dengler J, Desaga J. F, Meinzer H-R. Classification of pneumoconiosis by the self-learning topological feature map. Submitted to International Conference on Pattern Recognition. 1988
    Google Scholar
  • 2 Bigün J, Granlund G. H. Optimal Orientation Detection of Linear Symmetry. Proc. 1st International Conference on Computer Vision. Washington: IEEE Comp. Soc. Press; 1987: 433-438. 1987
    Google Scholar
  • 3 Burt P. J. The Pyramid as a Structure for Efficient Computation. In Rosenfeld A. (Ed.) Multiresolution Image Processing and Analysis. Berlin – Heidelberg – New York – Tokyo: Springer; 1984
    Google Scholar
  • 4 Cooley W. W, Lohnes P. R. Multivariate Data Analysis. London: John Wiley & Sons; 1971
    Google Scholar
  • 5 Dengler J, Schmidt M. A Multigrid Approach for the Stereo Problem with Depth Discontinuities. Accepted for International Society for Photogrammetry and Remote Sensing. 1988
    Google Scholar
  • 6 Fu K. S. Syntactical Methods in Pattern Recognition. New York, San Francisco, London: Academic Press; 1974
    Google Scholar
  • 7 Kass M, Witkin A. Analysing Oriented Patterns. Comput. Vis. Graph. Image Proc 1987; 37: 362-385.
    CrossrefPubMedGoogle Scholar
  • 8 Marr D. Vision. San Francisco: W. H. Freeman and Co; 1982
    Google Scholar
  • 9 Matheron G. Random Sets and Integral Geometry. London: John Wiley & Sons; 1975
    Google Scholar
  • 10 Pavlidis T. Structural Pattern Recognition. Berlin – Heidelberg – New York: Springer; 1977
    Google Scholar
  • 11 Rosenfeld A, Kak A.C. Digital Picture Processing. New York – San Francisco – London: Academic Press; 1976
    Google Scholar
  • 12 Schmidt M, Dengler J, Holder S, Meinzer H-R. Recognition and Segmentation of Cell Structures of Varying Intensities by Means of Linear and Morphological Filters. Accepted for Medical Informatics Europe. 1988
    Google Scholar
  • 13 Serra J. Image Analysis and Mathematical Morphology. London: Academic Press; 1982
    Google Scholar
  • 14 Serra J. From Mathematical Morphology to Artificial Intelligence. Proc. 8th International Conference on Pattern Recognition. Washington: IEEE Comp. Soc. Press; 1986: 1336-1343. 1986
    Google Scholar
  • 15 Shapiro L. G, Haralick R. M. Relational Matching. Appl. Optics 1987; 26: 1845-1851.
    CrossrefPubMedGoogle Scholar
  • 16 Sternberg S. R. Grayscale Morphology. Comput. Vision Graph. Image Proc 1986; 35: 333-355.
    CrossrefPubMedGoogle Scholar
  • 17 Tai J. W, Fu K. S. Semantic Syntax-Directed Translation for Pictorial Pattern Recognition. Proc. 6th International Conference on Pattern Recognition. Washington: IEEE Comp. Soc. Press; 1982: 169-171. 1985
    Google Scholar
  • 18 Torre V, Poggio T. A. On Edge Detection. IEEE Trans. Patt. Anal. Mach. Intell., PAMI-8. 1986; 147-163.
    PubMedGoogle Scholar
  • 19 Tsotsos J. K. A “Complexity Level” Analysis of Vision. Proc. 1st International Conference on Computer Vision. Washington: IEEE Comp. Soc. Press; 1987: 346-355. 1987
    Google Scholar
  • 20 Wilson H, Bergen J. A Four Mechanism Model for Spatial Vision. Vision Res 1979; 19: 19-32.
    CrossrefPubMedGoogle Scholar