Download PDF
Methods Inf Med 2004; 43(02): 150-155
DOI: 10.1055/s-0038-1633853
Original Article
Schattauer GmbH

Simulation Based Analysis of Automated Classification of Medical Images

W. Adler
1   Department of Medical Informatics, Biometry and Epidemiology, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany
,
T. Hothorn
1   Department of Medical Informatics, Biometry and Epidemiology, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany
,
B. Lausen
1   Department of Medical Informatics, Biometry and Epidemiology, Friedrich-Alexander-University of Erlangen-Nuremberg, Erlangen, Germany
› Author Affiliations
Further Information

Publication History

Publication Date:
05 February 2018 (online)

    Permissions and Reprints

Summary

Objectives: The ability of various classifiers to discriminate between normal and glaucomatous eyes based on features derived from automated analysis of laser scanning images of the eye background is investigated.

Methods: To compare the classifiers without over-optimization for a given dataset, we use a simulation model to create topography images. We designed three different simulation setups as model of extreme situations and medical subgroups.

Results: Neither linear nor tree-based classifiers are ideal for all setups. The most robust performance is obtained by a combination of both, so-called Double-Bagging. Classification of real data from a case-control study shows best results with Double-Bagging. All results obtained with the analysis method extracting features automatically are worse than those obtained by the same classifiers but with features derived from an analysis method that requires intervention of a physician.

Conclusions: Robust classification results for classification of laser scanning images obtained with the Heidelberg Retina Tomograph are achieved by combined classifiers. The examined automated procedure causes an increased misclassification error compared to the established clinical routine requiring an expert physician’s intervention.

Keywords

Classification - laser scanning images - glaucoma - simulation
 

  • References

  • 1 Coleman AL. Glaucoma. The Lancet 1999; 354 9192 1803-10.
    CrossrefPubMedGoogle Scholar
  • 2 Mardin CY, Hothorn T, Peters A, Jünemann AG, Nguyen NX, Lausen B. New glaucoma classification method based on standard HRT parameters by bagging classification trees. Journal of Glaucoma 2003; 12: 340-6.
    CrossrefPubMedGoogle Scholar
  • 3 Michelson G, Groh MJ. Screening models for glaucoma. Current Opinion in Ophthalmology 2001; 12: 105-11.
    CrossrefPubMedGoogle Scholar
  • 4 Peters A, Lausen B, Michelson G, Gefeller O. Diagnosis of glaucoma by indirect classifiers. Methods of Information in Medicine 2003; 42: 99-103.
    Article in Thieme ConnectPubMedGoogle Scholar
  • 5 Mikelberg FS, Parfitt CM, Swindale NV, Graham SL, Drance SM, Gosine R. Ability of the Heidelberg Retina Tomograph to detect early glaucomatous visual field loss. Journal of Glaucoma 1995; 4: 242-7.
    PubMedGoogle Scholar
  • 6 Mardin CY, Horn FK, Jonas JB, Budde WM. Preperimetric glaucoma diagnosis by confocal scanning laser tomography of the optic disc. British Journal of Ophthalmology 1999; 83 (03) 299-304.
    CrossrefPubMedGoogle Scholar
  • 7 Heidelberg-Engineering. Heidelberg Retina Tomograph: Bedienungsanleitung Software Version 2.01. Heidelberg: Heidelberg Engineering GmbH; 1997.
    PubMedGoogle Scholar
  • 8 Chrastek R, Wolf M, Donath K, Michelson G, Niemann H. Automated outlining of the external margin of the optic disk for early diagnosis of glaucoma. In Shuskova LT, Nikitin OP, Samsonov LM, Polushin PA. (eds) Physics and Radioelectronics in Medicine and Ecology, Proceedings of the 5th International Conference; 2002 Vladimir State University. 2002: 16-9.
    Google Scholar
  • 9 Swindale NV, Stjepanovic G, Chin A, Mikelberg FS. Automated analysis of normal and glaucomatous optic nerve head topography images. Investigative Ophthalmology and Visual Science 2000; 41 (07) 1730-42.
    PubMedGoogle Scholar
  • 10 Hothorn T, Lausen B. Bagging tree classifiers for laser scanning images: a data- and simulationbased strategy. Artificial Intelligence in Medicine 2003; 27: 65-79.
    CrossrefPubMedGoogle Scholar
  • 11 Press WH, Teukolsky S, Vetterling W, Flannery B. Numerical Recipes in FORTRAN – The Art of Scientific Computing. 2 ed. New York: Cambridge University Press; 1992: 675-94.
    Google Scholar
  • 12 Breiman L, Friedman JH, Olshen RA, Stone CJ. Classification and regression trees. California: Wadsworth; 1984
    Google Scholar
  • 13 Breiman L. Bagging Predictors. Machine Learning 1996; 24 (02) 123-40.
    PubMedGoogle Scholar
  • 14 Hothorn T, Lausen B. Double-Bagging: combining classifiers by bootstrap aggregation. Pattern Recognition 2003; 36 (06) 1303-9.
    CrossrefPubMedGoogle Scholar
  • 15 Efron B, Tibshirani R. Improvements on crossvalidation: the .632+ bootstrap method. Journal of the American Statistical Association 1997; 92 (438) 548-60.
    PubMedGoogle Scholar
  • 16 Ihaka R, Gentleman R. R: a language for data analysis and graphics. Journal of Computational and Graphical Statistics 1996; 5: 299-314.
    PubMedGoogle Scholar
  • 17 Peters A, Hothorn T, Lausen B. ipred: Improved Predictors. R News 2002; 2 (02) 33-6.
    PubMedGoogle Scholar
  • 18 Therneau TM, Atkinson EJ. An introduction to recursive partitioning using the rpart routine. Rochester: Section of Biostatistics, Mayo Clinic. 1997. Report No 61
    Google Scholar