Computer recognition of skin structures using discriminant and cluster analysis

Background/aims: Automated image analysis of complex tissues is usually limited by the difficulty of recognizing special structures by computer. The aim of this study was to test the applicability of discriminant and cluster analysis to the interpretation of skin images.

[1]  E. Kuntsche,et al.  Multivariate Analysemethoden: Eine anwendungsorientierte Einführung. , 2001 .

[2]  P H Bartels,et al.  Automated histometry in quantitative prostate pathology. , 1998, Analytical and quantitative cytology and histology.

[3]  F. B. Sørensen,et al.  Stereological estimates of nuclear volume in thin malignant melanomas , 1998, Melanoma research.

[4]  M. Binder,et al.  Increased nuclear volume in metastasizing "thick" melanomas. , 1996, The Journal of investigative dermatology.

[5]  M. Binder,et al.  Estimation of the volume-weighted mean nuclear volume discriminates Spitz's nevi from nodular malignant melanomas. , 1994, Laboratory investigation; a journal of technical methods and pathology.

[6]  R. Barnhill.  Pathology and prognostic factors , 1993, Current opinion in oncology.

[7]  A R Brown,et al.  Combined immunocytochemical staining and image analysis for the study of lymphocyte specificity and function in situ. , 1990, Journal of immunological methods.

[8]  E E Sahn,et al.  A new method for the comprehensive automatic morphologic image analysis of Langerhans cells. , 1988, The American Journal of dermatopathology.

[9]  L. Koss.  Quantitative and analytical cytology in historical perspective. , 1994, Journal of cellular biochemistry. Supplement.