6th ESACP Congress, Heidelberg, April 7-11, 1999

A110
DIAGNOSTIC CLASSIFICATION BASED ON FRACTAL FEATURES IN THE PERIPHERY OF CELL NUCLEI FROM LIVER LESIONS
Nielsen B, Albregtsen F, Danielsen HE

Group for Data Analysis, Signal and Image Processing, Department of Informatics, University of Oslo Blindern, Oslo, Division of Digital Pathology, the Norwegian Radium Hospital, Montebello, Oslo, Norway

A polygonization-based method was used to estimate the fractal dimension and several new scalar lacunarity features from digitized transmission electron micrographs (TEM) of mouse liver cell nuclei. The fractal features have been estimated in different segments of 1D curves obtained by scanning the 2D cell nuclei in a spiral-like fashion called ``peel-off-scanning''. This is a venue to separate estimates of fractal features in the center and periphery of a cell nucleus. Our aim was to see if a small set of fractal features could discriminate between samples from normal (including regenerating) liver, hyperplastic nodules and hepatocellular carcinomas. The Bhattacharyya distance was used to evaluate the features on the training data set. Bayesian classification with pooled covariance matrix and equal prior probabilties was used as the rule for classification. The conclusion after testing on an independent test set was that several single fractal features estimated from the periphery of the cell nuclei could discriminate samples from the hyperplastic nodules and hepatocellular carcinomas from normal ones. The outer 25%-30% of the cell nuclei contained important texture information about the differences between the classes. The polygonization-based method was also used as an analysis tool to relate the differences between the classes to differences in the chromatin structure.