FLUORESCENCE INTENSITY POSITIVITY CLASSIFICATION OF HEP-2 CELLS IMAGES USING FUZZY LOGIC

Indirect Immunofluorescence (IIF) is a gold standard used for antinuclear autoantibody (ANA) test using Hep-2 cells to determine specific diseases. Automated interpretation is crucial to assure high accuracy to determine the autoantibody type of diseases. There are different classifier algorithm methods that have been proposed in previous works to classify the fluorescence intensity, however, there is still no valid algorithms to set as a standard. The purpose of this study is to classify the fluorescence intensity by using fuzzy logic algorithm to determine the positivity of the Hep2-cell serum samples. The scope of study of this project involves converting the RGB colour space of images to LAB colour space and the mean value of the lightness channel and chromaticity layer (a) channel is extracted and classified by using fuzzy logic algorithm based on the standard score ranges of ANA fluorescence intensity which are 4+, 3+, 2+, 1+ and 0. Based on the results, the accuracy of intermediate and positive class is 85% and 87% respectively.