Automatic detection of acute lymphoblastic leukaemia based on extending the multifractal features

Abstract

The main purpose of this study is to introduce a new species of features to improve the diagnosis efficiency of acute lymphoblastic leukaemia from microscopic images. First, the authors segmented nuclei by the k -means and watershed algorithms. They extracted three sets of geometrical, statistical, and chaotic features from nuclei images. Six chaotic features were extracted by calculating the fractal dimension from five sub-images driven from the nuclei images, with their grey levels being modified. The authors classified the images into binary and multiclass types via the support vector machine algorithm. They conducted principal component analysis for dimensional reduction of feature space and then evaluated the proposed algorithm for the overfitting problem. The obtained overall results represent 99% accuracy, 99% specificity, and 97% sensitivity values in the classification of six-cell groups. The difference between the train and test errors was <;3%, which proves that the classification performance had improved by using the multifractal features.