Melanoma Detection From Lesion Images Using Optimized Features Selected by Metaheuristic Algorithms

Abstract

This paper deals with a simple but efficient method for detection of deadly malignant melanoma with optimized handcrafted feature sets selected by three alternative metaheuristic algorithms, namely particle swarm optimization (PSO), ant colony optimization (ACO), and simulated annealing (SA). A total of 1,898 features relating to lesion shapes, colors, and textures are extracted from each of the 170 non-dermoscopy camera images of the popular MED-NODE dataset. This large feature set is then optimized, and the number of features is reduced up to the range of single digit using metaheuristic algorithms as feature selector. Two well-known supervised classifiers (i.e., support vector machine [SVM] and artificial neural network [ANN]) are used to classify malignant and benign lesions. The best classification accuracy result found by this method is 87.69% with only seven features selected by PSO using ANN classifier which is far better than the results found in the literature so far.