COMPUTER AIDED DIAGNOSIS OF CONFOCAL LASER SCANNING MICROSCOPY IMAGES OF MELANOCYTIC SKIN TUMOURS

The aim of this study is to check the application of machine learning algorithms for the computer aided diagnosis of confocal laser scanning microscopy (CLSM) views of skin lesions. The images were dissected in equal square elements where the features, based on spectral properties of the wavelet transform, were calculated out. The images were discriminated according their features by several machine learning algorithms, based on tree classifiers, function classifiers and lazy classifiers. The results were evaluated and show that tree classifiers allow the best discrimination between CLSM views of benign common nevi and malignant melanoma.