Border Irregularity Measure Using Hidden Markov Models as a Malignant Melanoma Predictor
Benjamin S. Aribisala · 2005
Abstract. Malignant melanoma, a skin cancer, manifests itself as a dark lesion, most often with an irregular boundary. The degree of irregularity is an important diagnostic indicator. This paper presents a new measure of irregularity using Hidden Markov Models (HMMs) based on the Weibull probability distribution. The measure was tested on 98 skin lesions of which 16 were malignant melanoma. The ROC analysis showed that the measure is 82 % sensitive and 82 % specific in discriminating the malignant and benign lesions. These results compare favourably with other measures and indicate that HMM captures some distinguishing features in the boundary of malignant lesions. 1