Melanoma is the most deadly form of cancer which is easily curable if detected at the earlier stage. The main objective of this paper is to classify the Melanoma and Non-melanoma using dermoscopy images from the Med Node Dataset. The images are enhanced by bottomhat filter, and then segmentation is done by two methods 1. Morphological Operations, 2. Otsu Thresholding. The features extracted from the segmented lesions are ABCD features, Statistical features and is given to the classifier. The classification is done by Machine Learning Algorithms (FFNN, SVM, KNN). The performance is analysed by the sensitivity, specificity, accuracy, Positive predictive value, negative predictive value and manually by Total Dermatoscopy Score (TDS) for 9 different classification cases. The best among the cases is 96.7% accuracy is for FFNN algorithm.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 email@example.com
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 firstname.lastname@example.org