Back Propagation Neural Network (BPNN) based Melanoma Classification on Dermscopy Images

Abstract: Melanocytic tumors as Benign or Malignant can be diagnosed using different methods. One such method is a Digital Dermoscopic Image. Many conventional methods employ Support Vector Machines (SVMs), K- Nearest Neighbor (KNN), Adaboost, etc have been widely used for lesion classification. An Artificial Neural Network (ANN) is a computational model based on the structure and functions of biological neural networks. ANN can be used widely for medical diagnosis and tumor detection. There are various ANN that can be employed for this purpose. Our proposed method employs BPNN for melanoma classification on Dermoscopy images. We develop a novel method for classifying melanocytic tumors as Benign or Malignant by the analysis of digital dermoscopic images.

Keywords: Dermoscopy image, Benign, Malignant, BPNN (Back Propagation Neural Network)