Neural Network Diagnosis of Malignant Melanoma from Color Images

Fikret Erçal, Missouri University of Science and Technology
Hsi-Chieh Lee
William V. Stoecker, Missouri University of Science and Technology
Randy Hays Moss, Missouri University of Science and Technology
Anurag Chawla

This document has been relocated to http://scholarsmine.mst.edu/comsci_facwork/157/

There were 62 downloads as of 23 Jun 2016.

Abstract

Malignant melanoma is the deadliest form of all skin cancers. Approximately 32,000 new cases of malignant melanoma were diagnosed in 1991 in the United States, with approximately 80% of patients expected to survive 5 years. Fortunately, if detected early, even malignant melanoma may be treated successfully, Thus, in recent years, there has been rising interest in the automated detection and diagnosis of skin cancer, particularly malignant melanoma. Here, the authors present a novel neural network approach for the automated separation of melanoma from 3 benign categories of tumors which exhibit melanoma-like characteristics. The approach uses discriminant features, based on tumor shape and relative tumor color, that are supplied to an artificial neural network for classification of tumor images as malignant or benign. With this approach, for reasonably balanced training/testing sets, the authors are able to obtain above 80% correct classification of the malignant and benign tumors on real skin tumor images.