Diagnosing Malignant Melanoma using a Neural Network

Abstract

In recent years, there has been a rising interest in the early detection of skin cancer, particularly malignant melanoma, via automated screening and diagnosis process. In this paper, we present a novel neural network approach for the automated distinction of melanoma from three other benign categories of tumors which exhibit melanoma-like characteristics. Our approach is based on devising new and discriminant features which are used as inputs to an artificial neural network for classification of tumor images as malignant or benign. We have obtained promising results using our method on real skin cancer images.

Meeting Name

Artificial Neural Networks in Engineering (1992: Nov. 15-18, St. Louis, MO)

Department(s)

Computer Science

Second Department

Chemistry

Third Department

Electrical and Computer Engineering

Keywords and Phrases

Diagnosis; Image Analysis; Medical Imaging; Oncology; Tumor Image Diagnosis; Neural Networks

International Standard Book Number (ISBN)

791800296

Document Type

Article - Conference proceedings

Document Version

Citation

File Type

text

Language(s)

English

Rights

© 1992 American Society of Mechanical Engineers (ASME), All rights reserved.

Publication Date

01 Nov 1992

This document is currently not available here.

Share

 
COinS