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.

Department(s)

Computer Science

Second Department

Chemistry

Third Department

Electrical and Computer Engineering

Keywords and Phrases

5 Y; United States; Artificial Neural Network Classification; Automated Cancer Detection; Benign Tumors; Color Images; Deadliest Skin Cancer Form; Discriminant Features; Malignant Melanoma; Medical Diagnostic Images; Medical Image Processing; Neural Network Diagnosis; Patient Diagnosis; Relative Tumor Color; Skin; Skin Tumor Images; Tumor Shape

International Standard Serial Number (ISSN)

0018-9294

Document Type

Article - Journal

Document Version

Final Version

File Type

text

Language(s)

English

Rights

© 1994 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.

Full Text Link

Share

 
COinS