Skin Cancer Diagnosis using Hierarchical Neural Networks and Fuzzy Systems


Skin cancers of all types comprise the largest group of cancers in the U.S. This group accounts for 1% of all cancer deaths. Fortunately, even the deadliest form of skin cancer can be treated successfully if detected in its early stage. In this study, we present a diagnostic-tree based hierarchical neural network system (HNN) which is integrated with a fuzzy system for the classification of four classes of skin tumors. These classes are: malignant melanoma, atypical mole, basal cell carcinoma or actinic keratosis, and intradermal nevus or seborrheic keratosis. The hierarchical neural network system is the integration of four distinct neural networks which are trained separately using the backpropagation learning algorithm. Results obtained through the HNN and fuzzy systems combined were significantly better than those produced by a straightforward neural network.

Meeting Name

Artificial Neural Networks in Engineering Conference (1994: Nov. 13-16, St. Louis, MO)


Computer Science

Second Department


Third Department

Electrical and Computer Engineering

Keywords and Phrases

Algorithms; Backpropagation; Computer Aided Diagnosis; Computer Simulation; Diseases; Fuzzy Sets; Hierarchical Systems; Image Processing; Learning Systems; Trees (Mathematics); Actinic Keratosis; Atypical Mole; Basal Cell Carcinoma; Fuzzy Systems; Hierarchical Neural Networks; Intradermal Nevus; Malignant Melanoma; Seborrhoic Keratosis; Skin Cancer Diagnosis; Skin Tumors; Neural Networks

International Standard Book Number (ISBN)


Document Type

Article - Conference proceedings

Document Version


File Type





© 1994 American Society of Mechanical Engineers (ASME), All rights reserved.

Publication Date

01 Nov 1994

This document is currently not available here.