Abstract
Skin cancer, the most common cancer in the United States that affects about 600,000 Americans every year, accounts for 1% of all cancer deaths. Among all, Malignant Melanoma is the most virulent form of skin cancer that is responsible for 75% of all deaths from skin cancer. In 1992, approximately 32,000 people are expected to develop melanoma and about 6,700 will die. However, even malignant melanoma can be treated successfully if detected in the early phase. Therefore, our research goal is to diagnose skin cancer, especially malignant melanoma.
In this study, only the digitized images obtained from color tumor slides are used for the diagnosis. Image processing techniques, neural network system, and fuzzy inference system are combined here to diagnose skin cancer. The output yielded by the image processing techniques is served as the input to the proposed integrated systems. There are two integrated systems developed in this study. In system I, a rulebased pre-screener and a multi-layer perceptron with the backpropagation learning algorithm are combined for the diagnosis. In system II, a hierarchical diagnostic-tree based neural network system is developed which integrates a fuzzy inference system to improve the diagnostic accuracy. The results are also compared to those obtained by the dermatologists, which demonstrates the diagnostic capability of the proposed systems.
Recommended Citation
Lee, H. C. and Ercal, F., "Skin Cancer Diagnosis using Hierarchal Neural Networks and Fuzzy Logic" (1994). Computer Science Technical Reports. 161.
https://scholarsmine.mst.edu/comsci_techreports/161
Department(s)
Computer Science
Report Number
CSc-94-12
Document Type
Technical Report
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 1994 University of Missouri - Rolla, All rights reserved
Publication Date
1 May, 1994

Comments
The first Author is a Graduate Student.
This report is substantially the M.S. thesis of the first author, completed May, 1994