Evaluation of three neural network models using Wisconsin breast cancer database
Khalid Mumtaz, Sulaiman Sheriff, K. Duraiswamy · International Conference on Control and Automation · 2009
A major class of problems in medical science involves the diagnosis of a disease based upon various tests performed upon the patient. Cancer is a complex and clinical heterogeneous disease. The research into the diagnosis and treatment of cancer has become an important issue for the scientific community. The objective of cancer classification is to design a classifier to categorize the tissue samples into pre-defined classes (e.g. tumor and normal) using the gene expression levels produced by micro array techniques. The automatic diagnosis of breast cancer is an important, real-world medical problem. This paper evaluates the three neural network models namely 1. Adaptive Resonance Theory Based Neural Network (ART), 2. Self Organizing Map Based Neural Network (SOM) and 3.Back Propagation Neural network (BPN) using the Wisconsin breast cancer database.