A fuzzy ARTMAP-based classification system for detecting cancerous cells, based on the one-class problem approach

This work investigates the use of a fuzzy ARTMAP neural network for detecting cancerous cells, based on the one-class problem approach. This approach is inspired by the way human beings perform pattern recognition. We all know that children and adults alike are capable of detecting patterns belonging to a certain class, by learning the features of these patterns only. Moreover, a child or an adult is capable of detecting an unknown pattern belonging to another class without an a priori knowledge of the features in these patterns. Based on this approach, a fuzzy ARTMAPs-based system is developed for detecting cancerous cells by training the fuzzy ARTMAPs with the features belonging to the class of cancerous cells only. This is different from the two-class problem approach which requires that the classifier must be trained with features from the class of cancerous cells and the class of noncancerous cells. Experimental analysis were conducted using a set of 542 patterns taken from a sample of breast cancer. Training was performed with 383 cancerous cells. System performance was evaluated using 54 cancerous cells and 159 noncancerous cells. Evaluation results show 98% correct identification of cancerous cells and 95% correct identification of noncancerous cells