Optimized Fuzzy Min-Max Artificial Neural Network Got Cervical Cancer Application

Abstract

In this paper the application of a Fuzzy Min-Max Neural (FMM) network optimized by Genetic Algorithm (GA) for cervical cancer cells is proposed. The proposed system classifies cervical cells as normal, low-grade squamous intra-epithelial lesion (LSIL) and high-grade squamous intra-epithelial lesion (HSIL). The system consists of three stages. In the first stage, cervical cells are segmented using the Adaptive Fuzzy Moving K-means (AFMKM) clustering algorithm. In the second stage, feature extraction is performed where a total of 18 feature where extracted. Finally in the third stage the extracted features are fed to a FMM with GA Neural Network for classification. The obtained results show that the proposed system can enhance cancer cell classification. To further assess the obtained results the bootstrap hypothesis statistical technique is used to clarify the results.