Image Registration based Cervical Cancer Detection and Segmentation Using ANFIS Classifier

Abstract

Cervical cancer is the leading cancer in women around the world. In this paper, Adaptive Neuro Fuzzy Inference<br />System (ANFIS) classifier based cervical cancer detection and segmentation methodology is proposed. This proposed<br />system consists of the following stages as Image Registration, Feature extraction, Classifications and Segmentation.<br />Fast Fourier Transform (FFT) is used for image registration. Then, Grey Level Co-occurrence Matrix (GLCM), Grey<br />level and trinary features are extracted from the registered cervical image. Next, these extracted features are trained<br />and classified using ANFIS classifier. Morphological operations are now applied over the classified cervical image<br />to detect and segment the cancer region in cervical images. Simulations on large cervical image dataset demonstrate<br />that the proposed cervical cancer detection and segmentation methodology outperforms the state of-the-art methods in<br />terms of sensitivity, specificity and accuracy.