Feature selection using Artificial Bee Colony algorithm for medical image classification

Feature Selection in medical image processing is a process of selection of relevant features, which are useful in model construction, as it will lead to reduced training times and classification model designed will be easier to interrupt. In this paper a meta-heuristic algorithm Artificial Bee Colony (ABC) has been used for feature selection in Computed Tomography (CT Scan) images of cervical cancer with the objective of detecting whether the data given as input is cancerous or not. Starting with segmentation as a first step, performed by implementing Active Contour Segmentation (ACM) algorithm over the images. In this paper a semi-automated the system has been developed so as to obtain the region of interest (ROI). Further, textural features proposed by Haralick are extracted region of interest. Classification is performed using hybridization of Artificial Bee Colony (ABC) and k- Nearest Neighbors (k-NN) algorithm, ABC and Support Vector Machine (SVM). It is observed that combination of ABC with SVM (Gaussian kernel) performs better than combination of ABC with SVM (Linear Kernel) and ABC with K-NN classifier.