Cervical Cancer Classification Using Elman Recurrent Neural Network and Genetic Algorithm

Medical screening using Pap smear images is a standard method for cervical cancer diagnosis. However, this method still has many weaknesses, such as time-consuming and subjectivity in interpreting an image. This paper aims to develop a method used as a cervical cancer classification using pap-smear images. Five classes were used, namely: normal, CIN1, CIN2, CIN3, and malignant. The method work as follows: (i) pre-processes image using amoeba median filter and Gaussian filter (ii) nuclei detection, and segmentation (iii) extracts characteristics image using texture and shape analysis (iv) classify the image using Elman Recurrent Neural Network and Genetic Algorithm. Based on experiments conducted, the proposed method could detect and classify pap smear images with sensitivity, specificity, and accuracy of 96%, 98%, and 95%, respectively.