Abstract— Cervical cancerbeen known to be the cause of many deaths each year. Screening tests, such asthe Pap smear test used for the detection of the precancerous stage are able toavoid the occurrence of cervical cancer. However, the Pap smear test does havesome disappointing disadvantages such as the fact that it has less effectiveslide preparation and also that it is laden with human error. Therefore, acomputer-aided diagnosis system is introduced as a solution to the problem.Recently, artificial neural networks have been widely implemented as a cervicalcancer diagnosis system i.e. to classify cervical cancer into normal andabnormal cells. In this recent study, neural network architecture i.e. theHybrid Radial Basis Function (HRBF) network with Adaptive Fuzzy K-MeansClustering (AFKM) as a centre positioning algorithm is used to diagnosecervical cancer. Four extracted features of cervical cell are used as inputdata to the networks, which are the size of nucleus and cytoplasm and its greylevel. Cells from normal, Low-grade Squamous Intraepithelial Lesion (LSIL) andHigh-grade Squamous Intraepithelial Lesion (HSIL) categories are used as thetraining as well as the testing data. The data are fed randomly into the neuralnetworks via 5-folds cross validation techniques. The network performance iscompared with the HRBF network with the Moving K-Means algorithm as the centrepositioning algorithm. The proposed network produces better accuracy,sensitivity and specificity which illustrate the promising capability of thenetwork to be implemented as cervical cancer diagnosis system for Pap testperformance improvement.
Keywords: Cervical Cancer; Diagnosis System; ClusteringAlgorithm; NeuralPap.