Automatic Detection and Classification of Cervical Cancer in Pap Smear Images using ETCM & CFE methods based Texture features and Various Classification Techniques

Abstract: Classification of the cervical cell is one of the most important and crucial tasks in the medical image analysis. Due to its importance, the aim of the paper is to investigate about the classification of Cervical Cell as Normal Cell or Abnormal Cell by using individual feature extraction method and combining individual feature extraction features method with the classification technique. In this paper four Feature Extraction methods were used: from that four, two were existing individual feature extraction methods namely Gray Level Co-Occurrence Matrix (GLCM) & Texton Co-Occurrence Matrix (TCM) and the remained two were proposed novel methods. From that proposed two, one was individual feature extraction method, that is Enriched Texton Co-Occurrence Matrix (ETCM) and other was combining individual feature extraction features method, that is Concatenated Feature Extraction (CFE). The CFE method represents all the individual feature extraction methods of GLCM, TCM & ETCM features are combining together to one feature to assess their joint performance. Then, these four feature extraction methods are tested over three classifiers such as Support Vector Machine (SVM), Radial Basis Function (RBF) and Feed Forward Neural Network (FFNN). This Examination was conducted over a set of single cervical cell based pap smear images. The dataset contains two classes of images, with a total of 952 images. The distribution of number of images per class is not uniform. Then, the performance of the proposed system was evaluated in terms of the statistical parameters of sensitivity, specificity & accuracy in both the individual feature extraction method with the classification techniques and combining individual feature extraction methods with the classification techniques. Hence, the performance of individual combination method described, the proposed ETCM features with SVM Classifier combination had given the better results than the other combinations such as ETCM with RBF Classifier, ETCM with FFNN Classifier, GLCM with SVM Classifier, GLCM with RBF Classifier, GLCM with FFNN Classifier, TCM with SVM Classifier, TCM with RBF Classifier & TCM with FFNN Classifier. Then the performance of the combining individual feature extraction features method described, proposed Concatenated Feature Extraction (CFE) method with SVM Classifier had given the better results than all other remained CFE method with classifier combinations and all other individual feature extraction and classification combinations.