Monitoring system to classify cervical cancer stages based on pap smear nucleus analysis

Nowadays, in the hospital, cervical cancer is in the higher rank (number two) of the most popular cancer among ladies in the world. This type of cancer develops in the woman's cervix, which the womb is the entrance. The nucleus of the normal cell is in a smaller size compared to the abnormal nucleus. The abnormal nucleus has a bigger size, which sometimes, the size cannot be identified accurately by seeing with bare eyes to classify the stages of cervical cancer. As the solution, to detect and classifying the cells using methods through Pap smear images technique for handling the paper objectives with the better performance required. This method may improve the accuracy of the detection and the classification which to show better performance with the balance data and samples. Based on all of the results classified, the five methods were compared such as Wolf method, Nick method, Niblack method, Bradley method, and Bernsen method has been determined. Then, the Bradley method showed the best result of the cervical cancer threshold which has been chosen in this project. Furthermore, method modification has been made as to the new method of detection for the nucleus successfully proposed as stated in the project objective. After that, the analysis of the specificity, accuracy, PSNR, sensitivity, and F-Measure determined. All of the results of data analysis showed that the proposed method has a high percentage of the accuracy in total average, in which the project system performance of nucleus detection is good. Nevertheless, the analysis of the nucleus feature in terms of size by obtaining the area and the perimeter of the foreground (nucleus) made as the classification of cells were classed into three classes has been successfully made as to the second project objective. The three classes of cells finally success to identify, those are the ‘Abnormal Cell’, ‘Intermediate Cell’, and ‘Normal Cell’. This study could perhaps encourage researchers throughout the field in seeing the researched risk associated with some of the methods and to provide a solid base for design and implementing new algorithms or implementing new ones.