•  
  •  
 

Corresponding Author

Ahmed H. Eltanboly

Subject Area

Biomedical Engineering

Article Type

Original Study

Abstract

In third-world countries, cervical cancer is the most prevalent and leading cause of death. It is affected by a variety of factors, including smoking, poor nutritional status, immunological inadequacy, and prolonged use of contraception. The Pap smear test, which is intended to prevent cervical cancer, finds preneoplastic changes in cervical epithelial cells. This study framework classified cervical cancer cells from Pap smears into five specified cell types using machine learning-based classification algorithms. The SIPaKMeD database is used in this investigation. This public dataset, which was manually cropped from 966 cluster cell images taken from Pap smear slides, has 4045 isolated Pap smear cells. Depending on their cellular form and structure, experts categorize the cells into five distinct types which are superficial-intermediate, Parabasal, Koilocytotic, Dyskeratotic, and Metaplastic cells. Introducing a pipeline to improve algorithm accuracy and easy implementation by using a specified feature extractor and conducting a suitable preprocessing pipeline is the main contribution. The study reached the conclusion that machine learning could improve Pap smear screening classification results. We concluded that the support vector machine (SVM) is the most suitable algorithm for this application. The SVM has the highest accuracy of 0.968, the Neural Network (NN) at 0.958, and the (K-Nearest Neighbor) KNN at 0.941. These results support the proposed framework as a reliable classification diagnostic tool.

Keywords

Pap smear (PS); Feature Engineering; Principal Component Analysis (PCA); Neural Network; Deep Features

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Download

Share

COinS