Abstract—Cervical cancer is now the third most prevalent type of cancer in the universe. An early-stage detection may result into surgical procedure called hysterectomy. The majority of these cases are associated with the risk of infection from Human Papilloma Virus (HPV). Preventive measures, while the costliest approach to cancer prevention, can safeguard approximately 37% of cases. The Pap smear is a routine diagnostic tool used for the initial screening of cervical cancer. However, this manual procedure often results in a high number of false positives due to human error. Currently, data mining-based concept has gained huge attention in this domain of predictive analysis for disease detection where Machine Learning (ML) based models are widely adopted to predict the cervical cancer where supervised ML methods have played significant role. However, the performance of these models is affected for large dataset and computational complexity related issues also become more challenging. To address the issues of ML, researchers have introduced deep learning-based method to enhance the pattern learning capability of classification models to improve the overall accuracy. however, the black-box nature of these models can affect the system performance therefore combing two or multiple models can be beneficial to avoid this risk. In this work, we present a hybrid deep learning model where three Convolutional Neural Network (CNN) models are combined together and an averaging model is used to make the final decision related to prediction. Evaluated on a separate test set, the ensemble approach demonstrates improved diagnostic performance, achieving a higher accuracy compared to individual models. This study underscores the effectiveness of combining multiple CNNs in ensemble learning to advance the accuracy and reliability of cervical cancer detection, offering a promising tool for early diagnosis and improved patient outcomes. The experimental analysis shows that the average classification accuracy is obtained as 0.95, 0.91, 0.95, and 0.96 by using Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT), and proposed model, respectively.
 
Keywords—cervical cancer, Human Papilloma Virus (HPV), Convolutional Neural Network (CNN), ensemble approach, Random Forest (RF), Support Vector Machine (SVM), Decision Tree (DT)


Copyright © 2025 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).