Early-Stage Cervical Cancer Detection via Ensemble Learning and Image Feature Integration

Cervical cancer ranks as the fourth most common malignancy worldwide and poses a significant threat, particularly in resource-constrained regions. Automated diagnostic approaches, leveraging colposcope image analysis, hold great promise in curbing the impact of this disease. In this study, we introduce an ensemble of machine learning and deep learning models, including DenseNet 121, ResNet 50, and XGBoost to classify the cervical intraepithelial neoplasia. A novel feature integration is proposed which ensembles the results of the individual models in five fold validation process. Our methodology is deployed on a dataset sourced from the International Agency for Cancer Research. The results from the proposed framework have shown to be accurate, robust and dependable. This method can be utilized for achieving automatic identification of cervical cancer in early stages so it can be treated appropriately.