Hybrid Decision Fusion based Multimodal Ensemble Framework for Cervical Cancer Detection

Abstract

Cervical cancer is fourth in the list of cancers that affect women. It has remained the main cause of death for women in developing nations. The cancer is spread through human papilloma virus (HPV), which is sexually transmitted. Pap smear and colposcopy image analysis remain prominent methods of diagnosis. These screening tests require skilled diagnostic experts, a scarce resource in developing countries thus restricting the effectiveness of the cancer detection process in large scale. Machine learning and deep learning are branches of artificial intelligence that are being used increasingly in cancer diagnosis. This study proposes a novel hybrid intelligent system for cervical cancer detection. A hybrid model of feature extraction and feature fusion is proposed for merging the two-state image and clinical data. Subsequently a machine learning ensemble learner is assembled to classify the features. The model performed with a satisfactory accuracy of 96.16%. Our results show that our method outperforms state of the art approaches and archives better, dependable accuracy.