Review on Recent Hierarchical Learning Models For Automated Cervical Cancer Screening Using Pap Smear Cytology

It affects the cervix, which located at the bottom of the uterus and is connected to the vagina. Proper
detection and classification of the disease play an important role in improving survival rates.
Papanicolaou (Pap) and liquid Based Cytology (LBC) are the most commonly used methods. Advancements in technologies, especially hierarchical methods (Machine learning and deep learning) enhance the automation, efficiency, and a cervical cancer accuracy of cervical cancer (CC) testing. This
review introduces a detailed vision of the recent technology based on deep multi-level learning
architecture used for early finding and classification and discusses the lack of advancements in studies
to obtain an outline of future related work. The insights offered in this paper aim to contribute
knowledge to researchers and medical experts to make out the advancements in recent research and the
limitations they have faced while dealing with cervical cell cytology.