Abstract
Abstract
Early cancer detection is critical in enhancing a patient’s clinical results. Cervical cancer detection from a large number of whole slide images generated regularly in a clinical setting is a complex and time-consuming task. As a result, we require an efficient and accurate model for early cancer diagnosis, especially cervical cancer as it can be fully prevented if detected in an early stage. This study focuses on in-depth writing on current methodologies for cervical cancer segmentation and characterization from the whole cervical slide. It combines the state of their specialty’s performance measurement with the quantitative evaluation of cutting-edge techniques. Numerous publications over the last eleven years (2011-2022) clearly outline various cervical imaging methods over multiple blocks. And this review shows different types of algorithms used in each processing stage of detection. The study clearly indicates the advancements in the automation field and the necessity of the same.
Subject
Computer Science Applications,History,Education
Reference47 articles.
1. A fully-automated deep learning pipeline for cervical cancer classification;Alyafeai;Expert Systems with Applications,2020
2. Survival outcome prediction in cervical cancer: Cox models vs deep-learning model;Matsuo;American journal of obstetrics and gynecology,2019
3. Supervised deep learning embeddings for the prediction of cervical cancer diagnosis;Fernandes;Peer J Computer Science,2018
4. Comparison of machine and deep learning for the classification of cervical cancer based on cervicography images;Park;Scientific Reports,2021