Open AccessCervical Cancer Classification Using Image Processing Approach: A Review
Author(s) -
Low Zhe Wei,
Wan Azani Mustafa,
Mohd Aminudin Jamlos,
Syed Zulkarnain Syed Idrus,
Mohd Hamzari Sahabudin
Publication year - 2020
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/917/1/012068
Subject(s) - cervical cancer , cervix , cancer , perspective (graphical) , balance (ability) , medicine , stage (stratigraphy) , computer science , contextual image classification , cervical cancer screening , artificial intelligence , pattern recognition (psychology) , image (mathematics) , biology , physical medicine and rehabilitation , paleontology
At present, Cervical cancer is the second most common cancer among women around the world. This cancer develops in the cervix; which is the entrance to the uterus. Most of the time, hospital doctors are facing difficulties in identifying cancer cells because the nucleus is sometimes rather difficult to see with the naked eye. Normal cells nuclei are smaller than abnormal cells nuclei. Abnormal nuclei are larger, which sometimes cannot be precisely identified by classifying stages of cervical cancer with the naked eye. This is because each doctor has a different perspective to monitor the classification of cancer stages by observing the nucleus without precisely reducing the size of the classification accuracy. Lately, many researchers have proposed methods for detection and classification of Pap smear images to diagnose cervical cancer. This approach can improve detection and classification accuracy, resulting in better results with accurate data balance and samples. Some patients are found to be in Stage 2 but after retesting they are actually in Stage 4, where the chances of recovery are very low. This is because doctors cannot find the right balance data and unable to take samples properly. This article discusses a comprehensive review of cervical recognition based on segment core and classification.