An Artificial Intelligence Approach for the Detection of Cervical Abnormalities: Application of the Self Organizing Map

An Artificial Intelligence Approach for the Detection of Cervical Abnormalities: Application of the Self Organizing Map

Evangelos Salamalekis (Department of Cytopathology, Evangelismos Hospital, Paphos, Greece), Abraham Pouliakis (2nd Department of Pathology, National and Kapodistrian University of Athens, Athens, Greece), Niki Margari (Private Cytopathology Laboratory, Marousi, Greece), Christine Kottaridi (2nd Department of Pathology, National and Kapodistrian University of Athens, School of Medicine, Athens, Greece), Aris Spathis (2nd Department of Pathology, National and Kapodistrian University of Athens, School of Medicine, Athens, Greece), Effrosyni Karakitsou (Department of Biology, University of Barcelona, Barcelona, Spain), Alina-Roxani Gouloumi (2nd Department of Pathology, National and Kapodistrian University of Athens, School of Medicine, Athens, Greece), Danai Leventakou (2nd Department of Pathology, National and Kapodistrian University of Athens, School of Medicine, Athens, Greece), George Chrelias (3rd Department of Obstetrics and Gynecology, National and Kapodistrian University of Athens, Athens, Greece), George Valasoulis (Department of Obstetrics and Gynaecology, Health Center of Larisa, Larisa, Greece), Maria Nasioutziki (Molecular Cytopathology Laboratory, 2nd Obstetrics and Gynecology Department, Aristotle University of Thessaloniki, Medical School, Thessaloniki, Greece), Maria Kyrgiou (Department of Surgery and Cancer, Imperial College London, London, UK), Konstantinos Dinas (2nd Obstetrics and Gynecology Department, Aristotle University of Thessaloniki, Medical School, Thessaloniki, Greece), Ioannis G. Panayiotides (2nd Department of Pathology, National and Kapodistrian University of Athens, School of Medicine, Athens, Greece), Evangelos Paraskevaidis (Department of Obstetrics and Gynecology, University Hospital of Ioannina, Ioannina, Greece) and Charalampos Chrelias (3rd Department of Obstetrics and Gynecology, National and Kapodistrian University of Athens, Athens, Greece)
Copyright: © 2019 |Pages: 21
DOI: 10.4018/IJRQEH.2019040102

Abstract

Numerous ancillary techniques detecting HPV DNA or mRNA are viewed as competitors or ancillary techniques to test Papanicolaou. However, no technique is perfect because sensitivity increases at the cost of specificity. Various methods have been applied to resolve this issue by using many examination results, such as classification and regression trees and supervised artificial neural networks. In this article, 1258 cases with results from test Pap, HPV DNA, HPV mRNA, and p16 were used to evaluate the performance of the self-organizing map (SOM). An artificial neural network has three advantages: it is unsupervised, can tolerate missing data, and produces topographical maps. The results of the SOM application were encouraging and produced maps depicting the important tests.
Article Preview

Introduction

Cervical cancer (CC) is the third most common cancer and the fourth leading cause of cancer death in females worldwide (Jemal et al., 2011). More than 85% of these cases and deaths are in developing countries; this is due to lack of screening that may allow detection of precancerous lesions (i.e. early stage cervical cancer). Despite the advances in screening, cervical cancer remains a serious problem of public health even in developed countries, due to the high percentage of detection failures (Leyden et al., 2005).

CC is known to be caused almost always by human papillomavirus (HPV) infection which is the commonest sexually transmitted infection worldwide. About 100 types of HPV virus that can infect humans have been identified. Among them, 15 are high risk oncogenic and can cause CC. Improved understanding of HPV infection and the natural history of cervical neoplasia have resulted in the addition of the HPV DNA test along with the Pap test and frequently as a competing test.

Nowadays, ancillary techniques for CC screening are available. These include HPV DNA typing and mRNA identification of the viral E6/E7 oncogenes that are linked to oncogenic activation. Among them mRNA typing with nucleic acid-based amplification (NASBA) (Smits et al., 1995) and mRNA-Flow-FISH techniques in screening programs produced promising results in increasing PPV and reducing unnecessary recalls and referrals to colposcopy (Coquillard, Palao, & Patterson, 2011; Kottaridi et al., 2011; Narimatsu & Patterson, 2005; Sorbye, Fismen, Gutteberg, & Mortensen, 2010; Trope et al., 2009). At the same time, it was reported that the immunocytochemical detection of p16 could increase the diagnostic accuracy of the Pap-test (Tsoumpou et al., 2009; Valasoulis et al., 2011).

Several published studies in the literature attempted to clarify the role of each technique as a unique test to substitute the Pap-test (Benevolo et al., 2011; Carozzi, 2007; Coquillard et al., 2011; Cuschieri & Wentzensen, 2008; Cuzick et al., 2008; Denton et al., 2010; Kottaridi et al., 2011; Mathew & George, 2009; Mayrand et al., 2007; Narimatsu & Patterson, 2005; Naucler et al., 2009; Smits et al., 1995; Sorbye et al., 2010; Trope et al., 2009; Tsoumpou et al., 2009; Valasoulis et al., 2011). Through the detailed analysis of these, it can be concluded that the performance measures of the methods under control differ significantly, affected by the disease incidence and the prevalence of HPV infection in the population study group; thus, application of a single method, even if it may appear to improve key performance indicators, does not determine the risk reliably for individual women to harbor cervical intraepithelial neoplasia (CIN). However, from published studies (Cuzick et al., 2008; Karakitsos et al., 2011; Mathew & George, 2009; Mayrand et al., 2007; Naucler et al., 2009; Spathis et al., 2012) is evident that the sensitivity of Pap-test combined with the HPV DNA test is higher than the sensitivity of each method.

Complete Article List

Search this Journal:
Reset
Open Access Articles
Volume 8: 4 Issues (2019): 2 Released, 2 Forthcoming
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2014)
Volume 2: 4 Issues (2013)
Volume 1: 4 Issues (2012)
View Complete Journal Contents Listing