Learning Algorithms for Cervical Cancer Detection

Marco Antonio Acevedo, María Elena Acevedo, Sandra Orantes

2022

Abstract

Cervical cancer begins in the cervix, the lower part of the uterus (womb) that opens into the upper part of the vagina. Worldwide, cervical cancer is the third most common type of cancer in women. This type of cancer can be detected visually with pap-smear images. A secondary alternative is to evaluate the relevant risk factors to see the possible formation of cervical cancer; these factors are recorded in a questionary. In this paper, the dataset from the questionary is analysed with two machine learning algorithms: K-NN and Multi-Layer Perceptron. We proposed the architectures and the parameters which achieve the best results. Two validation algorithms were applied: K-Fold Cross-Validation and Hold Out (80-20). The results from the machine learning algorithms were: 100% with 1-NN and Multi-Layer Perceptron together with K-Fold Cross-Validation and 97% with 1-NN and 98% when Multi-Layer Perceptron was applied, and the validation algorithm was Hold-Out.

Paper Citation

in Harvard Style

Antonio Acevedo M., Elena Acevedo M. and Orantes S. (2022). Learning Algorithms for Cervical Cancer Detection. In Proceedings of the 3rd International Symposium on Automation, Information and Computing - Volume 1: ISAIC; ISBN 978-989-758-622-4, SciTePress, pages 782-787. DOI: 10.5220/0012047400003612

in Bibtex Style

@conference{isaic22,
author={Marco Antonio Acevedo and María Elena Acevedo and Sandra Orantes},
title={Learning Algorithms for Cervical Cancer Detection},
booktitle={Proceedings of the 3rd International Symposium on Automation, Information and Computing - Volume 1: ISAIC},
year={2022},
pages={782-787},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012047400003612},
isbn={978-989-758-622-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 3rd International Symposium on Automation, Information and Computing - Volume 1: ISAIC
TI - Learning Algorithms for Cervical Cancer Detection
SN - 978-989-758-622-4
AU - Antonio Acevedo M.
AU - Elena Acevedo M.
AU - Orantes S.
PY - 2022
SP - 782
EP - 787
DO - 10.5220/0012047400003612
PB - SciTePress