Integrating Autoencoder-Based Hybrid Models into Cervical Carcinoma Prediction from Liquid-Based Cytology

Ferdaous Idlahcen, Ali Idri, Ali Idri, Hasnae Zerouaoui

2023

Abstract

Artificial intelligence (AI)-assisted cervical cytology is poised to enhance sensitivity whilst lessening bias, labor, and time expenses. It typically involves image processing and deep learning to automatically recognize pre-cancerous lesions on a given whole-slide image (WSI) prior to lethal invasive cancer development. Here, we introduce autoencoder (AE)-based hybrid models for cervical carcinoma prediction on the Mendeley-liquid-based cytology dataset. This is built on fourteen combinations of AE, DenseNet-201, and six state-of-the-art classifiers: adaptive boosting (AdaBoost), support vector machine (SVM), multilayer perceptron (MLP), decision tree (DT), k-nearest neighbors (k-NN), and random forest (RF). As empirical evaluations, four performance metrics, Scott-Knott (SK), and Borda count voting scheme, were performed. The AE-based hybrid models integrating AdaBoost, MLP, and RF as classifiers are among the top-ranked architectures, with respective accuracy values of 99.30, 99.20, and 98.48%. Yet, DenseNet-201 remains a solid option when adopting an end-to-end training strategy.

Paper Citation

in Harvard Style

Idlahcen F., Idri A. and Zerouaoui H. (2023). Integrating Autoencoder-Based Hybrid Models into Cervical Carcinoma Prediction from Liquid-Based Cytology. In Proceedings of the 12th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-664-4, SciTePress, pages 343-350. DOI: 10.5220/0012084600003541

in Bibtex Style

@conference{data23,
author={Ferdaous Idlahcen and Ali Idri and Hasnae Zerouaoui},
title={Integrating Autoencoder-Based Hybrid Models into Cervical Carcinoma Prediction from Liquid-Based Cytology},
booktitle={Proceedings of the 12th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2023},
pages={343-350},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012084600003541},
isbn={978-989-758-664-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - Integrating Autoencoder-Based Hybrid Models into Cervical Carcinoma Prediction from Liquid-Based Cytology
SN - 978-989-758-664-4
AU - Idlahcen F.
AU - Idri A.
AU - Zerouaoui H.
PY - 2023
SP - 343
EP - 350
DO - 10.5220/0012084600003541
PB - SciTePress