An Investigation of Deep-Learned Features for Classifying Radiographic Images of COVID-19

Pedro Miguel, Adriano Cansian, Guilherme Rozendo, Giuliano Medalha, Marcelo Zanchetta do Nascimento, Leandro Neves

2023

Abstract

In this proposal, a study based on deep-learned features via transfer learning was developed to obtain a set of features and techniques for pattern recognition in the context of COVID-19 images. The proposal was based on the ResNet-50, DenseNet-201 and EfficientNet-b0 deep-learning models. In this work, the chosen layer for analysis was the avg pool layer from each model, with 2048 features from the ResNet-50, 1920 features from the DenseNet0201 and 1280 obtained features from the EfficientNet-b0. The most relevant descriptors were defined for the classification process, applying the ReliefF algorithm and two classification strategies: individually applied classifiers and employed an ensemble of classifiers using the score-level fusion approach. Thus, the two best combinations were identified, both using the DenseNet-201 model with the same subset of features. The first combination was defined via the SMO classifier (accuracy of 98.38%) and the second via the ensemble strategy (accuracy of 97.89%). The feature subset was composed of only 210 descriptors, representing only 10% of the original set. The strategies and information presented here are relevant contributions for the specialists interested in the study and development of computer-aided diagnosis in COVID-19 images.

Paper Citation

in Harvard Style

Miguel P., Cansian A., Rozendo G., Medalha G., Zanchetta do Nascimento M. and Neves L. (2023). An Investigation of Deep-Learned Features for Classifying Radiographic Images of COVID-19. In Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-758-648-4, SciTePress, pages 675-682. DOI: 10.5220/0012038500003467

in Bibtex Style

@conference{iceis23,
author={Pedro Miguel and Adriano Cansian and Guilherme Rozendo and Giuliano Medalha and Marcelo Zanchetta do Nascimento and Leandro Neves},
title={An Investigation of Deep-Learned Features for Classifying Radiographic Images of COVID-19},
booktitle={Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2023},
pages={675-682},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012038500003467},
isbn={978-989-758-648-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 25th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - An Investigation of Deep-Learned Features for Classifying Radiographic Images of COVID-19
SN - 978-989-758-648-4
AU - Miguel P.
AU - Cansian A.
AU - Rozendo G.
AU - Medalha G.
AU - Zanchetta do Nascimento M.
AU - Neves L.
PY - 2023
SP - 675
EP - 682
DO - 10.5220/0012038500003467
PB - SciTePress