Automatic Detection of COVID-19 Using Ensemble Transfer Learning Based on Lung CT Scans

Ricardo Pillay; Serestina Viriri; Reolyn Heymann

doi:10.1007/978-3-031-25271-6_12

Automatic Detection of COVID-19 Using Ensemble Transfer Learning Based on Lung CT Scans

Ricardo Pillay
, Serestina Viriri
, Reolyn Heymann

Electrical and Electronic Engineering Science

University of KwaZulu-Natal
University of Johannesburg

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

In order to curb the rapid spread of COVID-19, early and accurate detection is required. Computer Tomography (CT) scans of the lungs can be utilized for accurate COVID-19 detection because these medical images highlight COVID-19 infection with high sensitivity. Transfer learning was implemented on six state-of-the-art Convolutional Neural Networks (CNNs). From these six CNNs, the three with the highest accuracies (based on empirical experiments) were selected and used as base learners to produce hard voting and soft voting ensemble classifiers. These three CNNs were identified as Vgg16, EfficientNetB0 and EfficientNetB5. This study concludes that the soft voting ensemble classifier, with base learners Vgg16 and EfficientNetB5, outperformed all other ensemble classifiers with different base learners and individual models that were investigated. The proposed classifier achieved a new state-of-the-art accuracy on the SARS-CoV-2 dataset. The accuracy obtained from this framework was 98.13%, the recall was 98.94%, the precision was 97.40%, the specificity was 97.30% and the F1 score was 98.16%.

Original language	English
Title of host publication	Pan-African Artificial Intelligence and Smart Systems - Second EAI International Conference, PAAISS 2022, Proceedings
Editors	Telex Magloire Ngatched Nkouatchah, Isaac Woungang, Jules-Raymond Tapamo, Serestina Viriri
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	181-204
Number of pages	24
ISBN (Print)	9783031252709
DOIs	https://doi.org/10.1007/978-3-031-25271-6_12
Publication status	Published - 2023
Event	2nd International Conference on Pan-African Intelligence and Smart Systems, PAAISS 2022 - Dakar, Senegal Duration: 2 Nov 2022 → 4 Nov 2022

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	459 LNICST
ISSN (Print)	1867-8211
ISSN (Electronic)	1867-822X

Conference

Conference	2nd International Conference on Pan-African Intelligence and Smart Systems, PAAISS 2022
Country/Territory	Senegal
City	Dakar
Period	2/11/22 → 4/11/22

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Convolutional neural network
Deep learning
Hard voting
Soft voting
Transfer learning

ASJC Scopus subject areas

Computer Networks and Communications

Access to Document

10.1007/978-3-031-25271-6_12

Cite this

Pillay, R., Viriri, S., & Heymann, R. (2023). Automatic Detection of COVID-19 Using Ensemble Transfer Learning Based on Lung CT Scans. In T. M. Ngatched Nkouatchah, I. Woungang, J.-R. Tapamo, & S. Viriri (Eds.), Pan-African Artificial Intelligence and Smart Systems - Second EAI International Conference, PAAISS 2022, Proceedings (pp. 181-204). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 459 LNICST). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-25271-6_12

Pillay, Ricardo ; Viriri, Serestina ; Heymann, Reolyn. / Automatic Detection of COVID-19 Using Ensemble Transfer Learning Based on Lung CT Scans. Pan-African Artificial Intelligence and Smart Systems - Second EAI International Conference, PAAISS 2022, Proceedings. editor / Telex Magloire Ngatched Nkouatchah ; Isaac Woungang ; Jules-Raymond Tapamo ; Serestina Viriri. Springer Science and Business Media Deutschland GmbH, 2023. pp. 181-204 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{276b53cdf73a49688374e603551fafef,

title = "Automatic Detection of COVID-19 Using Ensemble Transfer Learning Based on Lung CT Scans",

abstract = "In order to curb the rapid spread of COVID-19, early and accurate detection is required. Computer Tomography (CT) scans of the lungs can be utilized for accurate COVID-19 detection because these medical images highlight COVID-19 infection with high sensitivity. Transfer learning was implemented on six state-of-the-art Convolutional Neural Networks (CNNs). From these six CNNs, the three with the highest accuracies (based on empirical experiments) were selected and used as base learners to produce hard voting and soft voting ensemble classifiers. These three CNNs were identified as Vgg16, EfficientNetB0 and EfficientNetB5. This study concludes that the soft voting ensemble classifier, with base learners Vgg16 and EfficientNetB5, outperformed all other ensemble classifiers with different base learners and individual models that were investigated. The proposed classifier achieved a new state-of-the-art accuracy on the SARS-CoV-2 dataset. The accuracy obtained from this framework was 98.13\%, the recall was 98.94\%, the precision was 97.40\%, the specificity was 97.30\% and the F1 score was 98.16\%.",

keywords = "Convolutional neural network, Deep learning, Hard voting, Soft voting, Transfer learning",

author = "Ricardo Pillay and Serestina Viriri and Reolyn Heymann",

note = "Publisher Copyright: {\textcopyright} 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.; 2nd International Conference on Pan-African Intelligence and Smart Systems, PAAISS 2022 ; Conference date: 02-11-2022 Through 04-11-2022",

year = "2023",

doi = "10.1007/978-3-031-25271-6\_12",

language = "English",

isbn = "9783031252709",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "181--204",

editor = "\{Ngatched Nkouatchah\}, \{Telex Magloire\} and Isaac Woungang and Jules-Raymond Tapamo and Serestina Viriri",

booktitle = "Pan-African Artificial Intelligence and Smart Systems - Second EAI International Conference, PAAISS 2022, Proceedings",

address = "Germany",

}

Pillay, R, Viriri, S & Heymann, R 2023, Automatic Detection of COVID-19 Using Ensemble Transfer Learning Based on Lung CT Scans. in TM Ngatched Nkouatchah, I Woungang, J-R Tapamo & S Viriri (eds), Pan-African Artificial Intelligence and Smart Systems - Second EAI International Conference, PAAISS 2022, Proceedings. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 459 LNICST, Springer Science and Business Media Deutschland GmbH, pp. 181-204, 2nd International Conference on Pan-African Intelligence and Smart Systems, PAAISS 2022, Dakar, Senegal, 2/11/22. https://doi.org/10.1007/978-3-031-25271-6_12

Automatic Detection of COVID-19 Using Ensemble Transfer Learning Based on Lung CT Scans. / Pillay, Ricardo; Viriri, Serestina; Heymann, Reolyn.
Pan-African Artificial Intelligence and Smart Systems - Second EAI International Conference, PAAISS 2022, Proceedings. ed. / Telex Magloire Ngatched Nkouatchah; Isaac Woungang; Jules-Raymond Tapamo; Serestina Viriri. Springer Science and Business Media Deutschland GmbH, 2023. p. 181-204 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 459 LNICST).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Automatic Detection of COVID-19 Using Ensemble Transfer Learning Based on Lung CT Scans

AU - Pillay, Ricardo

AU - Viriri, Serestina

AU - Heymann, Reolyn

PY - 2023

Y1 - 2023

N2 - In order to curb the rapid spread of COVID-19, early and accurate detection is required. Computer Tomography (CT) scans of the lungs can be utilized for accurate COVID-19 detection because these medical images highlight COVID-19 infection with high sensitivity. Transfer learning was implemented on six state-of-the-art Convolutional Neural Networks (CNNs). From these six CNNs, the three with the highest accuracies (based on empirical experiments) were selected and used as base learners to produce hard voting and soft voting ensemble classifiers. These three CNNs were identified as Vgg16, EfficientNetB0 and EfficientNetB5. This study concludes that the soft voting ensemble classifier, with base learners Vgg16 and EfficientNetB5, outperformed all other ensemble classifiers with different base learners and individual models that were investigated. The proposed classifier achieved a new state-of-the-art accuracy on the SARS-CoV-2 dataset. The accuracy obtained from this framework was 98.13%, the recall was 98.94%, the precision was 97.40%, the specificity was 97.30% and the F1 score was 98.16%.

AB - In order to curb the rapid spread of COVID-19, early and accurate detection is required. Computer Tomography (CT) scans of the lungs can be utilized for accurate COVID-19 detection because these medical images highlight COVID-19 infection with high sensitivity. Transfer learning was implemented on six state-of-the-art Convolutional Neural Networks (CNNs). From these six CNNs, the three with the highest accuracies (based on empirical experiments) were selected and used as base learners to produce hard voting and soft voting ensemble classifiers. These three CNNs were identified as Vgg16, EfficientNetB0 and EfficientNetB5. This study concludes that the soft voting ensemble classifier, with base learners Vgg16 and EfficientNetB5, outperformed all other ensemble classifiers with different base learners and individual models that were investigated. The proposed classifier achieved a new state-of-the-art accuracy on the SARS-CoV-2 dataset. The accuracy obtained from this framework was 98.13%, the recall was 98.94%, the precision was 97.40%, the specificity was 97.30% and the F1 score was 98.16%.

KW - Convolutional neural network

KW - Deep learning

KW - Hard voting

KW - Soft voting

KW - Transfer learning

UR - https://www.scopus.com/pages/publications/85149656467

U2 - 10.1007/978-3-031-25271-6_12

DO - 10.1007/978-3-031-25271-6_12

M3 - Conference contribution

AN - SCOPUS:85149656467

SN - 9783031252709

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 181

EP - 204

BT - Pan-African Artificial Intelligence and Smart Systems - Second EAI International Conference, PAAISS 2022, Proceedings

A2 - Ngatched Nkouatchah, Telex Magloire

A2 - Woungang, Isaac

A2 - Tapamo, Jules-Raymond

A2 - Viriri, Serestina

PB - Springer Science and Business Media Deutschland GmbH

T2 - 2nd International Conference on Pan-African Intelligence and Smart Systems, PAAISS 2022

Y2 - 2 November 2022 through 4 November 2022

ER -

Pillay R, Viriri S, Heymann R. Automatic Detection of COVID-19 Using Ensemble Transfer Learning Based on Lung CT Scans. In Ngatched Nkouatchah TM, Woungang I, Tapamo JR, Viriri S, editors, Pan-African Artificial Intelligence and Smart Systems - Second EAI International Conference, PAAISS 2022, Proceedings. Springer Science and Business Media Deutschland GmbH. 2023. p. 181-204. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-031-25271-6_12