DECOVID-CT: Lightweight 3D CNN for COVID-19 Infection Prediction

Kannan Rithesh; Lai-Kuan Wong; John See; Wai-Yee Chan; Kwan-Hong Ng

doi:10.1109/ICCE-Taiwan55306.2022.9869238

DECOVID-CT: Lightweight 3D CNN for COVID-19 Infection Prediction

Kannan Rithesh, Lai-Kuan Wong, John See, Wai-Yee Chan, Kwan-Hong Ng

School of Mathematical & Computer Sciences

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

1 Citation (Scopus)

Abstract

The COVID-19 pandemic has become a critical threat to global health and the economy since its first outbreak in 2019. The standard diagnosis for COVID-19, Reverse Transcription Polymerase Chain Reaction (RT-PCR) is time consuming, and has lower sensitivity compared to CT-scans. Therefore, CT-scans can be used as a complementary method, alongside RT-PCR tests for COVID-19 infection prediction. However, manually reviewing CT scans is time consuming. In this paper, we propose DECOVID-CT, a deep learning model based on 3D convolutional neural network (CNN) for the detection of COVID-19 infection with CT images. The model is trained and tested on the RICORD dataset, a multinational dataset, for higher robustness. Our model achieved an accuracy of 100%, for predicting COVID-19 positive images.

Original language	English
Title of host publication	2022 IEEE International Conference on Consumer Electronics - Taiwan
Publisher	IEEE
Pages	363-364
Number of pages	2
ISBN (Electronic)	9781665470506
DOIs	https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869238
Publication status	Published - 1 Sept 2022
Event	2022 IEEE International Conference on Consumer Electronics - Taiwan - Taipei, Taiwan, Province of China Duration: 6 Jul 2022 → 8 Jul 2022

Conference

Conference	2022 IEEE International Conference on Consumer Electronics - Taiwan
Abbreviated title	ICCE-Taiwan 2022
Country/Territory	Taiwan, Province of China
City	Taipei
Period	6/07/22 → 8/07/22

Keywords

3D CNN
AI COVID-19 imaging
Computed tomography
COVID-19 classification
lightweight model

ASJC Scopus subject areas

Artificial Intelligence
Computer Science Applications
Hardware and Architecture
Renewable Energy, Sustainability and the Environment
Electrical and Electronic Engineering
Media Technology
Health Informatics
Instrumentation

UN SDGs

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

Access to Document

10.1109/ICCE-Taiwan55306.2022.9869238

Cite this

@inproceedings{c7442d5f458640f89b90b39a3efd9b6b,

title = "DECOVID-CT: Lightweight 3D CNN for COVID-19 Infection Prediction",

abstract = "The COVID-19 pandemic has become a critical threat to global health and the economy since its first outbreak in 2019. The standard diagnosis for COVID-19, Reverse Transcription Polymerase Chain Reaction (RT-PCR) is time consuming, and has lower sensitivity compared to CT-scans. Therefore, CT-scans can be used as a complementary method, alongside RT-PCR tests for COVID-19 infection prediction. However, manually reviewing CT scans is time consuming. In this paper, we propose DECOVID-CT, a deep learning model based on 3D convolutional neural network (CNN) for the detection of COVID-19 infection with CT images. The model is trained and tested on the RICORD dataset, a multinational dataset, for higher robustness. Our model achieved an accuracy of 100%, for predicting COVID-19 positive images.",

keywords = "3D CNN, AI COVID-19 imaging, Computed tomography, COVID-19 classification, lightweight model",

author = "Kannan Rithesh and Lai-Kuan Wong and John See and Wai-Yee Chan and Kwan-Hong Ng",

note = "Publisher Copyright: {\textcopyright} 2022 IEEE.; 2022 IEEE International Conference on Consumer Electronics - Taiwan, ICCE-Taiwan 2022 ; Conference date: 06-07-2022 Through 08-07-2022",

year = "2022",

month = sep,

day = "1",

doi = "10.1109/ICCE-Taiwan55306.2022.9869238",

language = "English",

pages = "363--364",

booktitle = "2022 IEEE International Conference on Consumer Electronics - Taiwan",

publisher = "IEEE",

address = "United States",

}

Rithesh, K, Wong, L-K, See, J, Chan, W-Y & Ng, K-H 2022, DECOVID-CT: Lightweight 3D CNN for COVID-19 Infection Prediction. in 2022 IEEE International Conference on Consumer Electronics - Taiwan. IEEE, pp. 363-364, 2022 IEEE International Conference on Consumer Electronics - Taiwan, Taipei, Taiwan, Province of China, 6/07/22. https://doi.org/10.1109/ICCE-Taiwan55306.2022.9869238

TY - GEN

T1 - DECOVID-CT

T2 - 2022 IEEE International Conference on Consumer Electronics - Taiwan

AU - Rithesh, Kannan

AU - Wong, Lai-Kuan

AU - See, John

AU - Chan, Wai-Yee

AU - Ng, Kwan-Hong

PY - 2022/9/1

Y1 - 2022/9/1

N2 - The COVID-19 pandemic has become a critical threat to global health and the economy since its first outbreak in 2019. The standard diagnosis for COVID-19, Reverse Transcription Polymerase Chain Reaction (RT-PCR) is time consuming, and has lower sensitivity compared to CT-scans. Therefore, CT-scans can be used as a complementary method, alongside RT-PCR tests for COVID-19 infection prediction. However, manually reviewing CT scans is time consuming. In this paper, we propose DECOVID-CT, a deep learning model based on 3D convolutional neural network (CNN) for the detection of COVID-19 infection with CT images. The model is trained and tested on the RICORD dataset, a multinational dataset, for higher robustness. Our model achieved an accuracy of 100%, for predicting COVID-19 positive images.

AB - The COVID-19 pandemic has become a critical threat to global health and the economy since its first outbreak in 2019. The standard diagnosis for COVID-19, Reverse Transcription Polymerase Chain Reaction (RT-PCR) is time consuming, and has lower sensitivity compared to CT-scans. Therefore, CT-scans can be used as a complementary method, alongside RT-PCR tests for COVID-19 infection prediction. However, manually reviewing CT scans is time consuming. In this paper, we propose DECOVID-CT, a deep learning model based on 3D convolutional neural network (CNN) for the detection of COVID-19 infection with CT images. The model is trained and tested on the RICORD dataset, a multinational dataset, for higher robustness. Our model achieved an accuracy of 100%, for predicting COVID-19 positive images.

KW - 3D CNN

KW - AI COVID-19 imaging

KW - Computed tomography

KW - COVID-19 classification

KW - lightweight model

UR - http://www.scopus.com/inward/record.url?scp=85138681710&partnerID=8YFLogxK

U2 - 10.1109/ICCE-Taiwan55306.2022.9869238

DO - 10.1109/ICCE-Taiwan55306.2022.9869238

M3 - Conference contribution

AN - SCOPUS:85138681710

SP - 363

EP - 364

BT - 2022 IEEE International Conference on Consumer Electronics - Taiwan

PB - IEEE

Y2 - 6 July 2022 through 8 July 2022

ER -

DECOVID-CT: Lightweight 3D CNN for COVID-19 Infection Prediction

Abstract

Conference

Keywords

ASJC Scopus subject areas

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this