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

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

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)


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 languageEnglish
Title of host publication2022 IEEE International Conference on Consumer Electronics - Taiwan
Number of pages2
ISBN (Electronic)9781665470506
Publication statusPublished - 1 Sept 2022
Event2022 IEEE International Conference on Consumer Electronics - Taiwan - Taipei, Taiwan, Province of China
Duration: 6 Jul 20228 Jul 2022


Conference2022 IEEE International Conference on Consumer Electronics - Taiwan
Abbreviated titleICCE-Taiwan 2022
Country/TerritoryTaiwan, Province of China


  • 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


Dive into the research topics of 'DECOVID-CT: Lightweight 3D CNN for COVID-19 Infection Prediction'. Together they form a unique fingerprint.

Cite this