We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
A Neural Network Designed for COVID-19 Detection Using CT Images.
- Authors
ROUINI, Abdelghani; LARBI, Messaouda; BAKRIA, Derradji; KORICH, Belkacem
- Abstract
To quickly identify COVID-19 and stop its spread, Computer Tomography (CT) imaging of the chest is a reliable diagnostic method. In this work we implement a deep neural network based on Convolutional Neural Network (CNN), to effectively distinguish between healthy CT images and COVID-19 CT images. The final architecture allows for 91.6% accuracy, which is a 2% improvement over the first one. The result obtained can be very useful in medical diagnostics, particularly in the Covid-19 case. The implemented CNN model takes 2-3 seconds to run on a medium-end laptop without GPU acceleration.
- Subjects
CONVOLUTIONAL neural networks; ARTIFICIAL neural networks; COMPUTED tomography; COVID-19; COVID-19 pandemic; PHYSIOLOGICAL effects of acceleration
- Publication
Przeglad Elektrotechniczny, 2024, Vol 2024, Issue 4, p152
- ISSN
0033-2097
- Publication type
Article
- DOI
10.15199/48.2024.04.29