Diagnosis of COVID-19 Using Deep Learning and Data Augmentation from Chest CT-Scan Images
ISEF · 2021 Robotics and Intelligent Machines
Overview
Coronavirus disease 2019 (COVID-19) has infected more than 100 million individuals all over the world and caused more than 2.3 million deaths. There have been increasing efforts on developing deep learning methods to diagnose COVID-19 based on CT scans. In this work, the aim is to enhance the diagnosis accuracy by designing a new CNN classifier and adopting data augmentation to improve the training results. The proposed model is tested on a COVID 19-CT dataset that consists of 746 CT scan images. Results show that the proposed CNN model with data augmentation outperformed other pre-trained models such as DenseNet121, MobileNet, DenseNet169, and ResNet50. This model was able to achieve an accuracy of 94.2%, while the highest accuracy obtained by other pre-trained models is 83.4%. To simplify the use of this model and make it accessible, an online web-based tool has been developed that can provide the predicted diagnosis for any uploaded CT-scan image. This work has the potential to provide effective diagnosis tools that can help fight the spread of COVID-19.
Competition history
- ISEF 2021
Resources
Related projects
ISEF · 2022
COVision: A Novel Convolutional Neural Network for the Differentiation of COVID-19 From Common Pulmonary Conditions
ISEF · 2021
COVID-19 Chest X-ray Images: Lung Segmentation and Diagnosis Using Neural Networks
ISEF · 2022
COVID-19 Detection on Chest X-Ray Using an Enhanced Neural Network Model: Impact of Network Architecture Complexity, Data Augmentation, and Transfer Learning on Model
ISEF · 2023
CoVNet: A Deep Convolutional Neural Network Model for Improving COVID-19 Detection
Closest projects by meaning, across every fair and year in the corpus.
Source: Regeneron International Science and Engineering Fair