3D CNN Model for the Diagnosis of COVID-19 by Classification of Chest CT Scans

• Author(s): T. Gnana Jyothi ; R. Uma Dhathri ; Sk. Dilshadbe ; M. Sree Valli
• Paper ID: 1702820
• Page: 92-96
• Published Date: 08-07-2021
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 5 Issue 1 July-2021

Abstract

This paper will discuss the steps that are needed to build a 3D convolutional neural network (CNN) to predict the presence of viral pneumonia in Computer Tomography (CT) scans. 2D CNNs are commonly used to process RGB images (which have 3 channels). A 3D CNN is simply the 3D equivalent of 2D CNN. It takes a 3D volume or a sequence of 2D frames (e.g., slices in a CT scan) as input. To implement this project, we use a subset of the MosMedData: Chest CT Scans with COVID-19 Related Findings, which consists of CT scans of the lungs with COVID-19 related findings and without such findings. We will be using the associated radiological findings of the CT scans as labels to build a classifier to predict the presence of viral pneumonia. Hence, the task is a binary classification problem.

Keywords

Convolutional Neural Network (CNN), COVID-19, CT scan, Viral Pneumonia.

Citations

IRE Journals:
T. Gnana Jyothi , R. Uma Dhathri , Sk. Dilshadbe , M. Sree Valli "3D CNN Model for the Diagnosis of COVID-19 by Classification of Chest CT Scans" Iconic Research And Engineering Journals Volume 5 Issue 1 2021 Page 92-96

IEEE:
T. Gnana Jyothi , R. Uma Dhathri , Sk. Dilshadbe , M. Sree Valli "3D CNN Model for the Diagnosis of COVID-19 by Classification of Chest CT Scans" Iconic Research And Engineering Journals, 5(1)