DCNNV-19: A Deep Convolutional Neural Network for COVID-19 Detection in Chest Computed Tomographies

TL;DR

This paper introduces DCNNV-19, a deep convolutional neural network that accurately detects COVID-19 from chest CT images, offering a faster alternative to RT-PCR with high precision and reliability.

Contribution

The paper presents a novel deep learning model trained on a large dataset of CT images for rapid COVID-19 detection, outperforming existing diagnostic methods in speed and accuracy.

Findings

Achieved 98% F1-Score in COVID-19 detection

High accuracy with 98.4% in overall correctness

Model provides faster results than RT-PCR

Abstract

This technical report proposes the use of a deep convolutional neural network as a preliminary diagnostic method in the analysis of chest computed tomography images from patients with symptoms of Severe Acute Respiratory Syndrome (SARS) and suspected COVID-19 disease, especially on occasions when the delay of the RT-PCR result and the absence of urgent care could result in serious temporary, long-term, or permanent health damage. The model was trained on 83,391 images, validated on 15,297, and tested on 22,185 figures, achieving an F1-Score of 98%, 97.59% in Cohen's Kappa, 98.4% in Accuracy, and 5.09% in Loss. Attesting a highly accurate automated classification and providing results in less time than the current gold-standard exam, Real-Time reverse-transcriptase Polymerase Chain Reaction (RT-PCR).