CxSE: Chest X-ray Slow Encoding CNN forCOVID-19 Diagnosis

TL;DR

This paper introduces CxSE, a novel slow encoding CNN architecture designed for rapid and accurate COVID-19 diagnosis from chest X-ray images, demonstrating high sensitivity and predictive values.

Contribution

The paper presents a new CNN architecture specifically tailored for COVID-19 detection in X-ray images, achieving notable performance improvements.

Findings

Sensitivity of 0.96 for COVID-19 positive detection

Positive Predictive Value of 0.98

High sensitivity and specificity on test data

Abstract

The coronavirus continues to disrupt our everyday lives as it spreads at an exponential rate. It needs to be detected quickly in order to quarantine positive patients so as to avoid further spread. This work proposes a new convolutional neural network (CNN) architecture called 'slow Encoding CNN. The proposed model's best performance wrt Sensitivity, Positive Predictive Value (PPV) found to be SP=0.67, PP=0.98, SN=0.96, and PN=0.52 on AI AGAINST COVID19 - Screening X-ray images for COVID-19 Infections competition's test data samples. SP and PP stand for the Sensitivity and PPV of the COVID-19 positive class, while PN and SN stand for the Sensitivity and PPV of the COVID-19 negative class.