Convolutional Neural Network-Based Automatic Analysis of Chest Radiographs for the Detection of COVID-19 Pneumonia: A Prioritizing Tool in the Emergency Department, Phase I Study and Preliminary "Real Life" Results.

Davide Tricarico,Massimiliano Melis,Clara Piatti,Domenico Basile,Marco Gatti,Andrea Veltri,Marco Calandri,Matteo Barba,Carlotta Geninatti

doi:10.3390/diagnostics12030570

Davide Tricarico, Massimiliano Melis + Show 7 more

Open Access

https://doi.org/10.3390/diagnostics12030570

Copy DOI

Abstract

The aim of our study is the development of an automatic tool for the prioritization of COVID-19 diagnostic workflow in the emergency department by analyzing chest X-rays (CXRs). The Convolutional Neural Network (CNN)-based method we propose has been tested retrospectively on a single-center set of 542 CXRs evaluated by experienced radiologists. The SARS-CoV-2 positive dataset (n = 234) consists of CXRs collected between March and April 2020, with the COVID-19 infection being confirmed by an RT-PCR test within 24 h. The SARS-CoV-2 negative dataset (n = 308) includes CXRs from 2019, therefore prior to the pandemic. For each image, the CNN computes COVID-19 risk indicators, identifying COVID-19 cases and prioritizing the urgent ones. After installing the software into the hospital RIS, a preliminary comparison between local daily COVID-19 cases and predicted risk indicators for 2918 CXRs in the same period was performed. Significant improvements were obtained for both prioritization and identification using the proposed method. Mean Average Precision (MAP) increased (p < 1.21 × 10−21 from 43.79% with random sorting to 71.75% with our method. CNN sensitivity was 78.23%, higher than radiologists’ 61.1%; specificity was 64.20%. In the real-life setting, this method had a correlation of 0.873. The proposed CNN-based system effectively prioritizes CXRs according to COVID-19 risk in an experimental setting; preliminary real-life results revealed high concordance with local pandemic incidence.

Highlights

In 2020, the whole world was turned upside down by the COVID-19 pandemic
The aim of our study is the development of an automatic tool for the prioritization of COVID-19 diagnostic workflow in the emergency department by analyzing chest X-rays (CXRs)
The Convolutional Neural Network (CNN)-based method we propose has been tested retrospectively on a single-center set of 542 CXRs evaluated by experienced radiologists

Summary

Introduction

In 2020, the whole world was turned upside down by the COVID-19 pandemic. Italy was one of the first Western countries to be heavily affected and up to now, June 2021, more than 4,000,000 cases have been recorded, with more than 125,000 deaths [1].A key factor for the healthcare system response to the COVID-19 pandemic is the application of a correct diagnostic work up and triage of COVID-19 suspected cases. The RT-PCR test is the gold standard diagnostic tool for the identification of SARS-CoV-2 It has a high specificity, but a relatively low sensitivity (54–73%) [2]; results can take hours to come out, creating logistic issues in the emergency departments [3]. Chest X-rays (CXRs) are used during triage due to the large availability of portable units, that are easy to use and fast to clean. This approach has been endorsed by the main radiological societies worldwide since the beginning of the pandemic [5,6]. Preliminary data suggest that CXRs may not be sufficiently sensitive for the detection of COVID-19 lung disease, reducing the potential clinical and diagnostic impact of this exam [7]

Objectives

Methods

Findings

Discussion

Conclusion