Automated processing of thermal imaging to detect COVID-19

Rafael Y Brzezinski,Neta Rabin,Ori Rogowski,Liran Shechtman,Nili Naftali‐Shani ,Ehud Grossman,Ilan Ben-Zvi,Ariel Kerpel,Shani Shenhar‐Tsarfaty ,Omer Gendelman,Eyal Heller,Jonathan Leor,Irina Gringauz,Haim Mayan,Edith M Marom,Avinoah Ironi,Yair Zimmer,Avishai M Tsur ,Avshalom Leibowitz,Galia Rahav,Eli Konen,Zehava Ovadia‐Blechman ,Nir Lewis,Howard Amital,Racheli Peled,Oshrit Hoffer

doi:10.1038/s41598-021-96900-9

Abstract

Rapid and sensitive screening tools for SARS-CoV-2 infection are essential to limit the spread of COVID-19 and to properly allocate national resources. Here, we developed a new point-of-care, non-contact thermal imaging tool to detect COVID-19, based on advanced image processing algorithms. We captured thermal images of the backs of individuals with and without COVID-19 using a portable thermal camera that connects directly to smartphones. Our novel image processing algorithms automatically extracted multiple texture and shape features of the thermal images and achieved an area under the curve (AUC) of 0.85 in COVID-19 detection with up to 92% sensitivity. Thermal imaging scores were inversely correlated with clinical variables associated with COVID-19 disease progression. In summary, we show, for the first time, that a hand-held thermal imaging device can be used to detect COVID-19. Non-invasive thermal imaging could be used to screen for COVID-19 in out-of-hospital settings, especially in low-income regions with limited imaging resources.

Highlights

Rapid and sensitive screening tools for SARS-CoV-2 infection are essential to limit the spread of COVID-19 and to properly allocate national resources
We propose that advanced processing of thermal images, combined with machine learning analysis, could serve as an innovative diagnostic tool for detection of COVID-19 and its associated microvascular injury
The receiver operating characteristic (ROC) curves (Fig. 3) indicated that both fractal d imension27 (FD) and sum of extrema" (SX) scores were significantly associated with the diagnosis of COVID-19, with an area under the curve (AUC) of 0.85 and 0.82 respectively

Summary

Introduction

Rapid and sensitive screening tools for SARS-CoV-2 infection are essential to limit the spread of COVID-19 and to properly allocate national resources. We developed a new point-of-care, noncontact thermal imaging tool to detect COVID-19, based on advanced image processing algorithms. Immediate and sensitive screening tools for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection are essential in order to limit the spread of the disease and to properly allocate national resources. Infrared thermography scanners have been widely used as a screening tool during past infectious disease epidemics, including COVID-194,5 This technique is based on the assessment of absolute body temperature in order to screen individuals with fever, and lacks specificity for COVID-195. We developed automated image processing algorithms for analysis of thermal images of the back, captured by a portable thermal camera that connects directly to smartphones. We aimed to determine the ability of Scientific Reports | (2021) 11:17489

Objectives

Methods

Results

Conclusion