Automated processing of thermal imaging to detect COVID-19

This article has been Reviewed by the following groups

Read the full article See related articles

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.

Article activity feed

  1. SciScore for 10.1101/2020.12.22.20248691: (What is this?)

    Please note, not all rigor criteria are appropriate for all manuscripts.

    Table 1: Rigor

    Institutional Review Board StatementIRB: The study was approved by the institutional review boards of each participating medical center or academic institution, and participants provided verbal (recording) or written informed consent prior to their participation in the study.
    Consent: We excluded patients with any of the following conditions: lung malignancy, rheumatic disease with shoulder or back joint involvement, acute or chronic skin disease of the chest or back, critically ill patients with mechanical ventilation, and those unable to provide informed consent.
    RandomizationThe split was determined randomly.
    BlindingOn this pilot sample, we developed and calibrated our thermal image acquisition process, and began to develop our thermal image processing algorithms that we subsequently used in our final blinded study which comprised 101 individuals.
    Power Analysisnot detected.
    Sex as a biological variablenot detected.

    Table 2: Resources

    Software and Algorithms
    SentencesResources
    Statistical analyses were performed with SPSS (IBM SPSS Statistics, version 25, IBM Corp., Armonk, NY, USA, 2016), GraphPad Prism version 8.00 (GraphPad Software, La Jolla, CA, USA), and MATLAB software (Mathworks Inc. Natick, MA, USA).
    SPSS
    suggested: (SPSS, RRID:SCR_002865)
    GraphPad Prism
    suggested: (GraphPad Prism, RRID:SCR_002798)
    GraphPad
    suggested: (GraphPad Prism, RRID:SCR_002798)
    MATLAB
    suggested: (MATLAB, RRID:SCR_001622)

    Results from OddPub: We did not detect open data. We also did not detect open code. Researchers are encouraged to share open data when possible (see Nature blog).


    Results from LimitationRecognizer: We detected the following sentences addressing limitations in the study:
    Our study has several limitations. First, we used relatively small sample sizes. Second, the cutoffs used for our thermal scores to detect COVID-19 and lung injury were optimized for this specific study cohort, and need to be adjusted in future multi-center trials with larger study populations that are more gender and ethnically diverse. Future large scales efforts might also improve the relatively low specificity levels of our thermal scores in detecting COVID-19 and lung injury. Finally, data on smoking history and BMI were unavailable for the majority of the cohort due to missing variables in electronic health records. Smoking status and chronic lung injury may have an effect on thermal imaging scores and this aspect will need to be addressed in future studies. In summary, we have developed here a non-contact portable thermal imaging tool to detect COVID-19 and lung injury (Figure 7). This technique could facilitate the screening of large numbers of people in order to detect infected individuals in real time, limit the spread of COVID-19, and aid in the allocation of resources throughout the healthcare system.

    Results from TrialIdentifier: No clinical trial numbers were referenced.


    Results from Barzooka: We did not find any issues relating to the usage of bar graphs.


    Results from JetFighter: We did not find any issues relating to colormaps.


    Results from rtransparent:
    • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
    • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
    • No protocol registration statement was detected.

    About SciScore

    SciScore is an automated tool that is designed to assist expert reviewers by finding and presenting formulaic information scattered throughout a paper in a standard, easy to digest format. SciScore checks for the presence and correctness of RRIDs (research resource identifiers), and for rigor criteria such as sex and investigator blinding. For details on the theoretical underpinning of rigor criteria and the tools shown here, including references cited, please follow this link.