Automated Processing Of Non-Invasive Thermal Imaging Of Organ-Specific Diseases To Detect Inflammation And Vascular Dysfunction
During the COVID-19 worldwide pandemic, rapid and sensitive screening tools for SARS-CoV2 infection were defined critical for limiting the spread of COVID-19 and for allocating national resources properly. Researchers have developed and tested a new point-of-care, non-contact, thermal camera that connects directly to smartphones combined with image-processing algorithms, and machine learning-based analysis, to detect inflammation and vascular dysfunction caused by COVID-19 or any other pandemic.
The technology is suitable for other pandemic scenarios as a cheap and effective tool for detecting these phenomena.
The coronavirus disease 2019 (COVID-19) pandemic has imposed an immense burden on out-of-hospital health care services and community-based testing sites worldwide. Immediate and sensitive screening tools for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection were essential in order to limit the spread of the disease and to properly allocate national resources.
The common and standard diagnosis of SARS-CoV-2 infection is based on a virus-specific quantitative real-time PCR (qRT-PCR), and can take up to several hours to complete, depending on available resources and disease burden in the region. Furthermore, a significant amount of skilled labor is required at the different stages of the testing (sampling, preparation, and analysis).
We present an innovative diagnostic tool, a non-contact, non-invasive thermal imaging camera that connects directly to a smartphone combined with automated image-processing algorithms, and machine learning-based analysis to detect COVID-19 and its associated inflammation and vascular dysfunction, as described in Figure 1.
Our novel image processing algorithms automatically extracted multiple texture and shape features of the thermal images. Processing of the two leading features, fractal dimension and sum of extrema.
Our solution is relatively cheap, easy to use, and delivers immediate test results.
A portable image based tool for monitoring patients with pneumonia out-of-hospital, in quarantine or in in-home-care settings, for the purpose of early and quick triage, risk stratification of suspected individuals, promotion of clinical decisions, allocation of resources, and protecting public health.
It is therefore especially applicable for out-of-hospital screening by first responders (paramedics, nurses, medical technicians, etc.), home care facilities, military bases, and regions with limited diagnostic resources.
Potential applications using the technology - the technology can be used to detect and monitor ischemic and dead tissues or organs, wound healing, infections, inflammation, and fibrosis in tissues and organs (e.g., pneumonia, fatty liver, orchitis, epididymitis, etc.). note that some of the indications in specific organs need additional validation.
Full proof of concept laboratory scale.
THE TECHNOLOGY WAS DEVELOPED IN COLLABORATION WITH THE ADDITIONAL RESEARCHERS:
Dr. Oshrit Hopper - Afeka
Dr. Zehava Blechman - Afeka
Dr. Yair Zimmer - Afeka
Dr. Rafel Brzezinski – Tau / Tel Hashomer
THERMAL IMAGING FOR DETECTION OF DISEASE, US application No. 17/557,271, Priority Date Dec 21, 2020
Rafael Y. Brzezinski, Neta Rabin, Nir Lewis, Racheli Peled, Ariel Kerpel, Avishai M.Tsur, Omer Gendelman, Nili Naftali Shani, Irina Gringauz, Howard Amital, Avshalom Leibowitz, Haim Mayan, Ilan Ben Zvi, Eyal Heller, Liran Shechtman, Ori Rogowski, Shani Shenhar Tsarfaty, Eli Konen, Edith M. Marom, Avinoah Ironi, Galia Rahav, Yair Zimmer, Ehud Grossman, Zehava Ovadia Blechman, Jonathan Leor & Oshrit Hofer (2021). Automated processing of thermal imaging to detect COVID 19. Sci Rep 11, 17489 (2021). https://doi.org/10.1038/s41598...