Thales Thermography Triage (3T) - Pilot Project

In the fifty years since the emergence of thermal imaging technology, Thales in Glasgow has built up a world leading capability in the design, manufacture and supply of Thermal Imaging cameras. In addition to the cameras, Thales in Glasgow has a particular expertise in developing image processing algorithms (conventional and artificial intelligence based) to allow the cameras to perform critical user tasks beyond mere imaging.

COVID-19 [SARS-COV-2] has placed a huge challenge on the world. In response to the crisis, Thales is engaged in a number of initiatives, including one aimed at the possible application of thermal imaging cameras to detect people with a fever and hence those who may be suffering from COVID-19.Fever is a key symptom of covid-19. One of the major limitations of existing systems is thermographic accuracy. Most current thermographic camera systems offer an accuracy of ± 0.5°C. This can be reduced to ±0.3°C with the inclusion of a "Black Body" calibration source, although this limits the portability of the system. Using their unique knowledge and expertise in high resolution and precision thermal imaging and thermal image processing, Thales aims to develop a fever screening system with an accuracy of ± 0.1°C to enable more effective identification and triage of people with fever.

What Thales lacks is real world thermal images of patients suffering fever and access to clinicians who can advise on the medical aspects of the work. This research would fill these two voids.

In a pilot study conducted in the Emergency Department, Queen Elizabeth University Hospital (20/NS/0064), the Thales High Temperature Detection (HTD) system was found to be more accurate than a tympanic thermometer which captures Infrared radiation emitted by the tympanic membrane in the ear or forehead thermometer. Tympanic temperature measurements are typically used in the hospital setting in Scotland whereas forehead IR measurement is common in transportation and workplace settings.

The HTD has been redesigned in response to three key findings from the pilot study:

• The relative temperature of some facial features correlated more strongly with tympanic temperature than others.
• Having an external Black Body (BB) calibration source in the scene at all times was impractical in a clinical environment
• Camera systems require to be compact and portable to be useful to clinical staff.

As a result, the HTD is now significantly reduced in size, including peripheral devices. A novel calibration solution has been designed (and patented) that not only removes the need for the black body source but allows for a more accurate temperature evaluation. In addition, facial feature detection has been integrated into the software to allow it to automatically locate the patient's head and in the near future, automatically determine the temperatures of individual facial features. This development will capture facial feature detection - not facial recognition.