Patient monitoring in hospitals to improve with non-contact thermal imaging device

Share this on social media:

A team at Sheffield Hallam University in the UK has developed a medical device that uses infrared imaging to monitor patient respiratory rates. The system uses complex image processing to track the patient’s eyes and nose, details which are then used to extract pertinent thermal information relating to respiration rate and the person’s well-being.

Respiration rate (RR) is a physiological measurement, like temperature and heart rate, that gives an indication of a person's health. Most existing methods for measuring RR rely on attaching a device to the patient, which can be uncomfortable and impractical. An audit by the National Institute for Health and Care Excellence showed that 40 per cent of feverish children at the audit hospital did not have their respiration rate monitored due to unsettlement, according to an article in Pediatric Pulmonology.

The non-contact 4FA system developed at Sheffield Hallam University uses a thermal camera to monitor the temperature of the skin around the nose, which fluctuates as the patient breathes – exhaled air is always warmer than inhaled air. By analysing this area of skin, the subject’s respiration pattern can be determined without disturbing them.

Thermal images are captured at 25 frames per second. The respiration rate of an unwell infant can be greater than 80 cycles per minute, and, therefore, any image-based monitoring must be able to process enough images per second to obtain an acceptable respiration signal, according to Dr Reza Saatchi, who heads the Medical Electronics Engineering Research Group (MEERG) at Sheffield Hallam University.

National Instrument’s LabView and products from the NI Vision platform were used to control the camera operation. The thermal images are first normalised from 16-bit greyscale to 8 bits and then segmented to extract the face from the rest of the body.

The face is then mapped, using an intelligent learning algorithm developed in the NI Vision Development Module to detect the corners of the eyes, even when the head is inclined. The corners of the eyes are the warmest part of the face, the tip of the nose the coldest. The nostrils can be found by searching for the region directly below the corners of the eyes and in line with the tip of the nose. The pixel values are then extracted and processed within this region of interest, and the respiration rate determined by repeating the process over a number of frames.

According to Dr Saatchi, 4FA eliminates patient discomfort, improves analysis accuracy, and reduces set-up complexity, thereby increasing respiratory monitoring in child patients by about 50 per cent.

He said that the 2010 Resuscitation Guidelines of the Resuscitation Council (RC) recommend that monitoring of vital signs (including respiration rate) of patients is one of the ‘strategies for the prevention of avoidable in-hospital cardiac arrests’. A similar recommendation can be found in the National Confidentiality Enquiry into Patient Outcome and Death (NCEPOD). The device can improve respiration rate monitoring and help achieve the recommendations of both NCEPOD and RC, the researchers state.

Further information:

Related articles:

NIWeek Vision Summit to highlight automated and robotic inspection 

Recent News

29 July 2020

The Perseverance rover contains 19 cameras, including seven scientific instruments. It will analyse the climate and geology of Mars, looking for signs of past life, as well as monitoring the Martian atmosphere

02 July 2020

Norwegian seafood firm, Lerøy, has installed hyperspectral cameras on processing lines to sort fish. The system is able to measure the amount of blood in white fish, which gives a grade of quality

09 June 2020

Hyperspectral imaging is being used in a research programme at hospitals in Maryland and New York to investigate the prognostic value of skin findings associated with Covid-19 infection

27 May 2020

The composite picture of The Night Watch, made of 528 exposures stitched together digitally, makes it possible to zoom in on individual brushstrokes and even particles of pigment in the painting