Thermal Imaging Could Accurately Track Vital Signs for Early Disease Detection

Traditional methods for measuring these vital signs involve contact-based devices such as electrocardiograms for heart rate, pulse oximeters, capnography, or respiratory inductance plethysmography for respiratory rate, and thermometers for temperature. While these methods are effective, they often require direct contact and are less suited for continuous, comprehensive monitoring. The emergence of wearable health-monitoring devices like smartwatches, fitness bands, and adhesive patches allows for continuous ambulatory monitoring of these vital signs. However, many of these devices still require physical contact and may not be ideal for users with skin irritations, wounds, or insufficient skin area. Now, biomedical engineers have developed a novel system that collects and processes thermal images, enabling the reliable and detailed measurement of vital signs such as heart rate, respiration rate, and body temperature in a passive, non-contact manner. This system could eventually aid in early disease detection, including cancer, by identifying subtle changes in body tissues.

Thermal imaging has greatly advanced medical and health fields, enabling essential tasks like exploring human physiology, detecting diseases, assessing vascular disorders, monitoring inflammation, and screening for early-stage cancer. Despite these advancements, conventional thermal imaging systems face limitations, primarily due to spectral ambiguity in thermography. Researchers at the Georgia Institute of Technology (Atlanta, GA, USA) have overcome this issue, enhancing the texture and detail extracted from thermal images and eliminating environmental heat effects. With their phasor thermographic technology, they have increased the accuracy and efficiency of thermal imaging, enabling better detection of abnormalities. This method also allows for material segmentation, a capability not possible with traditional thermal imaging alone.

The improvement in this new system comes from its ability to eliminate the typical "fuzziness" associated with thermal images. Conventional thermal images struggle to distinguish subtle temperature variations, and environmental heat can introduce noise, making it difficult to accurately measure physiological signals. In a study published in Cell Reports Physical Science, the researchers demonstrated how their system precisely measured heart rate, respiratory rate, and body temperature across various body areas. The tool also effectively differentiated vital signs in images with multiple individuals and captured changes in respiration rate before and after exercise. The research team employed a series of filters to capture ten images from different parts of the infrared spectrum—specifically, the long-wavelength infrared region. This segment of the electromagnetic spectrum, which is beyond the visible light range, is where thermal radiation is detected.

Using these ten images, the researchers applied a powerful mathematical tool called thermal phasor analysis, which is commonly used in signal processing. Their algorithms resolved textures in three dimensions with sub-millimeter precision, enabling them to distinguish fine thermal variations, such as facial skin, hair of different thicknesses near the scalp, eyebrows, and even the metal rims of eyeglasses on a subject's face. Additionally, the system utilizes common equipment such as thermal cameras and filters to capture hyperspectral image data, making it highly scalable and adaptable. This capability allows the system to be integrated into virtually any thermal imaging platform used in hospitals or other healthcare environments. The team is now working on further developing the prototype and collaborating with doctors to apply it for the detection of breast cancer tumors specifically.

“Thermography could give us an advantage in early detection, because it could noninvasively detect abnormal cell activity that indicates early cancer. For example, tumor cells need more oxygen to reproduce, so their temperature will be a little bit higher than normal tissue. With this phasor thermography approach, we could spot that,” said Dingding Han, lead author on the study. “This can be the first step for the next generation of biomedical thermography for early detection and diagnosis of cancer. That’s what I’m working toward,” Han said. “It’s the first prototype with an ultimate goal of evolving the next versions and making it easier to use in hospitals and clinics.”