mHealth hyperspectral learning for instantaneous spatiospectral imaging of hemodynamics

Abstract

Hyperspectral imaging acquires data in both the spatial and frequency domains to offer abundant physical or biological information. However, conventional hyperspectral imaging has intrinsic limitations of bulky instruments, slow data acquisition rate, and spatiospectral tradeoff. Here we introduce hyperspectral learning for snapshot hyperspectral imaging in which sampled hyperspectral data in a small subarea are incorporated into a learning algorithm to recover the hypercube. Hyperspectral learning exploits the idea that a photograph is more than merely a picture and contains detailed spectral information. A small sampling of hyperspectral data enables spectrally informed learning to recover a hypercube from a red-green-blue (RGB) image without complete hyperspectral measurements. Hyperspectral learning is capable of recovering full spectroscopic resolution in the hypercube, comparable to high spectral resolutions of scientific spectrometers. Hyperspectral learning also enables ultrafast dynamic imaging, leveraging ultraslow video recording in an off-the-shelf smartphone, given that a video comprises a time series of multiple RGB images. To demonstrate its versatility, an experimental model of vascular development is used to extract hemodynamic parameters via statistical and deep-learning approaches. Subsequently, the hemodynamics of peripheral microcirculation is assessed at an ultrafast temporal resolution up to a millisecond, using a conventional smartphone camera. This spectrally informed learning method is analogous to compressed sensing; however, it further allows for reliable hypercube recovery and key feature extractions with a transparent learning algorithm. This learning-powered snapshot hyperspectral imaging method yields high spectral and temporal resolutions and eliminates the spatiospectral tradeoff, offering simple hardware requirements and potential applications of various machine-learning techniques.

Rapid Self-Healing Hydrogel with Ultralow Electrical Hysteresis for Wearable Sensing

“…Hyperspectral line-scan images (hypercube) of human skin were obtained to study inflammation, which is commonly characterized by erythema and changes in hemoglobin concentrations, following skin irritation. , A monochrome camera (GS3-U3-120S6M-C; FLIR) with a slit width of 23 μm and groove density of 150 mm –1 was used for imaging, and an LED light source with a color temperature of 6500 K (D65) was employed for illumination. Spectral calibration of the spectrograph was performed using a xenon calibration light source that emitted multiple narrow peaks at specific wavelengths.…”

In Situ Spray Polymerization of Conductive Polymers for Personalized E-textiles

“…This method involves detecting the increasing concentration of hemoglobin on the surface of the skin when inflammation occurs, in order to quantify the inflammation caused by irritants . Line-scan hyperspectral imaging technology was employed as demonstrated in previous research . Hyperspectral images (hypercubes) of human skin were obtained using a monochrome camera (GS3-U3-120S6M-C; FLIR), with a slit width of 23 μm and a groove density of 150 mm –1 .…”

“…57 Line-scan hyperspectral imaging technology was employed as demonstrated in previous research. 58 Hyperspectral images (hypercubes) of human skin were obtained using a monochrome camera (GS3-U3-120S6M-C; FLIR), with a slit width of 23 μm and a groove density of 150 mm −1 . An LED light source with a color temperature of 6,500 K (D65) was used for illumination, and spectral calibration of the spectrograph was performed using a xenon calibration light source that emitted multiple narrow peaks at specific wavelengths.…”

Tough Conductive Organohydrogel for Wearable Sensing in Extreme Environmental Conditions

“…Skin Irritation Testing: Hyperspectral line-scan images (hypercube) of human skin were captured to investigate inflammation, typically characterized by erythema and alterations in hemoglobin concentrations, following skin irritation. [16] Imaging was facilitated by a monochrome camera (GS3-U3-120S6M-C; FLIR) equipped with a 23 μm wide slit and a groove density of 150 mm −1 . Illumination was provided by an LED light source with a color temperature of 6500 K (D65).…”