mHealth spectroscopy of blood hemoglobin with spectral super-resolution

Abstract

Although blood hemoglobin (Hgb) testing is a routine procedure in a variety of clinical situations, noninvasive, continuous, and real-time blood Hgb measurements are still challenging. Optical spectroscopy can offer noninvasive blood Hgb quantification, but requires bulky optical components that intrinsically limit the development of mobile health (mHealth) technologies. Here, we report spectral super-resolution (SSR) spectroscopy that virtually transforms the built-in camera (RGB sensor) of a smartphone into a hyperspectral imager for accurate and precise blood Hgb analyses. Statistical learning of SSR enables us to reconstruct detailed spectra from three color RGB data. Peripheral tissue imaging with a mobile application is further combined to compute exact blood Hgb content without a priori personalized calibration. Measurements over a wide range of blood Hgb values show reliable performance of SSR blood Hgb quantification. Given that SSR does not require additional hardware accessories, the mobility, simplicity, and affordability of conventional smartphones support the idea that SSR blood Hgb measurements can be used as an mHealth method.

Smartphone-based imaging systems for medical applications: a critical review

“…This is especially important in spectroscopic, chromatic, and filtered light applications for external tissue measurements. 6 , 17 , 52 , 64 , 68 , 71 – 73 Additionally, light emission from tissue comes at high numerical aperture, and so control over access to these signals requires careful lens design and external light control. Filtering of signals is always challenging given the range of choices and the typically short camera–tissue distances, and so evaluation of the contaminating signals is important, as are choices about use of potentially multiple filters.…”

“…Monitoring applications often require repeated sampling over a sustained period (from hours up to months) to assess appreciable differences in disease states, and therefore benefit from being low-cost and noninvasive. In recent years, SBI systems have been proposed for monitoring of vital signs, 103 – 109 blood glucose, 110 – 113 blood pressure, 114 , 115 blood oxygenation, 68 , 116 hemoglobin concentration, 72 atrial fibrilation, 117 , 118 jaundice, 73 , 97 , 119 , 120 skin cancer, 121 and diabetic foot ulcers. 55 , 122 All of these applications propose utilizing either contact-based or contactless optical measurements using the smartphone camera, most often by individuals on themselves (i.e., self-monitoring).…”

“…Noncontact-based methods for extracting hemodynamics using video recording are a more recent development which more fully utilizes the spatial information provided by smartphone imaging. 68 , 72 , 104 , 123 , 124 Two recent works, by Park et al. 72 and He and Wang, 68 used computational techniques to infer higher resolution spectral responses and predict hemoglobin content in tissue using only RGB smartphone image data.…”

“…also performed a more rigorous quantitative comparison of their noninvasive hemoglobin concentration prediction compared to the gold-standard obtained by venous blood draw, observing good quantitative agreement of their noninvasive hemoglobin predictions ( for 15 test patients). 72 The work by Park et al. showed a rigorous and realistic assessment of their method in a clinical setting.…”

Optical density based quantification of total haemoglobin concentrations with spectroscopic optical coherence tomography

“…Non-invasive [tHb] quantification methods leverage on the high absorption of haemoglobin for wavelengths in the visible and near-infrared range 6 – 8 . These techniques include smart-phone image analysis 9 , photoplethysmography 10 , diffuse reflectance spectroscopy 11 , 12 , photoacoustic spectroscopy 13 , 14 , ultrasound 15 , 16 , and more recently, spectroscopic optical coherence tomography 17 , 18 . Smart-phone images have grown in attention because of their accessibility, ease of use and high precision ( g/dL).…”