ABSTRACT
We propose a remote method to estimate continuous blood pressure (BP) based on spatial information of a pulse-wave as a function of time. By setting regions of interest to cover a face in a mutually exclusive and collectively exhaustive manner, RGB facial video is converted into a spatial pulse-wave signal. The spatial pulse-wave signal is converted into spatial signals of contours of each segmented pulse beat and relationships of each segmented pulse beat. The spatial signal is represented as a time-continuous value based on a representation of a pulse contour in a time axis and a phase axis and an interpolation along with the time axis. A relationship between the spatial signals and BP is modeled by a convolutional neural network. A dataset was built to demonstrate the effectiveness of the proposed method. The dataset consists of continuous BP and facial RGB videos of ten healthy volunteers. The results show an adequate estimation of the performance of the proposed method when compared to the ground truth in mean BP, in both the correlation coefficient (0.85) and mean absolute error (5.4 mmHg). For comparison, the dataset was processed using conventional pulse features, and the estimation error produced by our method was significantly lower. To visualize the root source of the BP signals used by our method, we have visualized spatial-wise and channel-wise contributions to the estimation by the deep learning model. The result suggests the spatial-wise contribution pattern depends on the blood pressure, while the pattern of pulse contour-wise contribution pattern reflects the relationship between percussion wave and dicrotic wave.
ABSTRACT
Artificial red blood cells (i.e. hemoglobin [Hb] vesicles [Hb-Vs]) function effectively as photosensitizers in flashlamp-pumped pulsed-dye laser (PDL) treatment for port-wine stains in animal models. Hb-Vs deliver more Hb to the vicinity of the endothelial cells. Both Hb-Vs and red blood cells absorb the laser energy and generate heat, supporting the removal of very small blood vessels and deeper subcutaneous blood vessels with PDL irradiation in in vivo experiments. Here, we analyzed the photosensitizing effect of Hb-Vs in PDL irradiation on large blood vessels and surrounding soft tissues. We histopathologically analyzed markers of damage to the large vessels and surrounding dermal tissue in a rabbit auricle model following PDL irradiation alone or subsequent to the addition of intravenous Hb-V injection. Markers were graded on a five-point scale and statistically compared. The changes in laser light absorption and reflection in a human skin model caused by the administration of Hb-Vs were evaluated using Monte Carlo light-scattering programs. Histological markers of damage to blood vessels were significantly greater in Hb-V-injected arteries and veins measuring 1-3 mm in diameter as compared with the controls. However, Hb-V injection significantly reduced PDL-induced necrosis and hemorrhage in the surrounding tissues. During computer simulation, photon absorption increased within the vessel layer and decreased around the layer. Intravenous Hb-Vs increase the extent of damage in larger vessel walls but significantly reduce damage to the surrounding skin after subsequent PDL irradiation. These beneficial effects are the result of improving vessel selectivity by Hb-Vs in vessels. Hb-V administration prior to PDL irradiation therapy could mechanically improve the outcomes and safety profiles of port-wine stain treatment protocols.
