System and method for tissue analysis using remote PPG
A tissue analysis system and method process hyperspectral images to classify tissue types within the images. A presence or level of tissue oxygenation is estimated for each tissue type as well as a PPG perfusion. The estimated tissue oxygenation and PPG perfusion information are combined to provide a tissue status for each tissue type. The system and method uses remote PPG sensing.
1 . A system for tissue analysis, comprising:
a processor adapted to receive hyperspectral images captured by a hyperspectral image sensor and to process the images to:
derive a photoplethysmography (PPG) delay map from PPG relative delays between different image regions;
classify tissue types and segment the hyperspectral images into one or more regions corresponding to different tissue types using the different PPG delays to different regions of the images;
estimate a presence or level of tissue oxygenation for each tissue type;
derive a PPG perfusion map from PPG amplitude levels at one or more wavelengths of the hyperspectral image sensor; and
combine the estimated tissue oxygenation and PPG perfusion information from the PPG perfusion map to derive a tissue perfusion and oxygenation status for each tissue type.
2 . The system of claim 1 , wherein the processor is adapted to classify the tissue types using a machine learning algorithm.
3 . The system of claim 1 , wherein the tissue types comprise tissues for different organ types or tissues for different regions of an organ.
4 . The system of claim 1 , wherein the hyperspectral images comprise a set of 2D images, each at a different wavelength of a set of wavelengths.
5 . The system of claim 4 , wherein the processor is adapted to estimate the tissue oxygenation using spectral information from hyperspectral images for at least two different wavelengths and to derive the PPG perfusion map from at least one of the 2D images.
6 . The system of claim 1 , wherein said relative delays comprise a delay relative to a reference PPG signal which is an average delay time period for all image regions for a frame of image data.
7 . The system of claim 1 , wherein the tissue perfusion and oxygenation status comprises one of:
above normal pulsation and normal oxygenation;
above normal pulsation and below normal oxygenation;
normal pulsation and normal oxygenation;
normal pulsation and below normal oxygenation;
below normal pulsation and normal oxygenation;
below normal pulsation and below normal oxygenation.
8 . The system of claim 1 , further comprising a hyperspectral image sensor for capturing the hyperspectral images.
9 . The system of claim 1 , wherein the processor is further adapted to obtain a standard level of perfusion at homeostasis for each classified tissue type, for comparison with the derived tissue perfusion status.
10 . A computer-implemented tissue analysis method, comprising:
receiving hyperspectral image sensor images;
deriving a PPG delay map from PPG relative delays between different image regions;
classifying tissue types and segmenting the hyperspectral images into one or more regions corresponding to different tissue types using the different PPG delays to different regions of the images;
estimating a presence or level of tissue oxygenation for each tissue type;
deriving a PPG perfusion map from PPG amplitude levels at one or more wavelengths of the hyperspectral image sensor; and
combining the estimated tissue oxygenation and PPG perfusion information from the PPG perfusion map to derive a tissue perfusion and oxygenation status for each tissue type.
11 . The method of claim 10 , wherein the tissue types comprise tissues for different organ types or tissues for different regions of an organ.
12 . The method of claim 10 , wherein the hyperspectral images comprise a set of 2D images, each at a different wavelength of a set of wavelength and wherein the method comprises:
estimating the tissue oxygenation using spectral information from hyperspectral images for at least two different wavelengths; and
deriving the PPG perfusion map from at least one of the 2D images.
13 . The method of claim 10 , comprising obtaining a standard level of perfusion at homeostasis for each classified tissue type, for comparison with the derived tissue perfusion status.
14 . A non-transitory computer-readable medium storing instructions that, when executed by a processor, causes the processor to perform a method comprising:
receiving hyperspectral images captured by a hyperspectral image sensor:
deriving a photoplethysmography (PPG) delay map from PPG relative delays between different image regions;
classifying tissue types and segment the hyperspectral images into one or more regions corresponding to different tissue types using the different PPG delays to different regions of the images;
estimating a presence or level of tissue oxygenation for each tissue type;
deriving a PPG perfusion map from PPG amplitude levels at one or more wavelengths of the hyperspectral image sensor; and
combining the estimated tissue oxygenation and PPG perfusion information from the PPG perfusion map to derive a tissue perfusion and oxygenation status for each tissue type.
15 . The non-transitory computer-readable medium of claim 14 , wherein the hyperspectral images comprise a set of 2D images, each at a different wavelength of a set of wavelength, and wherein the method performed by the processor comprises:
estimating the tissue oxygenation using spectral information from hyperspectral images for at least two different wavelengths; and
deriving the PPG perfusion map from at least one of the 2D images.