Hyperspectral learning for instantaneous spatiospectral imaging of hemodynamics

A method of generating an image or video of a field of interest of a sample, comprising:

• obtaining:
• i) a first Red-Green-Blue (RGB) image from about a field of interest of a sample, and ii) hyperspectral data from a subarea of the field of interest;
• extracting an RGB image of the subarea from the first RGB image of the field of interest;
• applying the hyperspectral data of the subarea to conduct a spectroscopic analysis of a sample, thereby generating spectral parameters for the subarea;
• inputting i) the generated spectral parameters, and ii) the extracted RGB image of the subarea, collectively as training input data to a deep learning model;
• training the deep learning model with the training input data thus generating a trained deep learning model;
• obtaining a second RGB image about the field of interest including areas outside of the subarea;
• inputting the second RGB image of the field of interest to the trained deep learning model;
• outputting from the trained deep learning model a spectral map for the field of interest;
• and
• extracting hemodynamic parameters from the outputted spectral map of the field of interest;
• and
• determining oxygen saturation (sPO2).