Discrimination of tissues using a fast infrared probe

A system for discriminating tissue of a specimen of a subject using infrared (IR) light from an IR source, the system comprising:

• a probe, in communication with the IR source via a fiber optic cable, wherein the probe is configured to obtain a portion of an IR spectrum from response light from the specimen in response to illumination of the specimen using a specified subset of IR wavelengths provided by the IR source over a first measurement time period;
• an IR detector, couplable to the probe to detect a portion of the IR spectrum from the probe via the fiber optic cable;
• and
• a computing device, comprising a processor and a memory in communication with the processor, the memory comprising computer-executable instructions, wherein the computing device is coupled to the IR detector to receive a signal representative of the detected portion of the IR spectrum, wherein said computer-executable instructions cause the processor to evaluate the obtained portion of the IR spectrum using one or more metrics to discriminate tissue using a trained learning model that is trained by analyzing response light from ground truth training samples at specified wavelengths, wherein the specified wavelengths are specified using a specified metric comprising a ratio of absorbances of the illuminating infrared light, and wherein tissue discrimination is performed by the computing device using the trained model and a Figure of Merit (FOM) that is based on the specified metric.