Machine learning systems and techniques for multispectral amputation site analysis

A tissue classification system comprising:

• at least one light emitter configured to emit light at each of a plurality of wavelengths to illuminate a tissue region, each of the at least one light emitter being configured to emit spatially-even light;
• at least one light detection element configured to collect the light after being emitted from the at least one light emitter and reflected from the tissue region;
• one or more processors in communication with the at least one light emitter and the at least one light detection element and configured to:
• identify at least one patient health metric value corresponding to a patient having the tissue region,
• use the at least one patient health metric value to select a classifier from among a plurality of classifiers, each of the plurality of classifiers trained from a different subset of a set of training data, wherein the classifier is selected based on having been trained with a subset of the set of the training data including data from other patients having the at least one patient health metric value;
• control the at least one light emitter to sequentially emit each of the plurality of wavelengths of light;
• receive a plurality of signals from the at least one light detection element, a first subset of the plurality of signals representing light emitted at the plurality of wavelengths and reflected from the tissue region;
• generate, based on at least some of the plurality of signals, an image having a plurality of pixels depicting the tissue region;
• for each pixel of the plurality of pixels depicting the tissue region:
• determine, based on the first subset of the plurality of signals, a reflectance intensity value at the pixel at each of the plurality of wavelengths, and
• determine a healing classification score of the pixel by inputting the reflectance intensity value into the classifier;
• and
• generate, based on the healing classification score of each pixel, an overall healing score for the plurality of pixels depicting the tissue region.

A tissue classification method comprising:

• selecting, based on at least one patient health metric value, a classifier from among a plurality of classifiers, each of the plurality of classifiers trained from a different subset of a set of training data, wherein the classifier is selected based on having been trained with a subset of the set of the training data including data from other patients having the at least one patient health metric value;
• receiving a plurality of signals from at least one light detection element positioned to receive light reflected from a tissue region, a first subset of the plurality of signals representing light emitted at a plurality of wavelengths reflected from the tissue region;
• generating, based on at least a portion of the plurality of signals, an image having a plurality of pixels depicting the tissue region;
• for each pixel of the plurality of pixels depicting the tissue region:
• determining, based on the first subset of the plurality of signals, a reflectance intensity value at the pixel at each of the plurality of wavelengths, and
• determining a healing classification score of the pixel by inputting the reflectance intensity value into the classifier;
• and
• generating, based on the healing classification score of each pixel, an overall healing score for the plurality of pixels depicting the tissue region.

A method of identifying a recommended location of an amputation, the method comprising:

• selecting a patient having a tissue region in need of amputation;
• programmatically controlling, via one or more hardware processors, an imaging system to capture data representing a plurality of images of the tissue region, the data representing the plurality of images including a first subset each captured using light of a different one of a number of different wavelengths reflected from the tissue region;
• generating, based on at least one of the plurality of images, an image having a plurality of pixels depicting the tissue region;
• for each pixel of the plurality of pixels depicting the tissue region:
• determining, based on the first subset of the data representing the plurality of images, a reflectance intensity value at the pixel at each of the plurality of wavelengths, and
• determining a healing classification score of the pixel by at least inputting the reflectance intensity value into a classifier;
• and
• identifying, based on the healing classification score of each pixel, the recommended location of the amputation within the tissue region.