Multi-spectral imaging including at least one common stain

1. An apparatus comprising:

a means for obtaining a set of spectral images of a sample, wherein the sample has M>2 different components labeled with N<M stains so that at least two different components are labeled with a common stain and wherein the sample is further stained with at least one histological stain;

a display device; and

an electronic processor connected to the means for obtaining the set of spectral images and the display device, and comprising software instructions that, when executed, cause the electronic processor to:

display at least one image of the set of spectral images on the display device, wherein the at least one image shows the at least two different components labeled with the common stain;

analyze an image stack derived from the set of spectral images to generate a first image comprising contributions from only the at least one histological stain, and a second image comprising contributions from the at least two different components labeled with the common stain;

classify different cellular compartments of the sample into respective classes based on one or more of signal strength, shape, spectral features, and textural features in at least the first image;

identify each of the at least two different components in the sample labeled with the common stain based on the classified cellular compartments of the sample;

generate output image information from the set of spectral images based on the classified cellular compartments and comprising a set of additional images, wherein each additional image in the set shows a different one of the at least two different components labeled with the common stain; and

display the output image information on the display device.

2. The apparatus of claim 1 , wherein the electronic processor further comprises software instructions that, when executed, cause the electronic processor to determine relative amounts of multiple ones of the M different components in different regions of the sample.

3. The apparatus of claim 1 , wherein the electronic processor is configured to perform the classification by decomposing the set of spectral images into an unmixed image set, wherein each member of the unmixed image set corresponds to a respective one of the stains, and to classify the different parts of the sample into the respective classes based on an image stack comprising one or more of the unmixed images.

4. The apparatus of claim 1 , wherein M>2 and N>1.

5. The apparatus of claim 1 , wherein the means for obtaining the set of spectral images comprises an RGB camera.

6. The apparatus of claim 2 , wherein the electronic processor further comprises software instructions that, when executed, cause the electronic processor to perform the determination based on the set of spectral images and the classification.

7. The apparatus of claim 1 , wherein the electronic processor further comprises software instructions that, when executed, cause the electronic processor to:

decompose the set of spectral images into an unmixed image set, each member of the unmixed image set corresponding to a spectral contribution from a respective one of the N stains for labeling the M types of components or the histological stain; and

determine relative amounts of multiple ones of the M different components in different regions of the sample based on the unmixed image set.

8. The apparatus of claim 1 , wherein the electronic processor comprises software instructions that, when executed, cause the electronic processor to classify the different cellular compartments of the sample into respective classes using a neural network-based classifier.