System and method for automated stereology of cancer

1. An automated stereology system configured to determine whether a tissue sample is representative of cancerous tissue, the system comprising an electronic processor configured to:

apply an ensemble of segmentations to a plurality of greyscale images to generate a set of segmented images for each of the plurality of greyscale images;

determine if a segmented image of the set of segmented images comprises a blob that is larger than a predetermined maximum blob size, and reject the set of segmented images if a segmented image of the set of segmented images comprises a blob that is larger than a predetermined maximum blob size;

determine if at least half of the segmented images of the set of segmented images are similar, reject the set of segmented images if at least half of the segmented images of the set of segmented images are not similar, and accept the set of segmented images if at least half of the segmented images of the set of segmented images are similar to generate a set of accepted image level segmented images;

determine if a blob is present in at least half of the segmented images of the set of segmented images, reject the set of segmented images if the blob is not present in at least half of the segmented images of the set of segmented images, and accept the set of segmented images if the blob is present in at least half of the segmented images of the set of segmented images to generate a set of accepted blob level segmented images;

combine the segmented images of the set of accepted image level segmented images using a consensus function to generate a final image level segmentation;

combine the segmented images of the set of accepted blob level segmented images using a consensus function to generate a final blob level segmentation; and

calculate the mean nuclear volume of the final image level segmentation and the final blob level segmentation to determine if the tissue sample is representative of cancerous tissue.

2. The system of claim 1 , wherein the electronic processor is further configured to:

receive a plurality of color microscopy images of at least one stained tissue sample; and

convert the plurality of color microscopy images to the plurality of greyscale microscopy images.

3. The system of claim 2 , wherein the electronic processor is further configured to convert the plurality of color microscopy images to the plurality of greyscale microscopy images by using a Karhunen-Loeve transform to convert the images to greyscale.

4. The system of claim 1 , wherein the electronic processor is further configured to:

perform, prior to applying the ensemble of segmentations to the plurality of greyscale images, screening of each of the plurality of greyscale images to determine if the pixel intensity of each of the plurality of greyscale images is acceptable; and

reject the greyscale images if the pixel intensity of the greyscale image is not acceptable.

5. The system of claim 1 , wherein each of the segmentations of the ensemble of segmentations comprises a three-class Otsu thresholding algorithm.

6. The system of claim 1 , wherein each of the segmentations of the ensemble of segmentations comprises at least one morphological operation.

7. The system of claim 1 , wherein each of the segmentations of the ensemble of segmentations comprises a common algorithm having different parameter settings.

8. The system of claim 1 , wherein each of the segmentations of the ensemble of segmentations comprises a different algorithm.

9. The system of claim 1 , wherein the electronic processor is further configured to perform, prior to applying an ensemble of segmentations to the plurality of greyscale images, a connected component analysis to remove blobs from the greyscale images that are smaller than a predetermined minimum blob size.

10. The system of claim 1 , wherein the electronic processor is configured to determine if a blob is present in at least half of the segmented images of the set of segmented images by comparing the blobs of the segmented images based upon a colinearity criterion and an area overlap criterion.

11. The system of claim 1 , wherein the electronic processor is configured to calculate the mean nuclear volume of the final image level segmentation by applying stereological methods to obtain mean nuclear volume estimates of the blobs using a point-sampled intercept.

12. The system of claim 1 , wherein the electronic processor is further configured to:

receive a plurality of color microscopy images of at least one stained tissue sample;

convert the plurality of color microscopy images to a plurality of greyscale microscopy images; and

perform screening of each of the plurality of greyscale images to determine if the pixel intensity of each of the plurality of greyscale images is acceptable and reject the greyscale images if the pixel intensity of the greyscale image is not acceptable.

13. The system of claim 1 , further comprising a microscope imaging device configured to capture microscopy images.

14. The system of claim 13 , further comprising a motorized X-Y-Z stage configured to adjust a position of the microscope imaging device relative to a sample or a position of the sample relative or the microscope imaging device in order to capture color microscopy images of the sample from different positions.

15. The system of claim 13 , wherein the electronic processor is further configured to:

receive a plurality of color microscopy images of at least one stained tissue sample from the microscopy imaging device;

convert the plurality of color microscopy images to a plurality of greyscale microscopy images; and

perform a screening of each of the plurality of greyscale images to determine if the pixel intensity of each of the plurality of greyscale images is acceptable and reject the greyscale images if the pixel intensity of the greyscale image is not acceptable.

16. A microscopy system comprising:

a microscope imaging device including a camera configured to capture microscopy images of a sample;

an electronic processor; and

a non-transitory computer-readable memory storing instructions that, when executed by the electronic processor, cause the microscopy system to:

apply an ensemble of segmentations to a plurality of greyscale images to generate a set of segmented images for each of the plurality of greyscale images;

determine if a segmented image of the set of segmented images comprises a blob that is larger than a predetermined maximum blob size, and reject the set of segmented images if a segmented image of the set of segmented images comprises a blob that is larger than a predetermined maximum blob size;

determine if at least half of the segmented images of the set of segmented images are similar, reject the set of segmented images if at least half of the segmented images of the set of segmented images are not similar, and accept the set of segmented images if at least half of the segmented images of the set of segmented images are similar to generate a set of accepted image level segmented images;

determine if a blob is present in at least half of the segmented images of the set of segmented images, reject the set of segmented images if the blob is not present in at least half of the segmented images of the set of segmented images, and accept the set of segmented images if the blob is present in at least half of the segmented images of the set of segmented images to generate a set of accepted blob level segmented images;

combine the segmented images of the set of accepted image level segmented images using a consensus function to generate a final image level segmentation;

combine the segmented images of the set of accepted blob level segmented images using a consensus function to generate a final blob level segmentation; and

calculate the mean nuclear volume of the final image level segmentation and the final blob level segmentation to determine if the tissue sample is representative of cancerous tissue.

17. The microscopy system of claim 16 , wherein the instructions, when executed by the electronic processor, cause the microscopy system to:

operate the microscope imaging device to capture a plurality of color images of at least one stained tissue sample;

convert the plurality of color microscopy images to a plurality of greyscale microscopy images; and

perform a screening of each of the plurality of greyscale images to determine if the pixel intensity of each of the plurality of greyscale images is acceptable and reject the greyscale images if the pixel intensity of the greyscale image is not acceptable.