Real-time whole slide pathology image cell counting

1. A cell counting computing apparatus comprising:

at least one computer-readable memory storing cell counting software instructions;

at least one processor coupled with the at least one computer-readable memory and that operates as a cell counting engine upon execution of the cell counting software instructions to:

obtain, in the at least one computer-readable memory, a whole image comprising images of cells;

segment the whole image into image areas based on a first global thresholding filter with respect to a first threshold;

select a plurality of patches associated with the image areas;

generate an intensity image based on intensity vectors for each patch in the plurality of patches by determining an optical density of each patch;

generate at least one cell mask with at least one cell seed by iteratively segmenting the intensity image based on a second global thresholding filter with respect to a second iteratively reducing threshold;

generate a distance map from the at least one cell mask via a chamfer distance transform;

distinguish cell segments within the plurality of patches via a watershed transform of the distance map and at least one cell seed; and

configure a device to display a cell count for at least one patch in the plurality of patches based on counting the cell segments.

2. The apparatus of claim 1 , wherein the first threshold is based on at least one of an Otsu filter and a Yen filter.

3. The apparatus of claim 2 , wherein the first threshold is based on a minimum of the Otsu filter and the Yet filter.

4. The apparatus of claim 1 , wherein the second iteratively reducing threshold is related to a known cell size.

5. The apparatus of claim 4 , wherein the known cell size corresponds to a known human cell size or a known animal cell size.

6. The apparatus of claim 4 , wherein the known cell size is between about 5 microns and about 20 microns.

7. The apparatus of claim 1 , wherein the optical density comprises an RGB density.

8. The apparatus of claim 1 , wherein the plurality of patches is associated with at least one selected region of interest.

9. The apparatus of claim 8 , wherein the cell count relates to the at least one selected region of interest.

10. The apparatus of claim 8 , wherein the at least one selected region of interest is based on a set of points that form a closed curve in the whole image.

11. The apparatus of claim 1 , wherein the device is configured to display the cell count in real-time.

12. The apparatus of claim 1 , wherein the cell count comprises a whole cell count for the whole image.

13. The apparatus of claim 1 , wherein the whole image comprises a whole-slide pathology image.

14. The apparatus of claim 1 , wherein the plurality of patches is selected, at least in part, randomly.

15. The apparatus of claim 1 , wherein the image areas comprise tissue areas.

16. The apparatus of claim 1 , wherein the distance map indicates a distance to a nearest background point.

17. The apparatus of claim 1 , wherein the at least one cell seed is determined via gaussian smoothing the distance map.

18. The apparatus of claim 1 , wherein the at least one cell seed relates to a maximum height marker in the distance map.

19. The apparatus of claim 1 , where in the cell count comprises an updated cell count based a change in a region of interest.

20. A non-transitory, computer-readable medium storing instructions, when executed by at least one processor and memory, cause the at least one processor to perform one or more steps comprising:

obtaining, in at least one computer-readable memory, a whole image comprising images of cells;

segmenting the whole image into image areas based on a first global thresholding filter with respect to a first threshold;

selecting a plurality of patches associated with the image areas;

generating an intensity image based on intensity vectors for each patch in the plurality of patches by determining an optical density of each patch;

generating at least one cell mask with at least one cell seed by iteratively segmenting the intensity image based on a second global thresholding filter with respect to a second iteratively reducing threshold;

generating a distance map from the at least one cell mask via a chamfer distance transform;

distinguishing cell segments within the plurality of patches via a watershed transform of the distance map and at least one cell seed; and

configuring a device to display a cell count for at least one patch in the plurality of patches based on counting the cell segments.

21. A computerized method comprising:

obtaining, in at least one computer-readable memory, a whole image comprising images of cells;

segmenting the whole image into image areas based on a first global thresholding filter with respect to a first threshold;

selecting a plurality of patches associated with the image areas;

generating an intensity image based on intensity vectors for each patch in the plurality of patches by determining an optical density of each patch;

generating at least one cell mask with at least one cell seed by iteratively segmenting the intensity image based on a second global thresholding filter with respect to a second iteratively reducing threshold;

generating a distance map from the at least one cell mask via a chamfer distance transform;

distinguishing cell segments within the plurality of patches via a watershed transform of the distance map and at least one cell seed; and

configuring a device to display a cell count for at least one patch in the plurality of patches based on counting the cell segments.