System and method for on-phase microscopy

1. A method for processing microscopic images, comprising:

generating a smoothed image for a raw image by applying a smoothing filter to the raw image, wherein the raw image shows a plurality of cells and a background;

generating a high pass filter image by dividing the raw image by the smoothed image, wherein the high pass filter image has a median; and

transforming the high pass filter image into a transformed image by augmenting a spatial frequency of the plurality of cells shown in the high pass filter image with respect to the background, wherein transforming the high pass filter image into the transformed image further comprises:

normalizing the high pass filter image by the median to obtain a first result;

multiplying the first result by a scalar to obtain a second result;

subtracting the scalar from the second result to obtain a third result; and

generating the transformed image by taking an absolute value of the third result.

2. The method of claim 1 , further comprising:

selecting a sensitivity by iteratively applying a threshold to the transformed image until a sum of cells shown in the image is steady, wherein the threshold is applied at each iteration using a current sensitivity, wherein the sum of cells in the image is determined to be steady when the sum of cells remains within a threshold of an initial sum of cells after a predetermined period of time, wherein the selected sensitivity is the current sensitivity being used when the sum of cells shown in the image is determined to be steady; and

generating a processed image based on the transformed image and the selected sensitivity.

3. The method of claim 2 , wherein applying the threshold at each iteration further comprises:

determining a current threshold value for the threshold based on the current sensitivity and a focus value, wherein the threshold is applied using the current threshold value, wherein the focus value represents a degree of focus and is determined based on the raw image.

4. The method of claim 1 , wherein the plurality of cells is disposed on a plate having a first side and a second side, further comprising:

filtering at least one false positive object from the transformed image, wherein filtering the at least one false positive object further comprises calculating a jitter for each of the first side and the second side, wherein each false positive object is an object on the first side when the jitter calculated for the first side is less than the jitter calculated for the second side.

5. The method of claim 2 , wherein the processed image is a first processed image of a plurality of processed images, wherein each of the plurality of processed images shows a plate on which a plurality of cells is disposed, further comprising:

detecting the plurality of cells in each of the plurality of processed images; and

determining a degree of cell migration at each of a plurality of times based on the detected plurality of cells in each of the plurality of processed images, wherein each of the plurality of times corresponds to a respective processed image of the plurality of processed images.

6. The method of claim 5 , wherein the plate has a first side and a second side, wherein determining the degree of cell migration at each of the plurality of times further comprises:

comparing a number of cells on the first side to a number of cells on the second side based on the corresponding processed image; and

determining a value representing the degree of cell migration at the time based on the comparison.

7. The method of claim 5 , further comprising:

determining at least one morphological measure for each of the plurality of processed images based on the detected plurality of cells for the first processed image, wherein the at least one morphological measure includes at least one of: circularity, ratio between minor and major axes, area to convex area ratio, and area.

8. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process, the process comprising:

generating a smoothed image for a raw image by applying a smoothing filter to the raw image, wherein the raw image shows a plurality of cells and a background;

generating a high pass filter image by dividing the raw image by the smoothed image, wherein the high pass filter image has a median; and

transforming the high pass filter image into a transformed image by augmenting a spatial frequency of the plurality of cells shown in the high pass filter image with respect to the background, wherein transforming the high pass filter image into the transformed image further comprises:

normalizing the high pass filter image by the median to obtain a first result;

multiplying the first result by a scalar to obtain a second result;

subtracting the scalar from the second result to obtain a third result; and

generating the transformed image by taking an absolute value of the third result.

9. A system for processing images, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

generate a smoothed image for a raw image by applying a smoothing filter to the raw image, wherein the raw image shows a plurality of cells and a background;

generate a high pass filter image by dividing the raw image by the smoothed image, wherein the high pass filter image has a median; and

transform the high pass filter image into a transformed image by augmenting a spatial frequency of the plurality of cells shown in the high pass filter image with respect to the background, wherein the system is further configured to:

normalize the high pass filter image by the median to obtain a first result;

multiply the first result by a scalar to obtain a second result;

subtract the scalar from the second result to obtain a third result; and

generate the transformed image by taking an absolute value of the third result.

10. The system of claim 9 , wherein the system is further configured to:

select a sensitivity by iteratively applying a threshold to the transformed image until a sum of cells shown in the image is steady, wherein the threshold is applied at each iteration using a current sensitivity, wherein the sum of cells in the image is determined to be steady when the sum of cells remains within a threshold of an initial sum of cells after a predetermined period of time, wherein the selected sensitivity is the current sensitivity being used when the sum of cells shown in the image is determined to be steady; and

generate a processed image based on the transformed image and the selected sensitivity.

11. The system of claim 10 , wherein the system is further configured to:

determine a current threshold value for the threshold based on the current sensitivity and a focus value, wherein the threshold is applied using the current threshold value, wherein the focus value represents a degree of focus and is determined based on the raw image.

12. The system of claim 9 , wherein the plurality of cells is disposed on a plate having a first side and a second side, wherein the system is further configured to:

filter at least one false positive object from the transformed image, wherein filtering the at least one false positive object further comprises calculating a jitter for each of the first side and the second side, wherein each false positive object is an object on the first side when the jitter calculated for the first side is less than the jitter calculated for the second side.

13. The system of claim 10 , wherein the processed image is a first processed image of a plurality of processed images, wherein each of the plurality of processed images shows a plate on which a plurality of cells is disposed, wherein the system is further configured to:

detect the plurality of cells in each of the plurality of processed images; and

determine a degree of cell migration at each of a plurality of times based on the detected plurality of cells in each of the plurality of processed images, wherein each of the plurality of times corresponds to a respective processed image of the plurality of processed images.

14. The system of claim 13 , wherein the plate has a first side and a second side, wherein the system is further configured to:

compare a number of cells on the first side to a number of cells on the second side based on the corresponding processed image; and

determine a value representing the degree of cell migration at the time based on the comparison.

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

determine at least one morphological measure for each of the plurality of processed images based on the detected plurality of cells for the first processed image, wherein the at least one morphological measure includes at least one of: circularity, ratio between minor and major axes, area to convex area ratio, and area.

16. A method for processing microscopic images, comprising:

selecting a sensitivity by iteratively applying a threshold to a first image until a sum of cells shown in the image is steady, wherein the threshold is applied at each iteration using a current sensitivity, wherein the sum of cells in the image is determined to be steady when the sum of cells remains within a threshold of an initial sum of cells after a predetermined period of time, wherein the selected sensitivity is the current sensitivity being used when the sum of cells shown in the image is determined to be steady; and

generating a second image using the selected sensitivity, wherein the second image is a processed image.

17. The method of claim 16 , wherein the image is a transformed image, wherein applying the threshold to the image at each iteration further comprises:

determining a current threshold value for the threshold based on the current sensitivity and a focus value, wherein the threshold is applied using the current threshold value, wherein the focus value represents a degree of focus of a raw image, wherein the transformed image is generated based on the raw image.

18. The method of claim 17 , further comprising:

generating a smoothed image for the raw image by applying a smoothing filter to the raw image, wherein the raw image shows a plurality of cells and a background;

generating a high pass filter image by dividing the raw image by the smoothed image; and

transforming the high pass filter image into the transformed image by augmenting a spatial frequency of the plurality of cells shown in the high pass filter image with respect to the background.

19. A method for processing microscopic images, comprising:

generating a smoothed image for a raw image by applying a smoothing filter to the raw image, wherein the raw image shows a plurality of cells and a background;

generating a high pass filter image by dividing the raw image by the smoothed image;

transforming the high pass filter image into a transformed image by augmenting a spatial frequency of the plurality of cells shown in the high pass filter image with respect to the background;

selecting a sensitivity by iteratively applying a threshold to the transformed image until a sum of cells shown in the image is steady, wherein the threshold is applied at each iteration using a current sensitivity, wherein the sum of cells in the image is determined to be steady when the sum of cells remains within a threshold of an initial sum of cells after a predetermined period of time, wherein the selected sensitivity is the current sensitivity being used when the sum of cells shown in the image is determined to be steady; and

generating a processed image based on the transformed image and the selected sensitivity.

20. A method for processing microscopic images, comprising:

generating a smoothed image for a raw image by applying a smoothing filter to the raw image, wherein the raw image shows a plurality of cells and a background;

generating a high pass filter image by dividing the raw image by the smoothed image; and

transforming the high pass filter image into a transformed image by augmenting a spatial frequency of the plurality of cells shown in the high pass filter image with respect to the background, wherein the plurality of cells is disposed on a plate having a first side and a second side, further comprising:

filtering at least one false positive object from the transformed image, wherein filtering the at least one false positive object further comprises calculating a jitter for each of the first side and the second side, wherein each false positive object is an object on the first side when the jitter calculated for the first side is less than the jitter calculated for the second side.

21. A system for processing images, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

generate a smoothed image for a raw image by applying a smoothing filter to the raw image, wherein the raw image shows a plurality of cells and a background;

generate a high pass filter image by dividing the raw image by the smoothed image;

transform the high pass filter image into a transformed image by augmenting a spatial frequency of the plurality of cells shown in the high pass filter image with respect to the background;

select a sensitivity by iteratively applying a threshold to the transformed image until a sum of cells shown in the image is steady, wherein the threshold is applied at each iteration using a current sensitivity, wherein the sum of cells in the image is determined to be steady when the sum of cells remains within a threshold of an initial sum of cells after a predetermined period of time, wherein the selected sensitivity is the current sensitivity being used when the sum of cells shown in the image is determined to be steady; and

generate a processed image based on the transformed image and the selected sensitivity.

22. A system for processing images, comprising:

a processing circuitry; and

a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

generate a smoothed image for a raw image by applying a smoothing filter to the raw image, wherein the raw image shows a plurality of cells and a background;

generate a high pass filter image by dividing the raw image by the smoothed image; and

transform the high pass filter image into a transformed image by augmenting a spatial frequency of the plurality of cells shown in the high pass filter image with respect to the background, wherein the plurality of cells is disposed on a plate having a first side and a second side, wherein the system is further configured to:

filter at least one false positive object from the transformed image, wherein filtering the at least one false positive object further comprises calculating a jitter for each of the first side and the second side, wherein each false positive object is an object on the first side when the jitter calculated for the first side is less than the jitter calculated for the second side.