Systems and methods for cell membrane identification and tracking, and technique automation using the same

1. A system comprising:

at least one processor; and

at least one memory having stored thereon instructions that, when executed by the at least one processor, control the at least one processor to:

receive image data of a sequence of images, and a current image of the sequence of images being after a previous image in the sequence of images, each of the current and previous images including a cell;

filter the current image to remove noise;

iteratively deconvolve the filtered current image to identify edges of the cell within the current image based on determined edges of the cell within the previous image; and

segment the deconvolved current image to determine edges of the cell within the current image.

2. The system of claim 1 , wherein the instructions, when executed by the at least one processor, further control the at least one processor to:

identify, within the current image, a subset of the current image containing the cell, deconvolving being performed only on the identified subset of the current image.

3. The system of claim 1 , wherein the instructions, when executed by the at least one processor, control the at least one processor to iteratively deconvolve the filtered current image by:

determining an estimated edge that minimizes a cost function;

adjusting weights of the cost function based on the estimated edge; and

repeating the determining and adjusting.

4. The system of claim 3 , wherein the cost function comprises a first term corresponding to a predictive error between the current image and an image predicted from the estimated edge, and a second term corresponding to a connectivity determination of the estimated edge within the current image.

5. The system of claim 4 , wherein the adjusted weights of the cost function modify the connectivity determination of the estimated edge within the current image.

6. The system of claim 5 , wherein the determined edges of the cell within the previous image impact the adjusted weights.

7. The system of claim 1 , wherein the instructions, when executed by the at least one processor, control the at least one processor to iteratively deconvolve the filtered current image by:

iteratively estimate an edge that minimizes a cost function utilizing alternating direction method of multipliers (ADMM);

adjusting weights of the cost function based on the estimated edge; and

repeating the determining and adjusting.

8. The system of claim 1 , wherein the instructions, when executed by the at least one processor, further control the at least one processor to output instructions to an articulating arm to position an instrument proximal to the determined edge of the current image.

9. The system of claim 8 , wherein the instrument comprises one or more of:

an electrode;

an injector; and

a manipulation instrument.

10. The system of claim 1 , wherein the instructions, when executed by the at least one processor, further control the at least one processor to:

set the current image as the previous image;

set a next image in the sequence of images as the current image; and

repeat the filtering, iteratively deconvolving, and segmenting.

11. The system of claim 10 , wherein

the sequence of image comprises a live video, and

the edges of the cell within the current image are determined in near real-time.

12. A method comprising:

receiving image data of a sequence of images, and a current image of the sequence of images being after a previous image in the sequence of images, each of the current and previous images including a cell;

filtering the current image to remove noise;

iteratively deconvolving the filtered current image to identify edges of the cell within the current image based on determined edges of the cell within the previous image; and

segmenting the deconvolved current image to determine edges of the cell within the current image.

13. The method of claim 12 further comprising identifying, within the current image, a subset of the current image containing the cell, deconvolving being performed only on the identified subset of the current image.

14. The method of claim 12 further comprising iteratively deconvolving the current image by:

determining an estimated edge that minimizes a cost function;

adjusting weights of the cost function based on the estimated edge; and

repeating the determining and adjusting.

15. The method of claim 14 , wherein the cost function comprises a first term corresponding to a predictive error between the current image and an image predicted from the estimated edge, and a second term corresponding to a connectivity determination of the estimated edge within the current image.

16. The method of claim 15 , wherein

the adjusted weights of the cost function modify the connectivity determination of the estimated edge within the current image, and

the determined edges of the cell within the previous image impact the adjusted weights.

17. The method of claim 12 further comprising deconvolving the filtered current image by:

iteratively estimate an edge that minimizes a cost function utilizing alternating direction method of multipliers (ADMM);

adjusting weights of the cost function based on the estimated edge; and

repeating the determining and adjusting.

18. The method of claim 12 further comprising moving an articulating arm to position an instrument proximal to the determined edge of the current image.

19. The method of claim 12 further comprising:

setting the current image as the previous image;

setting a next image in the sequence of images as the current image; and

repeating the filtering, iteratively deconvolving, and segmenting.

20. The method of claim 19 , wherein

the sequence of image comprises a live video, and

the edges of the cell within the current image are determined in near real-time.