Deep-learning based structure reconstruction method and apparatus

1. A method for structure simulation for super-resolution fluorescence microscopy, the method comprising:

receiving a first image having a first resolution, which is indicative of a distribution of fluorophores;

applying a Markov model to the fluorophores to switch an emission state of the fluorophores, wherein the emission state is one of activated, inactivated, or bleached;

generating a plurality of second images, having the first resolution, based on the first image and the Markov model;

adding DC background to the plurality of second images to generate a plurality of third images, having the first resolution;

downsampling the plurality of third images to obtain a plurality of fourth images, which have a second resolution, lower than the first resolution; and

generating a time-series, low-resolution images by adding noise to the plurality of fourth images,

wherein the time-series, low-resolution images have the second resolution.

2. The method of claim 1 , wherein the step of applying a Markov model uses experimentally calibrated parameters.

3. The method of claim 2 , wherein the experimentally calibrated parameters describe a fluorescent protein.

4. The method of claim 3 , wherein a first parameter of the experimentally calibrated parameters is a switching probability between two of three possible states.

5. The method of claim 4 , wherein the switching probabilities between the three possible states are known.

6. The method of claim 3 , wherein a second parameter of the experimentally calibrated parameters is a point spread function of a fluorophore.

7. The method of claim 1 , wherein the second resolution is 8 times smaller than the first resolution.

8. A computing device for simulating a structure for super-resolution fluorescence microscopy, the computing device comprising:

an interface for receiving a first image having a first resolution, which is indicative of a distribution of fluorophores; and

a processor connected to the interface and configured to,

apply a Markov model to the fluorophores to switch an emission state of the fluorophores, wherein the emission state is one of activated, inactivated, or bleached;

generate a plurality of second images, having the first resolution, based on the first image and the Markov model;

add DC background to the plurality of second images to generate a plurality of third images, having the first resolution;

downsample the plurality of third images to obtain a plurality of fourth images, which have a second resolution, lower than the first resolution; and

generate a time-series, low-resolution images by adding noise to the plurality of fourth images,

wherein the time-series, low-resolution images have the second resolution.

9. The device of claim 8 , wherein the Markov model uses experimentally calibrated parameters.

10. The device of claim 9 , wherein the experimentally calibrated parameters describe a fluorescent protein,

wherein a first parameter of the experimentally calibrated parameters is a switching probability between two of three possible states, and

wherein a second parameter of the experimentally calibrated parameters is a point spread function of a fluorophore.