System and device for characterizing cells

1. A diagnostic device comprising:

a microscope configured to obtain image data on a plurality of cells;

a computing device configured to:

receive the image data;

identify at least a portion of each of the plurality of cells based on the received image data;

determine at least one of a value of a morphological parameter for each identified at least a portion of the plurality of cells or a relative organization among the identified at least a portion of the plurality of cells; and

calculate statistics for the plurality of cells based on the at least one of the determined values of the morphological parameter or the determined relative organization, the statistics including information suitable for distinguishing metastatic cells from non-metastatic cells; and

an output device configured to output the statistics for diagnosis,

wherein said identifying the at least a portion of each of the plurality of cells comprises:

normalizing the image data;

segmenting nuclei of the plurality of cells in the normalized image data; and

identifying the at least a portion of each of the of the plurality of cells based on the segmented nuclei, and

wherein said segmenting nuclei comprises:

obtaining Gaussian intensity image data of the normalized image data;

obtaining averaged intensity image data of the normalized image data;

obtaining nuclear intensity image data based on the difference between the Gaussian intensity image data and the averaged intensity image data; and

segmenting nuclei based on the nuclear intensity image data.

2. The diagnostic device of claim 1 , wherein normalizing the image comprises:

obtaining dark image data from the microscope;

obtaining reference illuminated image data from the microscope;

calibrating the image data of the plurality of cells based on the difference between intensities in the image data of the plurality of cells and the dark image data and the difference between intensities in the dark image data and the reference illuminated image data.

3. The diagnostic device of claim 1 , further comprising segmenting cell boundaries based on watershed segmentation.

4. The diagnostic device of claim 1 , wherein said determining the value of the morphological parameter comprises:

transforming a two-dimensional boundary of the cell and a nucleus of the cell into a one-dimensional curve.

5. The diagnostic device of claim 1 , wherein said identifying at least a portion of each of the plurality of cells comprises:

obtaining a total intensity of the plurality of cells in the image data;

obtaining an estimate of average intensity across a cell cycle of the plurality of cells;

obtaining a number of cells in the plurality of cells based on the total intensity and the estimate of average intensity; and

identifying the cells based on the number of cells.

6. A diagnostic device comprising:

a microscope configured to obtain image data on a plurality of cells;

a computing device configured to:

receive the image data;

identify at least a portion of each of the plurality of cells based on the received image data;

determine at least one of a value of a morphological parameter for each identified at least a portion of the plurality of cells or a relative organization among the identified at least a portion of the plurality of cells; and

calculate statistics for the plurality of cells based on the at least one of the determined values of the morphological parameter or the determined relative organization, the statistics including information suitable for distinguishing metastatic cells from non-metastatic cells; and

an output device configured to output the statistics for diagnosis,

wherein said identifying the at least a portion of each of the plurality of cells comprises:

normalizing the image data;

segmenting nuclei and cell boundaries of the plurality of cells in the normalized image data; and

identifying the at least a portion of each of the of the plurality of cells based on the segmented nuclei and the segmented cell boundaries, and

wherein said segmenting cell boundaries comprises:

obtaining averaged image data of the normalized image data;

obtaining an average background intensity of the averaged image data;

obtaining a noise in background intensity magnitude;

filtering the normalized image data based on the average background intensity and the noise in background intensity magnitude; and

segmenting cell boundaries based on the filtered normalized image data.

7. The diagnostic device of claim 6 , wherein the image data of the plurality of cells comprises first fluorescence channel data and second fluorescence channel data,

wherein said segmenting nuclei of the cells in the normalized image data is based on the first fluorescence channel data,

wherein said segmenting cell boundaries in the normalized image data is based on the second fluorescence channel data.

8. A method of characterizing a plurality of cells comprising:

receiving image data of a plurality of cells;

identifying at least a portion of each of the plurality of cells in the received image data;

determining at least one of a value of a morphological parameter for each identified at least a portion of each of the plurality of cells or a relative organization among the identified at least a portion of each of the plurality of cells;

calculating statistics for the plurality of cells based on the at least one of the determined values of the morphological parameter or the determined relative organization, the statistics including information suitable for distinguishing metastatic cells from non-metastatic cells; and

outputting the statistics for diagnosis,

wherein identifying the cell comprises:

normalizing the image data;

segmenting nuclei of the plurality of cells in the normalized image data; and

identifying the at least a portion of each of the plurality of cells based on the segmented nuclei, and

wherein said segmenting nuclei comprises:

obtaining Gaussian intensity image data of the normalized image data;

obtaining averaged intensity image data of the normalized image data;

obtaining nuclear intensity image data based on the difference between the Gaussian intensity image data and the averaged intensity image data; and

segmenting nuclei based on the nuclear intensity image data.

9. The method of claim 8 , wherein normalizing the image comprises:

obtaining dark image data from the microscope;

obtaining reference illuminated image data from the microscope;

calibrating the image data of the plurality of cells based on the difference between intensities in the image data of the plurality of cells and the dark image data and the difference between intensities in the dark image data and the reference illuminated image data.

10. The method of claim 8 , wherein calculating a morphological parameter for the identified cell comprises:

transforming a two-dimensional boundary of the cell and a nucleus of the cell into a one-dimensional curve.

11. The method of claim 8 , wherein identifying the plurality of cells comprises:

obtaining a total intensity of the plurality of cells in the image data;

obtaining an estimate of average intensity across a cell cycle of the plurality of cells;

obtaining a number of cells in the plurality of cells based on the total intensity and the estimate of average intensity; and

identifying the cells based on the number of cells.

12. A method of characterizing a plurality of cells comprising:

receiving image data of a plurality of cells;

identifying at least a portion of each of the plurality of cells in the received image data;

determining at least one of a value of a morphological parameter for each identified at least a portion of each of the plurality of cells or a relative organization among the identified at least a portion of each of the plurality of cells;

calculating statistics for the plurality of cells based on the at least one of the determined values of the morphological parameter or the determined relative organization, the statistics including information suitable for distinguishing metastatic cells from non-metastatic cells; and

outputting the statistics for diagnosis,

wherein identifying the cell comprises:

normalizing the image data;

segmenting nuclei of the plurality of cells in the normalized image data; and

identifying the at least a portion of each of the plurality of cells based on the segmented nuclei,

further comprising:

segmenting cell boundaries of the plurality of cells in the normalized image data; and

identifying the plurality of cells based on the segmented nuclei and the segmented cell boundaries,

further comprising:

segmenting cell boundaries of the plurality of cells in the normalized image data,

wherein identifying the at least a portion of each of the plurality of cells is based on the segmented nuclei and the segmented cell boundaries, and

wherein said segmenting cell boundaries comprises:

obtaining averaged image data of the normalized image data;

obtaining an average background intensity of the averaged image data;

obtaining a noise in background intensity magnitude;

filtering the normalized image data based on the average background intensity and the noise in background intensity magnitude; and

segmenting cell boundaries based on the filtered normalized image data.

13. The method of claim 12 , wherein the image data of the plurality of cells comprises first fluorescence channel data and second fluorescence channel data,

wherein said segmenting nuclei of the cells in the normalized image data is based on the first fluorescence channel data,

wherein said segmenting cell boundaries in the normalized image data is based on the second fluorescence channel data.