Automated methods to count corneal subbasal nerves
The present invention is directed to a software algorithm that measures the number of corneal nerve fibers in images captured by microscopy including images from patients obtained by in vivo corneal confocal microscopy, a noninvasive technique. The present invention solves a complicated segmentation problem, by exploiting the piece wise linear nature of the nerve fibers—i.e., the nerves are made up of a lot of straight line segments. The image is split into sub-regions, where each sub-region contains nerves mostly running in the same, straight direction. Having the nerves all in straight-lines within a single 2d image region dramatically simplifies the segmentation problem. The image intensities are summed in the direction of the nerves to reduce the 2d representation to a 1d signal having pronounced peaks where the nerves are located.
1. A non-transitory computer readable medium programmed with steps comprising:
receiving image data related to a region of interest of the subject;
dividing the image data into sub-regions, wherein each sub-region is defined by having nerve fibers running in approximately a same direction;
summing image intensities in the same direction of the nerve fibers for the sub-region;
reducing a two-dimensional representation to a one-dimensional signal having peaks where the nerve fibers are located; and
determining a nerve fiber count based on the peaks of the one-dimensional signal.
2. The non-transitory computer readable medium of claim 1 , further comprising receiving image data related to a cornea of the subject.
3. The non-transitory computer readable medium of claim 1 , further comprising receiving image data from in vivo corneal confocal microscopy.
4. The non-transitory computer readable medium of claim 1 , further comprising receiving image data from a whole mount specimen.
5. The non-transitory computer readable medium of claim 4 , further comprising the whole mount specimen being stained with βIII tubulin.
6. The non-transitory computer readable medium of claim 1 , further comprising comparing the nerve fiber count to a previous nerve fiber count or a normal nerve fiber count to diagnose peripheral neuropathy.
7. The non-transitory computer readable medium of claim 1 , further comprising comparing the nerve fiber count to a previous nerve fiber count in order to diagnose onset of or changes in extent of peripheral neuropathy.
8. The non-transitory computer readable medium of claim 1 , further comprising receiving in vivo image data from a confocal microscope.
9. The non-transitory computer readable medium of claim 1 , further comprising deriving measures of length, tortuosity, branching, and density to diagnose peripheral neuropathy.
10. A system for diagnosing peripheral neuropathy in a subject comprising:
a confocal microscope configured for obtaining image data of a region of interest of a cornea of the subject;
a non-transitory computer readable medium programmed for:
receiving the image data of the region of interest of the cornea of the subject;
dividing the image data into sub-regions, wherein each sub-region is defined by having nerve fibers running in approximately a same direction;
summing image intensities in the same direction of the nerve fibers for the sub-region;
reducing a two-dimensional representation to a one-dimensional signal having peaks where the nerve fibers are located; and
determining a nerve fiber count based on the peaks of the one-dimensional signal.
11. The system of claim 10 , further comprising comparing the nerve fiber count to a previous nerve fiber count or a normal nerve fiber count to diagnose peripheral neuropathy.
12. The system of claim 10 , further comprising comparing the nerve fiber count to a previous nerve fiber count in order to diagnose onset of or changes in extent of peripheral neuropathy.
13. The system of claim 10 , further comprising receiving in vivo image data from a confocal microscope.
14. The system of claim 10 , further comprising deriving measures of length, tortuosity, branching, and density to diagnose peripheral neuropathy.
15. The system of claim 10 , further comprising a computing device.
16. The system of claim 10 , further comprising the computing device being networked with the confocal microscope in order to receive the image data.
17. The system of claim 10 , further comprising a database for storing the image data.
18. The system of claim 17 , wherein a computing device is networked with the database for receiving the image data.
19. The system of claim 17 , wherein image data stored on the data base is analyzed to determine baseline never counts that indicate peripheral neuropathy.
20. The system of claim 10 , further comprising assessing peripheral neuropathy based on the nerve fiber count.