Estimating cell density in corneal endothelium by means of Fourier analysis

A very important clinical parameter for assessing the quality of explanted corneas in view of their implant is the cell density of corneal endothelium. The problem of its automatic estimation from specimen images obtained from optical microscopy is solved here by analyzing the spatial frequency of the images. A circular band in the Discrete Fourier Transform of the images is shown to contain the information about the cell density. A system for extracting from this spatial frequency information an estimate for the cell density has been developed and a confidence value for this estimate was also obtained. A preliminary clinical evaluation of the proposed technique confirmed its capability of correctly estimating corneal endothelium cell density.

[1]  M. Foracchia,et al.  Cell contour detection in corneal endothelium in-vivo microscopy , 2000, Proceedings of the 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society (Cat. No.00CH37143).

[2]  G. Corkidi,et al.  Automated in vivo and online morphometry of human corneal endothelium , 1993, Medical and Biological Engineering and Computing.

[3]  Kazuyoshi Itoh,et al.  Detection of Cell Membranes in Human Corneal Endothelial Micrograms Using Mathematical Morphology , 1992 .