RT Journal Article
A1 Bullet, Julien
A1 Gaujoux, Thomas
A1 Borderie, Vincent
A1 Laroche, Laurent
T1 Automated Segmentation For Corneal Epithelium Cell Images
JF Investigative Ophthalmology & Visual Science
JO Invest. Ophthalmol. Vis. Sci.
YR 2011
VO 52
IS 14
SP 4192
OP 4192
SN 1552-5783
AB Purpose: Corneal epithelium images can be obtained through Heidelberg Retina Tomograph corneal module. Automated analysis of epithelium cells morphology could help clinical and pathological diagnosis. First step toward this analysis is to extract cell borders from an HRT image. We propose an algorithm to automatically perform segmentation of these images (Fig. 1). Methods: Steps of the algorithm include:• A noise reduction through a fast-Fourier-transform (FFT) band pass filter with normalization (pixel values range from 0 to 255).• Image binarization with a median value threshold.• Standard watershed algorithm on distance map is used to separate fused cells (Fig 2).• Voronoi diagram segmentation algorithm gives a final border map (Fig 3). Results: Most cells borders are correctly found. However, a small number of oversegmented small cells are present. Conclusions: Epithelial cell image segmentation can be performed automatically, thus allowing a statistical analysis of cell morphological and pathological characteristics
RD 5/12/2021