Influence of applied corneal endothelium image segmentation techniques on the clinical parameters.

The corneal endothelium state is verified on the basis of an in vivo specular microscope image from which the shape and density of cells are exploited for data description. Due to the relatively low image quality resulting from a high magnification of the living, non-stained tissue, both manual and automatic analysis of the data is a challenging task. Although, many automatic or semi-automatic solutions have already been introduced, all of them are prone to inaccuracy. This work presents a comparison of four methods (fully-automated or semi-automated) for endothelial cell segmentation, all of which represent a different approach to cell segmentation; fast robust stochastic watershed (FRSW), KH method, active contours solution (SNAKE), and TOPCON ImageNET. Moreover, an improvement framework is introduced which aims to unify precise cell border location in images pre-processed with differing techniques. Finally, the influence of the selected methods on clinical parameters is examined, both with and without the improvement framework application. The experiments revealed that although the image segmentation approaches differ, the measures calculated for clinical parameters are in high accordance when CV (coefficient of variation), and CVSL (coefficient of variation of cell sides length) are considered. Higher variation was noticed for the H (hexagonality) metric. Utilisation of the improvement framework assured better repeatability of precise endothelial cell border location between the methods while diminishing the dispersion of clinical parameter values calculated for such images. Finally, it was proven statistically that the image processing method applied for endothelial cell analysis does not influence the ability to differentiate between the images using medical parameters.

Fully automatic evaluation of the corneal endothelium from in vivo confocal microscopy.

BACKGROUND: Manual and semi-automatic analyses of images, acquired in vivo by confocal microscopy, are often used to determine the quality of corneal endothelium in the human eye. These procedures are highly time consuming. Here, we present two fully automatic methods to analyze and quantify corneal endothelium imaged by in vivo white light slit-scanning confocal microscopy. METHODS: In the first approach, endothelial cell density is estimated with the help of spatial frequency analysis. We evaluate published methods, and propose a new, parameter-free method. In the second approach, based on the stochastic watershed, cells are automatically segmented and the result is used to estimate cell density, polymegathism (cell size variability) and pleomorphism (cell shape variation). We show how to determine optimal values for the three parameters of this algorithm, and compare its results to a semi-automatic delineation by a trained observer. RESULTS: The frequency analysis method proposed here is more precise than any published method. The segmentation method outperforms the fully automatic method in the NAVIS software (Nidek Technologies Srl, Padova, Italy), which significantly overestimates the number of cells for cell densities below approximately 1200 mm(-2), as well as previously published methods. CONCLUSIONS: The methods presented here provide a significant improvement over the state of the art, and make in vivo, automated assessment of corneal endothelium more accessible. The segmentation method proposed paves the way to many possible new morphometric parameters, which can quickly and precisely be determined from the segmented image.

Spatial pattern of glaucomatous visual field loss obtained with regionally condensed stimulus arrangements.

PURPOSE: To assess the spatial distribution of glaucomatous visual field defects (VFDs) obtained with regionally condensed stimulus arrangements. METHODS: Sixty-three eyes of 63 glaucoma subjects were examined with threshold-estimating automated static perimetry (full threshold 4-2-1 dB strategy with at least three reversals) on an automatic campimeter or a full-field perimeter. Stimuli were added by the examiner to regionally enhance spatial resolution in regions that were suspicious for a glaucomatous VFD. These regions were characterized by contiguous local VFDs, attributable to the retinal nerve fiber bundle course according to the impression of the examiner. The added stimulus locations were subsets of a predefined, dense perimetric grid. All VFD locations with P < 0.05 (total deviation plots) were assessed by superimposing the visual field records of all participants. RESULTS: Glaucomatous VFD loss occurred more frequently in the upper than in the lower hemifield, with a typical retinal nerve fiber-related pattern and a preference of the nasal step region. More than 50% of the eyes with predominantly mild to moderate glaucomatous field loss showed defective locations in the immediate superior paracentral region within an eccentricity of 3°. CONCLUSIONS: Conventional thresholding white-on-white perimetry with regionally enhanced spatial resolution reveals that glaucomatous visual field loss affects the immediate paracentral area, especially the upper hemifield, in many eyes with only mild to moderate glaucomatous visual field loss. Detailed knowledge about the spatial pattern and the local frequency distribution of glaucomatous VFDs is an essential prerequisite for creating regionally condensed stimulus arrangements for adequate detection and follow-up of functional glaucomatous damage.

Specification of progression in glaucomatous visual field loss, applying locally condensed stimulus arrangements.

PURPOSE: The goal of this work was to (i) determine patterns of progression in glaucomatous visual field loss, (ii) compare the detection rate of progression between locally condensed stimulus arrangements and conventional 6 degrees x 6 degrees grid, and (iii) assess the individual frequency distribution of test locations exhibiting a local event (i.e., an abrupt local deterioration of differential luminance sensitivity (DLS) by more than -10 dB between any two examinations). METHODS: The visual function of 41 glaucomatous eyes of 41 patients (16 females, 25 males, 37 to 75 years old) was examined with automated static perimetry (Tuebingen Computer Campimeter or Octopus 101-Perimeter). Stimuli were added to locally enhance the spatial resolution in suspicious regions of the visual field. The minimum follow-up was four subsequent sessions with a minimum of 2-month (median 6-month) intervals between each session. Progression was identified using a modified pointwise linear regression (PLR) method and a modified Katz criterion. The presence of events was assessed in all progressive visual fields. RESULTS: Eleven eyes (27%) showed progression over the study period (median 2.5 years, range 1.3-8.6 years). Six (55%) of these had combined progression in depth and size and five eyes (45%) progressed in depth only. Progression in size conformed always to the nerve fiber course. Seven out of 11 (64%) of the progressive scotomata detected by spatially condensed grids would have been missed by the conventional 6 degrees x 6 degrees grid. At least one event occurred in 64% of all progressive eyes. Five of 11 (46%) progressive eyes showed a cluster of events. CONCLUSIONS: The most common pattern of progression in glaucomatous visual fields is combined progression in depth and size of an existing scotoma. Applying individually condensed test grids remarkably enhances the detection rate of glaucomatous visual field deterioration (at the expense of an increased examination time) compared to conventional stimulus arrangements.