Morphometry of organ cultured corneal endothelium using Voronoi segmentation

Artificial intelligence for anterior segment diseases: Emerging applications in ophthalmology

With the advancement of computational power, refinement of learning algorithms and architectures, and availability of big data, artificial intelligence (AI) technology, particularly with machine learning and deep learning, is paving the way for 'intelligent' healthcare systems. AI-related research in ophthalmology previously focused on the screening and diagnosis of posterior segment diseases, particularly diabetic retinopathy, age-related macular degeneration and glaucoma. There is now emerging evidence demonstrating the application of AI to the diagnosis and management of a variety of anterior segment conditions. In this review, we provide an overview of AI applications to the anterior segment addressing keratoconus, infectious keratitis, refractive surgery, corneal transplant, adult and paediatric cataracts, angle-closure glaucoma and iris tumour, and highlight important clinical considerations for adoption of AI technologies, potential integration with telemedicine and future directions.

A fully automated cell segmentation and morphometric parameter system for quantifying corneal endothelial cell morphology

BACKGROUND AND OBJECTIVE

Corneal endothelial cell abnormalities may be associated with a number of corneal and systemic diseases. Damage to the endothelial cells can significantly affect corneal transparency by altering hydration of the corneal stroma, which can lead to irreversible endothelial cell pathology requiring corneal transplantation. To date, quantitative analysis of endothelial cell abnormalities has been manually performed by ophthalmologists using time consuming and highly subjective semi-automatic tools, which require an operator interaction. We developed and applied a fully-automated and real-time system, termed the Corneal Endothelium Analysis System (CEAS) for the segmentation and computation of endothelial cells in images of the human cornea obtained by in vivo corneal confocal microscopy.

METHODS

First, a Fast Fourier Transform (FFT) Band-pass filter is applied to reduce noise and enhance the image quality to make the cells more visible. Secondly, endothelial cell boundaries are detected using watershed transformations and Voronoi tessellations to accurately quantify the morphological parameters of the human corneal endothelial cells. The performance of the automated segmentation system was tested against manually traced ground-truth images based on a database consisting of 40 corneal confocal endothelial cell images in terms of segmentation accuracy and obtained clinical features. In addition, the robustness and efficiency of the proposed CEAS system were compared with manually obtained cell densities using a separate database of 40 images from controls (n = 11), obese subjects (n = 16) and patients with diabetes (n = 13).

RESULTS

The Pearson correlation coefficient between automated and manual endothelial cell densities is 0.9 (p < 0.0001) and a Bland-Altman plot shows that 95% of the data are between the 2SD agreement lines.

CONCLUSIONS

We demonstrate the effectiveness and robustness of the CEAS system, and the possibility of utilizing it in a real world clinical setting to enable rapid diagnosis and for patient follow-up, with an execution time of only 6 seconds per image.

Riding the cell jamming boundary: Geometry, topology, and phase of human corneal endothelium

It is important to assess the viability of eye-banked corneas prior to transplantation due to inherent senescence and known loss of endothelial cells during surgical manipulation. Corneal endothelial cells have a complex basal and paracellular shape making them challenging to accurately measure, particularly in oedematous ex vivo tissue. This study used calibrated centroidal Voronoi Diagrams to segment cells in images of these human corneas, in order to characterize endothelial geometry, topology, and phase. Hexagonal cells dominated the endothelia, with most comprised of five different pleomorphs exhibiting self-similar topological coarsening through most of the endothelial cell density range. There was a linear relationship between cell size and shape, though cells with greater than six sides were present in larger proportions than cells with less. Hexagonal cell regularity was stable and largely independent of density. Cell and tissue phase was also examined, using the cell shape index relative to the recently discovered 'cell jamming' phase transition boundary. Images showed fluid endothelia with a range of shape indices spanning the boundary, independent of density but dependent on hexagonal regularity. The cells showed a bimodal distribution centred at the boundary, with the largest proportion of cells on the fluid side. A shoulder at the boundary suggested phase switching via shape transformation across the energy barrier, with cells either side having distinctly different size and shape characteristics. Regular hexagonal cells were closest to the boundary. This study showed the corneal endothelium acts as a glassy viscous foam characterized by well-established physical laws. Endothelial cell death transiently and locally increases cell fluidity, which is subsequently arrested by jamming of the pleomorphically diverse cell collective, via rearrangement and shape change of a small proportion of cells, which become locked in place by their neighbours thereby maintaining structural equilibrium with little energy expenditure.