Corneal Endothelial Cell Segmentation by Classifier-driven Merging of Oversegmented Images

Vigueras Guillén, J.P.; Andrinopoulou, Eleni Rosalina; Engel, Angela; Lemij, Hans G.; van Rooij, J.; Vermeer, K.A.; van Vliet, L.J.

doi:10.1109/TMI.2018.2841910

Corneal Endothelial Cell Segmentation by Classifier-driven Merging of Oversegmented Images

Title

Corneal Endothelial Cell Segmentation by Classifier-driven Merging of Oversegmented Images

Author

Vigueras Guillén, J.P. (TU Delft ImPhys/Quantitative Imaging; Rotterdam Ophthalmic Institute)
Andrinopoulou, Eleni Rosalina (Erasmus MC)
Engel, Angela (Rotterdam Ophthalmic Institute)
Lemij, Hans G. (Rotterdam Eye Hospital)
van Rooij, J. (Rotterdam Eye Hospital)
Vermeer, K.A. (TU Delft ImPhys/Quantitative Imaging; Rotterdam Ophthalmic Institute)
van Vliet, L.J. (TU Delft ImPhys/Quantitative Imaging; TU Delft Applied Sciences)

Faculty

Applied Sciences

Date

2018

Abstract

Corneal endothelium images obtained by in vivo specular microscopy provide important information to assess the health status of the cornea. Estimation of clinical parameters, such as cell density, polymegethism, and pleomorphism, requires accurate cell segmentation. State-of-the-art techniques to automatically segment the endothelium are error-prone when applied to images with low contrast and/or large variation in cell size. Here, we propose an automatic method to segment the endothelium. Starting with an oversegmented image comprised of superpixels obtained from a stochastic watershed segmentation, the proposed method uses intensity and shape information of the superpixels to identify and merge those that constitute a cell, using Support Vector Machines. We evaluated the automatic segmentation on a dataset of in vivo specular microscopy images (Topcon SP-1P), obtaining 95.8merged cells and 2.0the parameter estimation against the results of the vendor’s builtin software, obtaining a statistically significant better precision in all parameters and a similar or better accuracy. The parameter estimation was also evaluated on three other datasets from different imaging modalities (confocal microscopy, phasecontrast microscopy, and fluorescence confocal microscopy) and tissue types (ex vivo corneal endothelium and retinal pigment epithelium). In comparison with the estimates of the datasets’ authors, we achieved statistically significant better accuracy and precision in all parameters except pleomorphism, where a similar accuracy and precision were obtained.

Subject

confocal microscopy
Cornea
Image segmentation
In vivo
Merging
merging superpixels
Microscopy
Optical microscopy
Specular microscopy
stochastic watershed
Support vector machines
support vector machines