Corneal guttae, which are the abnormal growth of extracellular matrix in the corneal endothelium, are observed in specular images as black droplets that occlude the endothelial cells. To estimate the corneal parameters (endothelial cell density [ECD], coefficient of variation [CV], and hexagonality [HEX]), we propose a new deep learning method that includes a novel attention mechanism (named fNLA), which helps to infer the cell edges in the occluded areas. The approach first derives the cell edges, then infers the well-detected cells, and finally employs a postprocessing method to fix mistakes. This results in a binary segmentation from which the corneal parameters are estimated. We analyzed 1203 images (500 contained guttae) obtained with a Topcon SP-1P microscope. To generate the ground truth, we performed manual segmentation in all images. Several networks were evaluated (UNet, ResUNeXt, DenseUNets, UNet++, etc.) and we found that DenseUNets with fNLA provided the lowest error: a mean absolute error of 23.16 [cells/mm²] in ECD, 1.28 [%] in CV, and 3.13 [%] in HEX. Compared with Topcon’s built-in software, our error was 3–6 times smaller. Overall, our approach handled notably well the cells affected by guttae, detecting cell edges partially occluded by small guttae and discarding large areas covered by extensive guttae.

Purpose: To present a fully automatic method to estimate the corneal endothelium parameters from specular microscopy images and to use it to study a one-year follow-up after ultrathin Descemet stripping automated endothelial keratoplasty. Methods: We analyzed 383 post ultrathin Descemet stripping automated endothelial keratoplasty images from 41 eyes acquired with a Topcon SP-1P specular microscope at 1, 3, 6, and 12 months after surgery. The estimated parameters were endothelial cell density (ECD), coefficient of variation (CV), and hexagonality (HEX). Manual segmentation was performed in all images. Results: Our method provided an estimate for ECD, CV, and HEX in 98.4% of the images, whereas Topcon’s software had a success rate of 71.5% for ECD/CV and 30.5% for HEX. For the images with estimates, the percentage error in our method was 2.5% for ECD, 5.7% for CV, and 5.7% for HEX, whereas Topcon’s software provided an error of 7.5% for ECD, 17.5% for CV, and 18.3% for HEX. Our method was significantly better than Topcon’s (P < 0.0001) and was not statistically significantly different from the manual assessments (P > 0.05). At month 12, the subjects presented an average ECD = 1377 ± 483 [cells/mm² ], CV = 26.1 ± 5.7 [%], and HEX = 58.1 ± 7.1 [%]. Conclusions: The proposed method obtains reliable and accurate estimations even in challenging specular images of pathologic corneas. Translational Relevance: CV and HEX, not currently used in the clinic owing to a lack of reliability in automatic methods, are useful biomarkers to analyze the postoperative healing process. Our accurate estimations allow now for their clinical use.

In images of the corneal endothelium (CE) acquired by specular microscopy, endothelial cells are commonly only visible in a part of the image due to varying contrast, mainly caused by challenging imaging conditions as a result of a strongly curved endothelium. In order to estimate the morphometric parameters of the corneal endothelium, the analyses need to be restricted to trustworthy regions - the region of interest (ROI) - where individual cells are discernible. We developed an automatic method to find the ROI by Dense U-nets, a densely connected network of convolutional layers. We tested the method on a heterogeneous dataset of 140 images, which contains a large number of blurred, noisy, and/or out of focus images, where the selection of the ROI for automatic biomarker extraction is vital. By using edge images as input, which can be estimated after retraining the same network, Dense U-net detected the trustworthy areas with an accuracy of 98.94% and an area under the ROC curve (AUC) of 0.998, without being affected by the class imbalance (9:1 in our dataset). After applying the estimated ROI to the edge images, the mean absolute percentage error (MAPE) in the estimated endothelial parameters was 0.80% for ECD, 3.60% for CV, and 2.55% for HEX.

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&#x2019;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&#x2019; authors, we achieved statistically significant better accuracy and precision in all parameters except pleomorphism, where a similar accuracy and precision were obtained.

Clinical parameters related to the corneal endothelium can only be estimated by segmenting endothelial cell images. Specular microscopy is the current standard technique to image the endothelium, but its low SNR make the segmentation a complicated task. Recently, we proposed a method to segment such images by starting with an oversegmented image and merging the superpixels that constitute a cell. Here, we show how our merging method provides better results than optimizing the segmentation itself. Furthermore, our method can provide accurate results despite the degree of the initial oversegmentation, resulting into a precision and recall of 0.91 for the optimal oversegmentation.