In images of the corneal endothelium (CE) acquired by specular microscopy, endothelial cells are commonlyonly visible in a part of the image due to varying contrast, mainly caused by challenging imaging conditionsas a result of a strongly curved endothelium. In order to estimate the morphometric parameters of the cornealendothelium, the analyses need to be restricted to trustworthy regions - the region of interest (ROI) - whereindividual cells are discernible. We developed an automatic method to find the ROI by Dense U-nets, a denselyconnected 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 forautomatic biomarker extraction is vital. By using edge images as input, which can be estimated after retrainingthe same network, Dense U-net detected the trustworthy areas with an accuracy of 98.94% and an area under theROC curve (AUC) of 0.998, without being affected by the class imbalance (9:1 in our dataset). After applyingthe estimated ROI to the edge images, the mean absolute percentage error (MAPE) in the estimated endothelialparameters was 0.80% for ECD, 3.60% for CV, and 2.55% for HEX.
展开▼
