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.

Original languageEnglish
Title of host publicationProceeedings of SPIE
Subtitle of host publicationMedical Imaging 2019 : Image Processing
EditorsElsa D. Angelini, Elsa D. Angelini, Elsa D. Angelini, Bennett A. Landman
Number of pages12
ISBN (Electronic)978-151062545-7
Publication statusPublished - 2019
EventMedical Imaging 2019: Image Processing - San Diego, United States
Duration: 19 Feb 201921 Feb 2019

Publication series

ISSN (Print)0277-786X


ConferenceMedical Imaging 2019: Image Processing
CountryUnited States
CitySan Diego

    Research areas

  • biomarkers, Dense U-net, fully CNN, segmentation, specular microscopy

ID: 55179508