DenseUNets with feedback non-local attention for the segmentation of specular microscopy images of the corneal endothelium with guttae

Juan P. Vigueras-Guillén*, Jeroen van Rooij, Bart T.H. van Dooren, Hans G. Lemij, Esma Islamaj, Lucas J. van Vliet, Koenraad A. Vermeer

*Corresponding author for this work

Research output: Contribution to journalArticleAcademicpeer-review

1 Downloads (Pure)

Abstract

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.

Original languageEnglish
Article number14035
JournalScientific Reports
Volume12
Issue number1
DOIs
Publication statusPublished - 18 Aug 2022

Bibliographical note

Funding Information:
This work was supported by the Dutch Organization for Health Research and Healthcare Innovation (ZonMw, The Hague, The Netherlands) under Grants 842005004 and 842005007, and by the Combined Ophthalmic Research Rotterdam (CORR, Rotterdam, The Netherlands) under grant no. 2.1.0. The authors thank Angela Engel, Caroline Jordaan, and Annemiek Krijnen for their contribution in acquiring the images.

Publisher Copyright:
© 2022, The Author(s).

Fingerprint

Dive into the research topics of 'DenseUNets with feedback non-local attention for the segmentation of specular microscopy images of the corneal endothelium with guttae'. Together they form a unique fingerprint.

Cite this