Automated corneal endothelium image segmentation in the presence of cornea guttata via convolutional neural networks

Juan S. Sierra, Jesus Pineda, Eduardo Viteri, Daniela Rueda, Beatriz Tibaduiza, Rúben D. Berrospi, Alejandro Tello, Virgilio Galvis, Giovanni Volpe, Mariá S. Millán, Lenny A. Romero, Andrés G. Marrugo

Research output: Book / Book Chapter / ReportResearch Bookspeer-review

9 Scopus citations


Automated cell counting in in-vivo specular microscopy images is challenging, especially in situations where single-cell segmentation methods fail due to pathological conditions. This work aims to obtain reliable cell segmentation from specular microscopy images of both healthy and pathological corneas. We cast the problem of cell segmentation as a supervised multi-class segmentation problem. The goal is to learn a mapping relation between an input specular microscopy image and its labeled counterpart, indicating healthy (cells) and pathological regions (e.g., guttae). We trained a U-net model by extracting 96×96 pixel patches from corneal endothelial cell images and the corresponding manual segmentation by a physician. Encouraging results show that the proposed method can deliver reliable feature segmentation enabling more accurate cell density estimations for assessing the state of the cornea.

Original languageEnglish
Title of host publicationApplications of Machine Learning 2020
EditorsMichael E. Zelinski, Tarek M. Taha, Jonathan Howe, Abdul A. Awwal, Khan M. Iftekharuddin
ISBN (Electronic)9781510638280
StatePublished - 2020
EventApplications of Machine Learning 2020 - Virtual, Online, United States
Duration: 24 Aug 20204 Sep 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X


ConferenceApplications of Machine Learning 2020
Country/TerritoryUnited States
CityVirtual, Online


  • Convolutional neural network
  • Cornea guttata
  • Corneal endothelium
  • Medical image segmentation
  • Specular microscopy
  • U-net


Dive into the research topics of 'Automated corneal endothelium image segmentation in the presence of cornea guttata via convolutional neural networks'. Together they form a unique fingerprint.

Cite this