Skip to main navigation Skip to search Skip to main content

Automatic segmentation of corneal endothelium images with convolutional neural network

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

A fully-automatic segmentation of corneal endothelial images is addressed in this paper. It can find its application in the medicine removing the burden of manual annotations from the physicians allowing for faster patient diagnosis. The proposed system is based on pre-trained convolutional neural network AlexNet and uses a transfer learning methodology to build a system for delineation of endothelial cells. The training is based on the classification of small patches of an image which represents cell body or cell border class. The validation set proved that 99% correct classification ratio accuracy and F1 score were achieved. Exploiting this network in a system configured for segmentation it proved very good detection of cell bodies and supported by best-fit skeletonization allowed to locate cell borders precisely.

Original languageEnglish
Title of host publicationBeyond Databases, Architectures and Structures. Facing the Challenges of Data Proliferation and Growing Variety - 14th International Conference, BDAS 2018, Held at the 24th IFIP World Computer Congress, WCC 2018, Proceedings
EditorsStanislaw Kozielski, Dariusz Mrozek, Pawel Kasprowski, Bozena Malysiak-Mrozek, Daniel Kostrzewa
PublisherSpringer Verlag
Pages323-333
Number of pages11
ISBN (Print)9783319999869
DOIs
Publication statusPublished - 2018
Event14th International Conference on Beyond Databases, Architectures and Structures, BDAS 2018 Held at the 24th IFIP World Computer Congress, WCC 2018 - Poznan, Poland
Duration: 18 Sept 201820 Sept 2018

Publication series

NameCommunications in Computer and Information Science
Volume928
ISSN (Print)1865-0929

Conference

Conference14th International Conference on Beyond Databases, Architectures and Structures, BDAS 2018 Held at the 24th IFIP World Computer Congress, WCC 2018
Country/TerritoryPoland
CityPoznan
Period18/09/1820/09/18

Keywords

  • Classification
  • Convolutional neural network
  • Corneal endothelium images
  • Segmentation

ASJC Scopus subject areas

  • General Computer Science
  • General Mathematics

Fingerprint

Dive into the research topics of 'Automatic segmentation of corneal endothelium images with convolutional neural network'. Together they form a unique fingerprint.

Cite this