A1 Journal article (refereed), original research

Active learning of the ground truth for retinal image segmentation


Open Access publication


Publication Details

Authors: Nedoshivina Liubov, Lensu Lasse

Publisher: Optical Society of America: No Paid Open Access

Publication year: 2020

Language: English

Related journal or series: Journal of Optical Technology

Journal name in source: Journal of Optical Technology (A Translation of Opticheskii Zhurnal)

Volume number: 86

Issue number: 11

Start page: 697

End page: 703

Number of pages: 7

ISSN: 1070-9762

JUFO level of this publication: 1

Digital Object Identifier (DOI): http://dx.doi.org/10.1364/JOT.86.000697

Permanent website address: https://www.osapublishing.org/jot/abstract.cfm?uri=jot-86-11-697

Open Access: Open Access publication

Location of the parallel saved publication: http://urn.fi/URN:NBN:fi-fe2020120399200


Abstract

Different diseases can be diagnosed from eye fundus images by medical
experts. Automated diagnosis methods can help medical doctors to
increase the diagnosis accuracy and decrease the time needed. In order
to have a proper dataset for training and evaluating the methods, a
large set of images should be annotated by several experts to form the
ground truth. To enable efficient utilization of the experts’ time,
active learning is studied to accelerate the collection of the ground
truth. Since one of the important steps in retinal image diagnosis is
blood vessel segmentation, the corresponding approaches were studied.
Two approaches were implemented and extended by proposed active learning
methods for selecting the next image to be annotated. The performance
of the methods in the cases of standard implementation and active
learning application was compared for several retinal image databases.


Last updated on 2021-16-03 at 12:47