Annotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation

Optical coherence tomography (OCT) images of the retina provide a structural representation and give an insight into the pathological changes present in age-related macular degeneration (AMD). Due to the three-dimensionality and complexity of the images, manual analysis of pathological features is d...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Martina Melinščak, Marin Radmilović, Zoran Vatavuk, Sven Lončarić
Formato:	article
Lenguaje:	EN
Publicado:	Taylor & Francis Group 2021
Materias:	annotated retinal oct images images database automatic image segmentation deep learning age-related macular degeneration Control engineering systems. Automatic machinery (General) TJ212-225 Automation T59.5
Acceso en línea:	https://doaj.org/article/b97b81ffaada4b5e953a4a150fa3c0df
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b97b81ffaada4b5e953a4a150fa3c0df
record_format	dspace
spelling	oai:doaj.org-article:b97b81ffaada4b5e953a4a150fa3c0df2021-11-04T15:00:41ZAnnotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation0005-11441848-338010.1080/00051144.2021.1973298https://doaj.org/article/b97b81ffaada4b5e953a4a150fa3c0df2021-10-01T00:00:00Zhttp://dx.doi.org/10.1080/00051144.2021.1973298https://doaj.org/toc/0005-1144https://doaj.org/toc/1848-3380Optical coherence tomography (OCT) images of the retina provide a structural representation and give an insight into the pathological changes present in age-related macular degeneration (AMD). Due to the three-dimensionality and complexity of the images, manual analysis of pathological features is difficult, time-consuming, and prone to subjectivity. Computer analysis of 3D OCT images is necessary to enable automated quantitative measuring of the features, objectively and repeatedly. As supervised and semi-supervised learning-based automatic segmentation depends on the training data and quality of annotations, we have created a new database of annotated retinal OCT images – the AROI database. It consists of 1136 images with annotations for pathological changes (fluid accumulation and related findings) and basic structures (layers) in patients with AMD. Inter- and intra-observer errors have been calculated in order to enable the validation of developed algorithms in relation to human variability. Also, we have performed the automatic segmentation with standard U-net architecture and two state-of-the-art architectures for medical image segmentation to set a baseline for further algorithm development and to get insight into challenges for automatic segmentation. To facilitate and encourage further research in the field, we have made the AROI database openly available.Martina MelinščakMarin RadmilovićZoran VatavukSven LončarićTaylor & Francis Grouparticleannotated retinal oct imagesimages databaseautomatic image segmentationdeep learningage-related macular degenerationControl engineering systems. Automatic machinery (General)TJ212-225AutomationT59.5ENAutomatika, Vol 62, Iss 3-4, Pp 375-385 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	annotated retinal oct images images database automatic image segmentation deep learning age-related macular degeneration Control engineering systems. Automatic machinery (General) TJ212-225 Automation T59.5
spellingShingle	annotated retinal oct images images database automatic image segmentation deep learning age-related macular degeneration Control engineering systems. Automatic machinery (General) TJ212-225 Automation T59.5 Martina Melinščak Marin Radmilović Zoran Vatavuk Sven Lončarić Annotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation
description	Optical coherence tomography (OCT) images of the retina provide a structural representation and give an insight into the pathological changes present in age-related macular degeneration (AMD). Due to the three-dimensionality and complexity of the images, manual analysis of pathological features is difficult, time-consuming, and prone to subjectivity. Computer analysis of 3D OCT images is necessary to enable automated quantitative measuring of the features, objectively and repeatedly. As supervised and semi-supervised learning-based automatic segmentation depends on the training data and quality of annotations, we have created a new database of annotated retinal OCT images – the AROI database. It consists of 1136 images with annotations for pathological changes (fluid accumulation and related findings) and basic structures (layers) in patients with AMD. Inter- and intra-observer errors have been calculated in order to enable the validation of developed algorithms in relation to human variability. Also, we have performed the automatic segmentation with standard U-net architecture and two state-of-the-art architectures for medical image segmentation to set a baseline for further algorithm development and to get insight into challenges for automatic segmentation. To facilitate and encourage further research in the field, we have made the AROI database openly available.
format	article
author	Martina Melinščak Marin Radmilović Zoran Vatavuk Sven Lončarić
author_facet	Martina Melinščak Marin Radmilović Zoran Vatavuk Sven Lončarić
author_sort	Martina Melinščak
title	Annotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation
title_short	Annotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation
title_full	Annotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation
title_fullStr	Annotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation
title_full_unstemmed	Annotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation
title_sort	annotated retinal optical coherence tomography images (aroi) database for joint retinal layer and fluid segmentation
publisher	Taylor & Francis Group
publishDate	2021
url	https://doaj.org/article/b97b81ffaada4b5e953a4a150fa3c0df
work_keys_str_mv	AT martinamelinscak annotatedretinalopticalcoherencetomographyimagesaroidatabaseforjointretinallayerandfluidsegmentation AT marinradmilovic annotatedretinalopticalcoherencetomographyimagesaroidatabaseforjointretinallayerandfluidsegmentation AT zoranvatavuk annotatedretinalopticalcoherencetomographyimagesaroidatabaseforjointretinallayerandfluidsegmentation AT svenloncaric annotatedretinalopticalcoherencetomographyimagesaroidatabaseforjointretinallayerandfluidsegmentation
_version_	1718444794705870848

Annotated retinal optical coherence tomography images (AROI) database for joint retinal layer and fluid segmentation

Ejemplares similares