Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE Models

The performance of a Glaucoma assessment system is highly affected by the number of labelled images used during the training stage. However, labelled images are often scarce or costly to obtain. In this paper, we address the problem of synthesising retinal fundus images by training a Variational Aut...

Descripción completa

Detalles Bibliográficos
Autores: Díaz-Pinto, Andrés Yesid, Xu, Yanwu, Frangi, Alejandro F., Colomer, Adrián|||0000-0002-7616-6029, Naranjo Ornedo, Valeriana|||0000-0002-0181-3412, Morales, Sandra|||0000-0003-0763-1545
Tipo de recurso: capítulo de libro
Fecha de publicación:2019
País:España
Institución:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:riunet.upv.es:10251/124078
Acceso en línea:https://riunet.upv.es/handle/10251/124078
Access Level:acceso abierto
Palabra clave:Medical imaging
Retinal Image Synthesis
Fundus Images
DCGAN
VAE
TEORIA DE LA SEÑAL Y COMUNICACIONES
id ES_a760192c00a3536b1be0c584fb517ee2
oai_identifier_str oai:riunet.upv.es:10251/124078
network_acronym_str ES
network_name_str España
repository_id_str
spelling Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE ModelsDíaz-Pinto, Andrés YesidXu, YanwuFrangi, Alejandro F.Colomer, Adrián|||0000-0002-7616-6029Naranjo Ornedo, Valeriana|||0000-0002-0181-3412Morales, Sandra|||0000-0003-0763-1545Medical imagingRetinal Image SynthesisFundus ImagesDCGANVAETEORIA DE LA SEÑAL Y COMUNICACIONESThe performance of a Glaucoma assessment system is highly affected by the number of labelled images used during the training stage. However, labelled images are often scarce or costly to obtain. In this paper, we address the problem of synthesising retinal fundus images by training a Variational Autoencoder and an adversarial model on 2357 retinal images. The innovation of this approach is in synthesising retinal images without using previous vessel segmentation from a separate method, which makes this system completely independent. The obtained models are image synthesizers capable of generating any amount of cropped retinal images from a simple normal distribution. Furthermore, more images were used for training than any other work in the literature. Synthetic images were qualitatively evaluated by 10 clinical experts and their consistency were estimated by measuring the proportion of pixels corresponding to the anatomical structures around the optic disc. Moreover, we calculated the mean-squared error between the average 2D-histogram of synthetic and real images, obtaining a small difference of 3e-4. Further analysis of the latent space and cup size of the images was performed by measuring the Cup/Disc ratio of synthetic images using a state-of-the-art method. The results obtained from this analysis and the qualitative and quantitative evaluation demonstrate that the synthesised images are anatomically consistent and the system is a promising step towards a model capable of generating labelled images.We gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan Xp GPU used for this research. This work was supported by the Project GALAHAD [H2020-ICT-2016-2017, 732613]SpringerEscuela Técnica Superior de Ingeniería de TelecomunicaciónDepartamento de Matemática AplicadaDepartamento de Estadística e Investigación Operativa Aplicadas y CalidadDepartamento de ComunicacionesEscuela Técnica Superior de Ingeniería Aeroespacial y Diseño IndustrialInstituto Universitario de Investigación en Tecnología Centrada en el Ser HumanoEuropean CommissionRepositorio Institucional de la Universitat Politècnica de València Riunet20192019-07-24book parthttp://purl.org/coar/resource_type/c_3248VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/bookPartapplication/pdfapplication/pdfhttps://riunet.upv.es/handle/10251/124078reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengEuropean Commission https://doi.org/10.13039/501100000780 H2020 732613 Glaucoma – Advanced, LAbel-free High resolution Automated OCT Diagnosticsopen accesshttp://purl.org/coar/access_right/c_abf2Reserva de todos los derechoshttp://rightsstatements.org/vocab/InC/1.0/info:eu-repo/semantics/openAccessoai:riunet.upv.es:10251/1240782026-06-13T07:49:27Z
dc.title.none.fl_str_mv Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE Models
title Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE Models
spellingShingle Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE Models
Díaz-Pinto, Andrés Yesid
Medical imaging
Retinal Image Synthesis
Fundus Images
DCGAN
VAE
TEORIA DE LA SEÑAL Y COMUNICACIONES
title_short Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE Models
title_full Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE Models
title_fullStr Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE Models
title_full_unstemmed Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE Models
title_sort Retinal Image Synthesis for Glaucoma Assessment using DCGAN and VAE Models
dc.creator.none.fl_str_mv Díaz-Pinto, Andrés Yesid
Xu, Yanwu
Frangi, Alejandro F.
Colomer, Adrián|||0000-0002-7616-6029
Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
Morales, Sandra|||0000-0003-0763-1545
author Díaz-Pinto, Andrés Yesid
author_facet Díaz-Pinto, Andrés Yesid
Xu, Yanwu
Frangi, Alejandro F.
Colomer, Adrián|||0000-0002-7616-6029
Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
Morales, Sandra|||0000-0003-0763-1545
author_role author
author2 Xu, Yanwu
Frangi, Alejandro F.
Colomer, Adrián|||0000-0002-7616-6029
Naranjo Ornedo, Valeriana|||0000-0002-0181-3412
Morales, Sandra|||0000-0003-0763-1545
author2_role author
author
author
author
author
dc.contributor.none.fl_str_mv Escuela Técnica Superior de Ingeniería de Telecomunicación
Departamento de Matemática Aplicada
Departamento de Estadística e Investigación Operativa Aplicadas y Calidad
Departamento de Comunicaciones
Escuela Técnica Superior de Ingeniería Aeroespacial y Diseño Industrial
Instituto Universitario de Investigación en Tecnología Centrada en el Ser Humano
European Commission
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Medical imaging
Retinal Image Synthesis
Fundus Images
DCGAN
VAE
TEORIA DE LA SEÑAL Y COMUNICACIONES
topic Medical imaging
Retinal Image Synthesis
Fundus Images
DCGAN
VAE
TEORIA DE LA SEÑAL Y COMUNICACIONES
description The performance of a Glaucoma assessment system is highly affected by the number of labelled images used during the training stage. However, labelled images are often scarce or costly to obtain. In this paper, we address the problem of synthesising retinal fundus images by training a Variational Autoencoder and an adversarial model on 2357 retinal images. The innovation of this approach is in synthesising retinal images without using previous vessel segmentation from a separate method, which makes this system completely independent. The obtained models are image synthesizers capable of generating any amount of cropped retinal images from a simple normal distribution. Furthermore, more images were used for training than any other work in the literature. Synthetic images were qualitatively evaluated by 10 clinical experts and their consistency were estimated by measuring the proportion of pixels corresponding to the anatomical structures around the optic disc. Moreover, we calculated the mean-squared error between the average 2D-histogram of synthetic and real images, obtaining a small difference of 3e-4. Further analysis of the latent space and cup size of the images was performed by measuring the Cup/Disc ratio of synthetic images using a state-of-the-art method. The results obtained from this analysis and the qualitative and quantitative evaluation demonstrate that the synthesised images are anatomically consistent and the system is a promising step towards a model capable of generating labelled images.
publishDate 2019
dc.date.none.fl_str_mv 2019
2019-07-24
dc.type.none.fl_str_mv book part
http://purl.org/coar/resource_type/c_3248
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/bookPart
format bookPart
dc.identifier.none.fl_str_mv https://riunet.upv.es/handle/10251/124078
url https://riunet.upv.es/handle/10251/124078
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv European Commission https://doi.org/10.13039/501100000780 H2020 732613 Glaucoma – Advanced, LAbel-free High resolution Automated OCT Diagnostics
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reserva de todos los derechos
http://rightsstatements.org/vocab/InC/1.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reserva de todos los derechos
http://rightsstatements.org/vocab/InC/1.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
application/pdf
dc.publisher.none.fl_str_mv Springer
publisher.none.fl_str_mv Springer
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869415772957179904
score 15,300719

Similares en LA Referencia