Detection and removal of dust artifacts in retinal images via sparse-based inpainting

Dust particle artifacts are present in all imaging modalities but have more adverse consequences in medical images like retinal images. They could be mistaken as small lesions, such as microaneurysms. We propose a method for detecting and accurately segmenting dust artifacts in retinal images based...

Descripción completa

Detalles Bibliográficos
Autores: Barrios Montes, Erik Miguel, Sierra, E., Romero Pérez, Lenny Alexandra, Millán Garcia-Varela, M. Sagrario|||0000-0001-6950-2373, Marrugo Hernandez, Andrés Guillermo
Tipo de recurso: artículo
Fecha de publicación:2021
País:España
Institución:Universitat Politècnica de Catalunya (UPC)
Repositorio:UPCommons. Portal del coneixement obert de la UPC
Idioma:inglés
OAI Identifier:oai:upcommons.upc.edu:2117/361445
Acceso en línea:https://hdl.handle.net/2117/361445
https://dx.doi.org/10.7149/OPA.54.3.51060
Access Level:acceso abierto
Palabra clave:Retina
Machine learning
Artifact detection
Dust particle
Retinal image
Fundus image
Image restoration
Dictionary learning
Inpainting
Sensor artifact
Sparse representation
Aprenentatge automàtic
Àrees temàtiques de la UPC::Ciències de la visió
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
id ES_c97f8ea7a6adc8b9fc3f208ca9ec833e
oai_identifier_str oai:upcommons.upc.edu:2117/361445
network_acronym_str ES
network_name_str España
repository_id_str
spelling Detection and removal of dust artifacts in retinal images via sparse-based inpaintingBarrios Montes, Erik MiguelSierra, E.Romero Pérez, Lenny AlexandraMillán Garcia-Varela, M. Sagrario|||0000-0001-6950-2373Marrugo Hernandez, Andrés GuillermoRetinaMachine learningArtifact detectionDust particleRetinal imageFundus imageImage restorationDictionary learningInpaintingSensor artifactSparse representationRetinaAprenentatge automàticÀrees temàtiques de la UPC::Ciències de la visióÀrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàticDust particle artifacts are present in all imaging modalities but have more adverse consequences in medical images like retinal images. They could be mistaken as small lesions, such as microaneurysms. We propose a method for detecting and accurately segmenting dust artifacts in retinal images based on multi-scale template-matching on several input images and an iterative segmentation via an inpainting approach. The inpainting is done through dictionary learning and sparse-based representation. The artifact segmentation is refined by comparing the original image to the initial restoration. On average, 90% of the dust artifacts were detected in the test images, with state-of-theart restoration results. All detected artifacts were accurately segmented and removed. Even the most challenging artifacts located on top of blood vessels were removed. Thus, ensuring the continuity of the retinal structures. The proposed method successfully detects and removes dust artifacts in retinal images, which could be used to avoid false-positive lesion detections or as an image quality criterion. An implementation of the proposed algorithm can be accessed and executed through a Code Ocean compute capsule.The authors acknowledge the financial support from the Centre de Cooperació i Desenvolupament (CCD) at the Universitat Politècnica de Catalunya under project ref. CCD 2019-B004, and from the Universidad Tecnológica de Bolívar. Authors are grateful to Juan Luís Fuentes from the Miguel Servet University Hospital (Zaragoza, Spain) for providing the real images from clinical practice. E. Barrios thanks Minciencias and Sistema General de Regalías (Programa de Becas de Excelencia) for a PhD scholarship. E. Sierra thanks the Universidad Tecnológica de Bolívar for a post-graduate scholarship. Parts of this work were presented at the Pattern Recognition and Tracking XXX - SPIE DCS, 2019 [39]. L. Romero, A. Marrugo, and M.S. Millán thank the funds provided by the Spanish Ministerio de Ciencia e Innovación under the project reference PID2020-114582RB-I00.Peer Reviewed20212021-09-0120222022-02-02journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://hdl.handle.net/2117/361445https://dx.doi.org/10.7149/OPA.54.3.51060reponame:UPCommons. Portal del coneixement obert de la UPCinstname:Universitat Politècnica de Catalunya (UPC)InglésengAgencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2020-114582RB-I00 IMPLANTES OPTICOS INTRAOCULARES CORRECTORES DE LA PRESBICIA PARA UNA COMPENSACION VISUAL PERSONALIZADAopen accesshttp://purl.org/coar/access_right/c_abf2Attribution-NonCommercial-NoDerivs 3.0 Spainhttp://creativecommons.org/licenses/by-nc-nd/3.0/es/info:eu-repo/semantics/openAccessoai:upcommons.upc.edu:2117/3614452026-05-27T15:37:01Z
dc.title.none.fl_str_mv Detection and removal of dust artifacts in retinal images via sparse-based inpainting
title Detection and removal of dust artifacts in retinal images via sparse-based inpainting
spellingShingle Detection and removal of dust artifacts in retinal images via sparse-based inpainting
Barrios Montes, Erik Miguel
Retina
Machine learning
Artifact detection
Dust particle
Retinal image
Fundus image
Image restoration
Dictionary learning
Inpainting
Sensor artifact
Sparse representation
Retina
Aprenentatge automàtic
Àrees temàtiques de la UPC::Ciències de la visió
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
title_short Detection and removal of dust artifacts in retinal images via sparse-based inpainting
title_full Detection and removal of dust artifacts in retinal images via sparse-based inpainting
title_fullStr Detection and removal of dust artifacts in retinal images via sparse-based inpainting
title_full_unstemmed Detection and removal of dust artifacts in retinal images via sparse-based inpainting
title_sort Detection and removal of dust artifacts in retinal images via sparse-based inpainting
dc.creator.none.fl_str_mv Barrios Montes, Erik Miguel
Sierra, E.
Romero Pérez, Lenny Alexandra
Millán Garcia-Varela, M. Sagrario|||0000-0001-6950-2373
Marrugo Hernandez, Andrés Guillermo
author Barrios Montes, Erik Miguel
author_facet Barrios Montes, Erik Miguel
Sierra, E.
Romero Pérez, Lenny Alexandra
Millán Garcia-Varela, M. Sagrario|||0000-0001-6950-2373
Marrugo Hernandez, Andrés Guillermo
author_role author
author2 Sierra, E.
Romero Pérez, Lenny Alexandra
Millán Garcia-Varela, M. Sagrario|||0000-0001-6950-2373
Marrugo Hernandez, Andrés Guillermo
author2_role author
author
author
author
dc.subject.none.fl_str_mv Retina
Machine learning
Artifact detection
Dust particle
Retinal image
Fundus image
Image restoration
Dictionary learning
Inpainting
Sensor artifact
Sparse representation
Retina
Aprenentatge automàtic
Àrees temàtiques de la UPC::Ciències de la visió
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
topic Retina
Machine learning
Artifact detection
Dust particle
Retinal image
Fundus image
Image restoration
Dictionary learning
Inpainting
Sensor artifact
Sparse representation
Retina
Aprenentatge automàtic
Àrees temàtiques de la UPC::Ciències de la visió
Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial::Aprenentatge automàtic
description Dust particle artifacts are present in all imaging modalities but have more adverse consequences in medical images like retinal images. They could be mistaken as small lesions, such as microaneurysms. We propose a method for detecting and accurately segmenting dust artifacts in retinal images based on multi-scale template-matching on several input images and an iterative segmentation via an inpainting approach. The inpainting is done through dictionary learning and sparse-based representation. The artifact segmentation is refined by comparing the original image to the initial restoration. On average, 90% of the dust artifacts were detected in the test images, with state-of-theart restoration results. All detected artifacts were accurately segmented and removed. Even the most challenging artifacts located on top of blood vessels were removed. Thus, ensuring the continuity of the retinal structures. The proposed method successfully detects and removes dust artifacts in retinal images, which could be used to avoid false-positive lesion detections or as an image quality criterion. An implementation of the proposed algorithm can be accessed and executed through a Code Ocean compute capsule.
publishDate 2021
dc.date.none.fl_str_mv 2021
2021-09-01
2022
2022-02-02
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://hdl.handle.net/2117/361445
https://dx.doi.org/10.7149/OPA.54.3.51060
url https://hdl.handle.net/2117/361445
https://dx.doi.org/10.7149/OPA.54.3.51060
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020 PID2020-114582RB-I00 IMPLANTES OPTICOS INTRAOCULARES CORRECTORES DE LA PRESBICIA PARA UNA COMPENSACION VISUAL PERSONALIZADA
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
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
Attribution-NonCommercial-NoDerivs 3.0 Spain
http://creativecommons.org/licenses/by-nc-nd/3.0/es/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:UPCommons. Portal del coneixement obert de la UPC
instname:Universitat Politècnica de Catalunya (UPC)
instname_str Universitat Politècnica de Catalunya (UPC)
reponame_str UPCommons. Portal del coneixement obert de la UPC
collection UPCommons. Portal del coneixement obert de la UPC
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869419376637116416
score 15.301629

Similares en LA Referencia