Cargando…

Combination of Global Features for the Automatic Quality Assessment of Retinal Images

Diabetic retinopathy (DR) is one of the most common causes of visual loss in developed countries. Computer-aided diagnosis systems aimed at detecting DR can reduce the workload of ophthalmologists in screening programs. Nevertheless, a large number of retinal images cannot be analyzed by physicians...

Descripción completa

Detalles Bibliográficos
Autores principales: Jiménez-García, Jorge, Romero-Oraá, Roberto, García, María, López-Gálvez, María I., Hornero, Roberto
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2019
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7514792/
https://www.ncbi.nlm.nih.gov/pubmed/33267025
http://dx.doi.org/10.3390/e21030311
_version_ 1783586670489108480
author Jiménez-García, Jorge
Romero-Oraá, Roberto
García, María
López-Gálvez, María I.
Hornero, Roberto
author_facet Jiménez-García, Jorge
Romero-Oraá, Roberto
García, María
López-Gálvez, María I.
Hornero, Roberto
author_sort Jiménez-García, Jorge
collection PubMed
description Diabetic retinopathy (DR) is one of the most common causes of visual loss in developed countries. Computer-aided diagnosis systems aimed at detecting DR can reduce the workload of ophthalmologists in screening programs. Nevertheless, a large number of retinal images cannot be analyzed by physicians and automatic methods due to poor quality. Automatic retinal image quality assessment (RIQA) is needed before image analysis. The purpose of this study was to combine novel generic quality features to develop a RIQA method. Several features were calculated from retinal images to achieve this goal. Features derived from the spatial and spectral entropy-based quality (SSEQ) and the natural images quality evaluator (NIQE) methods were extracted. They were combined with novel sharpness and luminosity measures based on the continuous wavelet transform (CWT) and the hue saturation value (HSV) color model, respectively. A subset of non-redundant features was selected using the fast correlation-based filter (FCBF) method. Subsequently, a multilayer perceptron (MLP) neural network was used to obtain the quality of images from the selected features. Classification results achieved 91.46% accuracy, 92.04% sensitivity, and 87.92% specificity. Results suggest that the proposed RIQA method could be applied in a more general computer-aided diagnosis system aimed at detecting a variety of retinal pathologies such as DR and age-related macular degeneration.
format Online
Article
Text
id pubmed-7514792
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-75147922020-11-09 Combination of Global Features for the Automatic Quality Assessment of Retinal Images Jiménez-García, Jorge Romero-Oraá, Roberto García, María López-Gálvez, María I. Hornero, Roberto Entropy (Basel) Article Diabetic retinopathy (DR) is one of the most common causes of visual loss in developed countries. Computer-aided diagnosis systems aimed at detecting DR can reduce the workload of ophthalmologists in screening programs. Nevertheless, a large number of retinal images cannot be analyzed by physicians and automatic methods due to poor quality. Automatic retinal image quality assessment (RIQA) is needed before image analysis. The purpose of this study was to combine novel generic quality features to develop a RIQA method. Several features were calculated from retinal images to achieve this goal. Features derived from the spatial and spectral entropy-based quality (SSEQ) and the natural images quality evaluator (NIQE) methods were extracted. They were combined with novel sharpness and luminosity measures based on the continuous wavelet transform (CWT) and the hue saturation value (HSV) color model, respectively. A subset of non-redundant features was selected using the fast correlation-based filter (FCBF) method. Subsequently, a multilayer perceptron (MLP) neural network was used to obtain the quality of images from the selected features. Classification results achieved 91.46% accuracy, 92.04% sensitivity, and 87.92% specificity. Results suggest that the proposed RIQA method could be applied in a more general computer-aided diagnosis system aimed at detecting a variety of retinal pathologies such as DR and age-related macular degeneration. MDPI 2019-03-21 /pmc/articles/PMC7514792/ /pubmed/33267025 http://dx.doi.org/10.3390/e21030311 Text en © 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Jiménez-García, Jorge
Romero-Oraá, Roberto
García, María
López-Gálvez, María I.
Hornero, Roberto
Combination of Global Features for the Automatic Quality Assessment of Retinal Images
title Combination of Global Features for the Automatic Quality Assessment of Retinal Images
title_full Combination of Global Features for the Automatic Quality Assessment of Retinal Images
title_fullStr Combination of Global Features for the Automatic Quality Assessment of Retinal Images
title_full_unstemmed Combination of Global Features for the Automatic Quality Assessment of Retinal Images
title_short Combination of Global Features for the Automatic Quality Assessment of Retinal Images
title_sort combination of global features for the automatic quality assessment of retinal images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7514792/
https://www.ncbi.nlm.nih.gov/pubmed/33267025
http://dx.doi.org/10.3390/e21030311
work_keys_str_mv AT jimenezgarciajorge combinationofglobalfeaturesfortheautomaticqualityassessmentofretinalimages
AT romerooraaroberto combinationofglobalfeaturesfortheautomaticqualityassessmentofretinalimages
AT garciamaria combinationofglobalfeaturesfortheautomaticqualityassessmentofretinalimages
AT lopezgalvezmariai combinationofglobalfeaturesfortheautomaticqualityassessmentofretinalimages
AT horneroroberto combinationofglobalfeaturesfortheautomaticqualityassessmentofretinalimages