Cargando…

Merging Information From Infrared and Autofluorescence Fundus Images for Monitoring of Chorioretinal Atrophic Lesions

PURPOSE: To develop a method for automated detection and progression analysis of chorioretinal atrophic lesions using the combined information of standard infrared (IR) and autofluorescence (AF) fundus images. METHODS: Eighteen eyes (from 16 subjects) with punctate inner choroidopathy were analyzed....

Descripción completa

Detalles Bibliográficos
Autores principales: Ometto, Giovanni, Montesano, Giovanni, Sadeghi Afgeh, Saman, Lazaridis, Georgios, Liu, Xiaoxuan, Keane, Pearse A., Crabb, David P., Denniston, Alastair K.
Formato: Online Artículo Texto
Lenguaje:English
Publicado: The Association for Research in Vision and Ophthalmology 2020
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7453042/
https://www.ncbi.nlm.nih.gov/pubmed/32908801
http://dx.doi.org/10.1167/tvst.9.9.38
_version_ 1783575279429484544
author Ometto, Giovanni
Montesano, Giovanni
Sadeghi Afgeh, Saman
Lazaridis, Georgios
Liu, Xiaoxuan
Keane, Pearse A.
Crabb, David P.
Denniston, Alastair K.
author_facet Ometto, Giovanni
Montesano, Giovanni
Sadeghi Afgeh, Saman
Lazaridis, Georgios
Liu, Xiaoxuan
Keane, Pearse A.
Crabb, David P.
Denniston, Alastair K.
author_sort Ometto, Giovanni
collection PubMed
description PURPOSE: To develop a method for automated detection and progression analysis of chorioretinal atrophic lesions using the combined information of standard infrared (IR) and autofluorescence (AF) fundus images. METHODS: Eighteen eyes (from 16 subjects) with punctate inner choroidopathy were analyzed. Macular IR and blue AF images were acquired in all eyes with a Spectralis HRA+OCT device (Heidelberg Engineering, Heidelberg, Germany). Two clinical experts manually segmented chorioretinal lesions on the AF image. AF images were aligned to the corresponding IR. Two random forest models were trained to classify pixels of lesions, one based on the AF image only, the other based on the aligned IR-AF. The models were validated using a leave-one-out cross-validation and were tested against the manual segmentation to compare their performance. A time series from one eye was identified and used to evaluate the method based on the IR-AF in a case study. RESULTS: The method based on the AF images correctly classified 95% of the pixels (i.e., in vs. out of the lesion) with a Dice's coefficient of 0.80. The method based on the combined IR-AF correctly classified 96% of the pixels with a Dice's coefficient of 0.84. CONCLUSIONS: The automated segmentation of chorioretinal lesions using IR and AF shows closer alignment to manual segmentation than the same method based on AF only. Merging information from multimodal images improves the automatic and objective segmentation of chorioretinal lesions even when based on a small dataset. TRANSLATIONAL RELEVANCE: Merged information from multimodal images improves segmentation performance of chorioretinal lesions.
format Online
Article
Text
id pubmed-7453042
institution National Center for Biotechnology Information
language English
publishDate 2020
publisher The Association for Research in Vision and Ophthalmology
record_format MEDLINE/PubMed
spelling pubmed-74530422020-09-08 Merging Information From Infrared and Autofluorescence Fundus Images for Monitoring of Chorioretinal Atrophic Lesions Ometto, Giovanni Montesano, Giovanni Sadeghi Afgeh, Saman Lazaridis, Georgios Liu, Xiaoxuan Keane, Pearse A. Crabb, David P. Denniston, Alastair K. Transl Vis Sci Technol Article PURPOSE: To develop a method for automated detection and progression analysis of chorioretinal atrophic lesions using the combined information of standard infrared (IR) and autofluorescence (AF) fundus images. METHODS: Eighteen eyes (from 16 subjects) with punctate inner choroidopathy were analyzed. Macular IR and blue AF images were acquired in all eyes with a Spectralis HRA+OCT device (Heidelberg Engineering, Heidelberg, Germany). Two clinical experts manually segmented chorioretinal lesions on the AF image. AF images were aligned to the corresponding IR. Two random forest models were trained to classify pixels of lesions, one based on the AF image only, the other based on the aligned IR-AF. The models were validated using a leave-one-out cross-validation and were tested against the manual segmentation to compare their performance. A time series from one eye was identified and used to evaluate the method based on the IR-AF in a case study. RESULTS: The method based on the AF images correctly classified 95% of the pixels (i.e., in vs. out of the lesion) with a Dice's coefficient of 0.80. The method based on the combined IR-AF correctly classified 96% of the pixels with a Dice's coefficient of 0.84. CONCLUSIONS: The automated segmentation of chorioretinal lesions using IR and AF shows closer alignment to manual segmentation than the same method based on AF only. Merging information from multimodal images improves the automatic and objective segmentation of chorioretinal lesions even when based on a small dataset. TRANSLATIONAL RELEVANCE: Merged information from multimodal images improves segmentation performance of chorioretinal lesions. The Association for Research in Vision and Ophthalmology 2020-08-25 /pmc/articles/PMC7453042/ /pubmed/32908801 http://dx.doi.org/10.1167/tvst.9.9.38 Text en Copyright 2020 The Authors http://creativecommons.org/licenses/by/4.0/ This work is licensed under a Creative Commons Attribution 4.0 International License.
spellingShingle Article
Ometto, Giovanni
Montesano, Giovanni
Sadeghi Afgeh, Saman
Lazaridis, Georgios
Liu, Xiaoxuan
Keane, Pearse A.
Crabb, David P.
Denniston, Alastair K.
Merging Information From Infrared and Autofluorescence Fundus Images for Monitoring of Chorioretinal Atrophic Lesions
title Merging Information From Infrared and Autofluorescence Fundus Images for Monitoring of Chorioretinal Atrophic Lesions
title_full Merging Information From Infrared and Autofluorescence Fundus Images for Monitoring of Chorioretinal Atrophic Lesions
title_fullStr Merging Information From Infrared and Autofluorescence Fundus Images for Monitoring of Chorioretinal Atrophic Lesions
title_full_unstemmed Merging Information From Infrared and Autofluorescence Fundus Images for Monitoring of Chorioretinal Atrophic Lesions
title_short Merging Information From Infrared and Autofluorescence Fundus Images for Monitoring of Chorioretinal Atrophic Lesions
title_sort merging information from infrared and autofluorescence fundus images for monitoring of chorioretinal atrophic lesions
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7453042/
https://www.ncbi.nlm.nih.gov/pubmed/32908801
http://dx.doi.org/10.1167/tvst.9.9.38
work_keys_str_mv AT omettogiovanni merginginformationfrominfraredandautofluorescencefundusimagesformonitoringofchorioretinalatrophiclesions
AT montesanogiovanni merginginformationfrominfraredandautofluorescencefundusimagesformonitoringofchorioretinalatrophiclesions
AT sadeghiafgehsaman merginginformationfrominfraredandautofluorescencefundusimagesformonitoringofchorioretinalatrophiclesions
AT lazaridisgeorgios merginginformationfrominfraredandautofluorescencefundusimagesformonitoringofchorioretinalatrophiclesions
AT liuxiaoxuan merginginformationfrominfraredandautofluorescencefundusimagesformonitoringofchorioretinalatrophiclesions
AT keanepearsea merginginformationfrominfraredandautofluorescencefundusimagesformonitoringofchorioretinalatrophiclesions
AT crabbdavidp merginginformationfrominfraredandautofluorescencefundusimagesformonitoringofchorioretinalatrophiclesions
AT dennistonalastairk merginginformationfrominfraredandautofluorescencefundusimagesformonitoringofchorioretinalatrophiclesions