Cargando…

Detection of Stroke with Retinal Microvascular Density and Self-Supervised Learning Using OCT-A and Fundus Imaging

Acute cerebral stroke is a leading cause of disability and death, which could be reduced with a prompt diagnosis during patient transportation to the hospital. A portable retina imaging system could enable this by measuring vascular information and blood perfusion in the retina and, due to the homol...

Descripción completa

Detalles Bibliográficos
Autores principales: Pachade, Samiksha, Coronado, Ivan, Abdelkhaleq, Rania, Yan, Juntao, Salazar-Marioni, Sergio, Jagolino, Amanda, Green, Charles, Bahrainian, Mozhdeh, Channa, Roomasa, Sheth, Sunil A., Giancardo, Luca
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9788382/
https://www.ncbi.nlm.nih.gov/pubmed/36556024
http://dx.doi.org/10.3390/jcm11247408
_version_ 1784858740926709760
author Pachade, Samiksha
Coronado, Ivan
Abdelkhaleq, Rania
Yan, Juntao
Salazar-Marioni, Sergio
Jagolino, Amanda
Green, Charles
Bahrainian, Mozhdeh
Channa, Roomasa
Sheth, Sunil A.
Giancardo, Luca
author_facet Pachade, Samiksha
Coronado, Ivan
Abdelkhaleq, Rania
Yan, Juntao
Salazar-Marioni, Sergio
Jagolino, Amanda
Green, Charles
Bahrainian, Mozhdeh
Channa, Roomasa
Sheth, Sunil A.
Giancardo, Luca
author_sort Pachade, Samiksha
collection PubMed
description Acute cerebral stroke is a leading cause of disability and death, which could be reduced with a prompt diagnosis during patient transportation to the hospital. A portable retina imaging system could enable this by measuring vascular information and blood perfusion in the retina and, due to the homology between retinal and cerebral vessels, infer if a cerebral stroke is underway. However, the feasibility of this strategy, the imaging features, and retina imaging modalities to do this are not clear. In this work, we show initial evidence of the feasibility of this approach by training machine learning models using feature engineering and self-supervised learning retina features extracted from OCT-A and fundus images to classify controls and acute stroke patients. Models based on macular microvasculature density features achieved an area under the receiver operating characteristic curve (AUC) of 0.87–0.88. Self-supervised deep learning models were able to generate features resulting in AUCs ranging from 0.66 to 0.81. While further work is needed for the final proof for a diagnostic system, these results indicate that microvasculature density features from OCT-A images have the potential to be used to diagnose acute cerebral stroke from the retina.
format Online
Article
Text
id pubmed-9788382
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-97883822022-12-24 Detection of Stroke with Retinal Microvascular Density and Self-Supervised Learning Using OCT-A and Fundus Imaging Pachade, Samiksha Coronado, Ivan Abdelkhaleq, Rania Yan, Juntao Salazar-Marioni, Sergio Jagolino, Amanda Green, Charles Bahrainian, Mozhdeh Channa, Roomasa Sheth, Sunil A. Giancardo, Luca J Clin Med Article Acute cerebral stroke is a leading cause of disability and death, which could be reduced with a prompt diagnosis during patient transportation to the hospital. A portable retina imaging system could enable this by measuring vascular information and blood perfusion in the retina and, due to the homology between retinal and cerebral vessels, infer if a cerebral stroke is underway. However, the feasibility of this strategy, the imaging features, and retina imaging modalities to do this are not clear. In this work, we show initial evidence of the feasibility of this approach by training machine learning models using feature engineering and self-supervised learning retina features extracted from OCT-A and fundus images to classify controls and acute stroke patients. Models based on macular microvasculature density features achieved an area under the receiver operating characteristic curve (AUC) of 0.87–0.88. Self-supervised deep learning models were able to generate features resulting in AUCs ranging from 0.66 to 0.81. While further work is needed for the final proof for a diagnostic system, these results indicate that microvasculature density features from OCT-A images have the potential to be used to diagnose acute cerebral stroke from the retina. MDPI 2022-12-14 /pmc/articles/PMC9788382/ /pubmed/36556024 http://dx.doi.org/10.3390/jcm11247408 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/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 (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Pachade, Samiksha
Coronado, Ivan
Abdelkhaleq, Rania
Yan, Juntao
Salazar-Marioni, Sergio
Jagolino, Amanda
Green, Charles
Bahrainian, Mozhdeh
Channa, Roomasa
Sheth, Sunil A.
Giancardo, Luca
Detection of Stroke with Retinal Microvascular Density and Self-Supervised Learning Using OCT-A and Fundus Imaging
title Detection of Stroke with Retinal Microvascular Density and Self-Supervised Learning Using OCT-A and Fundus Imaging
title_full Detection of Stroke with Retinal Microvascular Density and Self-Supervised Learning Using OCT-A and Fundus Imaging
title_fullStr Detection of Stroke with Retinal Microvascular Density and Self-Supervised Learning Using OCT-A and Fundus Imaging
title_full_unstemmed Detection of Stroke with Retinal Microvascular Density and Self-Supervised Learning Using OCT-A and Fundus Imaging
title_short Detection of Stroke with Retinal Microvascular Density and Self-Supervised Learning Using OCT-A and Fundus Imaging
title_sort detection of stroke with retinal microvascular density and self-supervised learning using oct-a and fundus imaging
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9788382/
https://www.ncbi.nlm.nih.gov/pubmed/36556024
http://dx.doi.org/10.3390/jcm11247408
work_keys_str_mv AT pachadesamiksha detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT coronadoivan detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT abdelkhaleqrania detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT yanjuntao detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT salazarmarionisergio detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT jagolinoamanda detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT greencharles detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT bahrainianmozhdeh detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT channaroomasa detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT shethsunila detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging
AT giancardoluca detectionofstrokewithretinalmicrovasculardensityandselfsupervisedlearningusingoctaandfundusimaging