Cargando…
Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning
Purpose: We investigated whether a deep learning algorithm applied to retinal fundoscopic images could predict cerebral white matter hyperintensity (WMH), as represented by a modified Fazekas scale (FS), on brain magnetic resonance imaging (MRI). Methods: Participants who had undergone brain MRI and...
Autores principales: | , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9224833/ https://www.ncbi.nlm.nih.gov/pubmed/35743380 http://dx.doi.org/10.3390/jcm11123309 |
_version_ | 1784733465910968320 |
---|---|
author | Cho, Bum-Joo Lee, Minwoo Han, Jiyong Kwon, Soonil Oh, Mi Sun Yu, Kyung-Ho Lee, Byung-Chul Kim, Ju Han Kim, Chulho |
author_facet | Cho, Bum-Joo Lee, Minwoo Han, Jiyong Kwon, Soonil Oh, Mi Sun Yu, Kyung-Ho Lee, Byung-Chul Kim, Ju Han Kim, Chulho |
author_sort | Cho, Bum-Joo |
collection | PubMed |
description | Purpose: We investigated whether a deep learning algorithm applied to retinal fundoscopic images could predict cerebral white matter hyperintensity (WMH), as represented by a modified Fazekas scale (FS), on brain magnetic resonance imaging (MRI). Methods: Participants who had undergone brain MRI and health-screening fundus photography at Hallym University Sacred Heart Hospital between 2010 and 2020 were consecutively included. The subjects were divided based on the presence of WMH, then classified into three groups according to the FS grade (0 vs. 1 vs. 2+) using age matching. Two pre-trained convolutional neural networks were fine-tuned and evaluated for prediction performance using 10-fold cross-validation. Results: A total of 3726 fundus photographs from 1892 subjects were included, of which 905 fundus photographs from 462 subjects were included in the age-matched balanced dataset. In predicting the presence of WMH, the mean area under the receiver operating characteristic curve was 0.736 ± 0.030 for DenseNet-201 and 0.724 ± 0.026 for EfficientNet-B7. For the prediction of FS grade, the mean accuracies reached 41.4 ± 5.7% with DenseNet-201 and 39.6 ± 5.6% with EfficientNet-B7. The deep learning models focused on the macula and retinal vasculature to detect an FS of 2+. Conclusions: Cerebral WMH might be partially predicted by non-invasive fundus photography via deep learning, which may suggest an eye–brain association. |
format | Online Article Text |
id | pubmed-9224833 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-92248332022-06-24 Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning Cho, Bum-Joo Lee, Minwoo Han, Jiyong Kwon, Soonil Oh, Mi Sun Yu, Kyung-Ho Lee, Byung-Chul Kim, Ju Han Kim, Chulho J Clin Med Article Purpose: We investigated whether a deep learning algorithm applied to retinal fundoscopic images could predict cerebral white matter hyperintensity (WMH), as represented by a modified Fazekas scale (FS), on brain magnetic resonance imaging (MRI). Methods: Participants who had undergone brain MRI and health-screening fundus photography at Hallym University Sacred Heart Hospital between 2010 and 2020 were consecutively included. The subjects were divided based on the presence of WMH, then classified into three groups according to the FS grade (0 vs. 1 vs. 2+) using age matching. Two pre-trained convolutional neural networks were fine-tuned and evaluated for prediction performance using 10-fold cross-validation. Results: A total of 3726 fundus photographs from 1892 subjects were included, of which 905 fundus photographs from 462 subjects were included in the age-matched balanced dataset. In predicting the presence of WMH, the mean area under the receiver operating characteristic curve was 0.736 ± 0.030 for DenseNet-201 and 0.724 ± 0.026 for EfficientNet-B7. For the prediction of FS grade, the mean accuracies reached 41.4 ± 5.7% with DenseNet-201 and 39.6 ± 5.6% with EfficientNet-B7. The deep learning models focused on the macula and retinal vasculature to detect an FS of 2+. Conclusions: Cerebral WMH might be partially predicted by non-invasive fundus photography via deep learning, which may suggest an eye–brain association. MDPI 2022-06-09 /pmc/articles/PMC9224833/ /pubmed/35743380 http://dx.doi.org/10.3390/jcm11123309 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 Cho, Bum-Joo Lee, Minwoo Han, Jiyong Kwon, Soonil Oh, Mi Sun Yu, Kyung-Ho Lee, Byung-Chul Kim, Ju Han Kim, Chulho Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning |
title | Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning |
title_full | Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning |
title_fullStr | Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning |
title_full_unstemmed | Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning |
title_short | Prediction of White Matter Hyperintensity in Brain MRI Using Fundus Photographs via Deep Learning |
title_sort | prediction of white matter hyperintensity in brain mri using fundus photographs via deep learning |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9224833/ https://www.ncbi.nlm.nih.gov/pubmed/35743380 http://dx.doi.org/10.3390/jcm11123309 |
work_keys_str_mv | AT chobumjoo predictionofwhitematterhyperintensityinbrainmriusingfundusphotographsviadeeplearning AT leeminwoo predictionofwhitematterhyperintensityinbrainmriusingfundusphotographsviadeeplearning AT hanjiyong predictionofwhitematterhyperintensityinbrainmriusingfundusphotographsviadeeplearning AT kwonsoonil predictionofwhitematterhyperintensityinbrainmriusingfundusphotographsviadeeplearning AT ohmisun predictionofwhitematterhyperintensityinbrainmriusingfundusphotographsviadeeplearning AT yukyungho predictionofwhitematterhyperintensityinbrainmriusingfundusphotographsviadeeplearning AT leebyungchul predictionofwhitematterhyperintensityinbrainmriusingfundusphotographsviadeeplearning AT kimjuhan predictionofwhitematterhyperintensityinbrainmriusingfundusphotographsviadeeplearning AT kimchulho predictionofwhitematterhyperintensityinbrainmriusingfundusphotographsviadeeplearning |