Cargando…

Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models

While color fundus photos are used in routine clinical practice to diagnose ophthalmic conditions, evidence suggests that ocular imaging contains valuable information regarding the systemic health features of patients. These features can be identified through computer vision techniques including dee...

Descripción completa

Detalles Bibliográficos
Autores principales: Khan, Nergis C., Perera, Chandrashan, Dow, Eliot R., Chen, Karen M., Mahajan, Vinit B., Mruthyunjaya, Prithvi, Do, Diana V., Leng, Theodore, Myung, David
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9322827/
https://www.ncbi.nlm.nih.gov/pubmed/35885619
http://dx.doi.org/10.3390/diagnostics12071714
_version_ 1784756400253042688
author Khan, Nergis C.
Perera, Chandrashan
Dow, Eliot R.
Chen, Karen M.
Mahajan, Vinit B.
Mruthyunjaya, Prithvi
Do, Diana V.
Leng, Theodore
Myung, David
author_facet Khan, Nergis C.
Perera, Chandrashan
Dow, Eliot R.
Chen, Karen M.
Mahajan, Vinit B.
Mruthyunjaya, Prithvi
Do, Diana V.
Leng, Theodore
Myung, David
author_sort Khan, Nergis C.
collection PubMed
description While color fundus photos are used in routine clinical practice to diagnose ophthalmic conditions, evidence suggests that ocular imaging contains valuable information regarding the systemic health features of patients. These features can be identified through computer vision techniques including deep learning (DL) artificial intelligence (AI) models. We aim to construct a DL model that can predict systemic features from fundus images and to determine the optimal method of model construction for this task. Data were collected from a cohort of patients undergoing diabetic retinopathy screening between March 2020 and March 2021. Two models were created for each of 12 systemic health features based on the DenseNet201 architecture: one utilizing transfer learning with images from ImageNet and another from 35,126 fundus images. Here, 1277 fundus images were used to train the AI models. Area under the receiver operating characteristics curve (AUROC) scores were used to compare the model performance. Models utilizing the ImageNet transfer learning data were superior to those using retinal images for transfer learning (mean AUROC 0.78 vs. 0.65, p-value < 0.001). Models using ImageNet pretraining were able to predict systemic features including ethnicity (AUROC 0.93), age > 70 (AUROC 0.90), gender (AUROC 0.85), ACE inhibitor (AUROC 0.82), and ARB medication use (AUROC 0.78). We conclude that fundus images contain valuable information about the systemic characteristics of a patient. To optimize DL model performance, we recommend that even domain specific models consider using transfer learning from more generalized image sets to improve accuracy.
format Online
Article
Text
id pubmed-9322827
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93228272022-07-27 Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models Khan, Nergis C. Perera, Chandrashan Dow, Eliot R. Chen, Karen M. Mahajan, Vinit B. Mruthyunjaya, Prithvi Do, Diana V. Leng, Theodore Myung, David Diagnostics (Basel) Article While color fundus photos are used in routine clinical practice to diagnose ophthalmic conditions, evidence suggests that ocular imaging contains valuable information regarding the systemic health features of patients. These features can be identified through computer vision techniques including deep learning (DL) artificial intelligence (AI) models. We aim to construct a DL model that can predict systemic features from fundus images and to determine the optimal method of model construction for this task. Data were collected from a cohort of patients undergoing diabetic retinopathy screening between March 2020 and March 2021. Two models were created for each of 12 systemic health features based on the DenseNet201 architecture: one utilizing transfer learning with images from ImageNet and another from 35,126 fundus images. Here, 1277 fundus images were used to train the AI models. Area under the receiver operating characteristics curve (AUROC) scores were used to compare the model performance. Models utilizing the ImageNet transfer learning data were superior to those using retinal images for transfer learning (mean AUROC 0.78 vs. 0.65, p-value < 0.001). Models using ImageNet pretraining were able to predict systemic features including ethnicity (AUROC 0.93), age > 70 (AUROC 0.90), gender (AUROC 0.85), ACE inhibitor (AUROC 0.82), and ARB medication use (AUROC 0.78). We conclude that fundus images contain valuable information about the systemic characteristics of a patient. To optimize DL model performance, we recommend that even domain specific models consider using transfer learning from more generalized image sets to improve accuracy. MDPI 2022-07-14 /pmc/articles/PMC9322827/ /pubmed/35885619 http://dx.doi.org/10.3390/diagnostics12071714 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
Khan, Nergis C.
Perera, Chandrashan
Dow, Eliot R.
Chen, Karen M.
Mahajan, Vinit B.
Mruthyunjaya, Prithvi
Do, Diana V.
Leng, Theodore
Myung, David
Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models
title Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models
title_full Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models
title_fullStr Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models
title_full_unstemmed Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models
title_short Predicting Systemic Health Features from Retinal Fundus Images Using Transfer-Learning-Based Artificial Intelligence Models
title_sort predicting systemic health features from retinal fundus images using transfer-learning-based artificial intelligence models
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9322827/
https://www.ncbi.nlm.nih.gov/pubmed/35885619
http://dx.doi.org/10.3390/diagnostics12071714
work_keys_str_mv AT khannergisc predictingsystemichealthfeaturesfromretinalfundusimagesusingtransferlearningbasedartificialintelligencemodels
AT pererachandrashan predictingsystemichealthfeaturesfromretinalfundusimagesusingtransferlearningbasedartificialintelligencemodels
AT doweliotr predictingsystemichealthfeaturesfromretinalfundusimagesusingtransferlearningbasedartificialintelligencemodels
AT chenkarenm predictingsystemichealthfeaturesfromretinalfundusimagesusingtransferlearningbasedartificialintelligencemodels
AT mahajanvinitb predictingsystemichealthfeaturesfromretinalfundusimagesusingtransferlearningbasedartificialintelligencemodels
AT mruthyunjayaprithvi predictingsystemichealthfeaturesfromretinalfundusimagesusingtransferlearningbasedartificialintelligencemodels
AT dodianav predictingsystemichealthfeaturesfromretinalfundusimagesusingtransferlearningbasedartificialintelligencemodels
AT lengtheodore predictingsystemichealthfeaturesfromretinalfundusimagesusingtransferlearningbasedartificialintelligencemodels
AT myungdavid predictingsystemichealthfeaturesfromretinalfundusimagesusingtransferlearningbasedartificialintelligencemodels