Tags

Type your tag names separated by a space and hit enter

Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy.
Transl Vis Sci Technol. 2020 07; 9(2):35.TV

Abstract

Purpose

To test the feasibility of using deep learning for optical coherence tomography angiography (OCTA) detection of diabetic retinopathy.

Methods

A deep-learning convolutional neural network (CNN) architecture, VGG16, was employed for this study. A transfer learning process was implemented to retrain the CNN for robust OCTA classification. One dataset, consisting of images of 32 healthy eyes, 75 eyes with diabetic retinopathy (DR), and 24 eyes with diabetes but no DR (NoDR), was used for training and cross-validation. A second dataset consisting of 20 NoDR and 26 DR eyes was used for external validation. To demonstrate the feasibility of using artificial intelligence (AI) screening of DR in clinical environments, the CNN was incorporated into a graphical user interface (GUI) platform.

Results

With the last nine layers retrained, the CNN architecture achieved the best performance for automated OCTA classification. The cross-validation accuracy of the retrained classifier for differentiating among healthy, NoDR, and DR eyes was 87.27%, with 83.76% sensitivity and 90.82% specificity. The AUC metrics for binary classification of healthy, NoDR, and DR eyes were 0.97, 0.98, and 0.97, respectively. The GUI platform enabled easy validation of the method for AI screening of DR in a clinical environment.

Conclusions

With a transfer learning process for retraining, a CNN can be used for robust OCTA classification of healthy, NoDR, and DR eyes. The AI-based OCTA classification platform may provide a practical solution to reducing the burden of experienced ophthalmologists with regard to mass screening of DR patients.

Translational Relevance

Deep-learning-based OCTA classification can alleviate the need for manual graders and improve DR screening efficiency.

Authors+Show Affiliations

Department of Bioengineering, University of Illinois at Chicago, Chicago, IL, USA.Department of Bioengineering, University of Illinois at Chicago, Chicago, IL, USA.Hinsdale Central High School, Hinsdale, IL, USA.Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, IL, USA.Department of Ophthalmology, National Taiwan University, Taipei, Taiwan.Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, IL, USA.Department of Bioengineering, University of Illinois at Chicago, Chicago, IL, USA. Department of Ophthalmology, Antalya Training and Research Hospital, Antalya, Turkey.Department of Bioengineering, University of Illinois at Chicago, Chicago, IL, USA. Department of Ophthalmology and Visual Sciences, University of Illinois at Chicago, Chicago, IL, USA.

Pub Type(s)

Journal Article
Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

Language

eng

PubMed ID

32855839

Citation

Le, David, et al. "Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy." Translational Vision Science & Technology, vol. 9, no. 2, 2020, p. 35.
Le D, Alam M, Yao CK, et al. Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy. Transl Vis Sci Technol. 2020;9(2):35.
Le, D., Alam, M., Yao, C. K., Lim, J. I., Hsieh, Y. T., Chan, R. V. P., Toslak, D., & Yao, X. (2020). Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy. Translational Vision Science & Technology, 9(2), 35. https://doi.org/10.1167/tvst.9.2.35
Le D, et al. Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy. Transl Vis Sci Technol. 2020;9(2):35. PubMed PMID: 32855839.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy. AU - Le,David, AU - Alam,Minhaj, AU - Yao,Cham K, AU - Lim,Jennifer I, AU - Hsieh,Yi-Ting, AU - Chan,Robison V P, AU - Toslak,Devrim, AU - Yao,Xincheng, Y1 - 2020/07/02/ PY - 2019/09/30/received PY - 2020/04/05/accepted PY - 2020/8/29/entrez PY - 2020/8/29/pubmed PY - 2020/8/29/medline KW - artificial intelligence KW - deep learning KW - detection KW - diabetic retinopathy KW - screening SP - 35 EP - 35 JF - Translational vision science & technology JO - Transl Vis Sci Technol VL - 9 IS - 2 N2 - Purpose: To test the feasibility of using deep learning for optical coherence tomography angiography (OCTA) detection of diabetic retinopathy. Methods: A deep-learning convolutional neural network (CNN) architecture, VGG16, was employed for this study. A transfer learning process was implemented to retrain the CNN for robust OCTA classification. One dataset, consisting of images of 32 healthy eyes, 75 eyes with diabetic retinopathy (DR), and 24 eyes with diabetes but no DR (NoDR), was used for training and cross-validation. A second dataset consisting of 20 NoDR and 26 DR eyes was used for external validation. To demonstrate the feasibility of using artificial intelligence (AI) screening of DR in clinical environments, the CNN was incorporated into a graphical user interface (GUI) platform. Results: With the last nine layers retrained, the CNN architecture achieved the best performance for automated OCTA classification. The cross-validation accuracy of the retrained classifier for differentiating among healthy, NoDR, and DR eyes was 87.27%, with 83.76% sensitivity and 90.82% specificity. The AUC metrics for binary classification of healthy, NoDR, and DR eyes were 0.97, 0.98, and 0.97, respectively. The GUI platform enabled easy validation of the method for AI screening of DR in a clinical environment. Conclusions: With a transfer learning process for retraining, a CNN can be used for robust OCTA classification of healthy, NoDR, and DR eyes. The AI-based OCTA classification platform may provide a practical solution to reducing the burden of experienced ophthalmologists with regard to mass screening of DR patients. Translational Relevance: Deep-learning-based OCTA classification can alleviate the need for manual graders and improve DR screening efficiency. SN - 2164-2591 UR - https://www.unboundmedicine.com/medline/citation/32855839/Transfer_Learning_for_Automated_OCTA_Detection_of_Diabetic_Retinopathy_ L2 - https://tvst.arvojournals.org/article.aspx?doi=10.1167/tvst.9.2.35 DB - PRIME DP - Unbound Medicine ER -