Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy

Le, David; Alam, Minhaj Nur; Yao, Cham K.; Lim, Jennifer I.; Hsieh, Yi‐Ting; Chan, Robison Vernon Paul; Toslak, Devrim; Yao, Xincheng

doi:10.1167/tvst.9.2.35

Cited by 104 publications

(63 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Device implementation of image alignment and tracking for longitudinal data will better serial assessment of progressive retinal diseases, including AMD and DR. As these improvements become commercially available, the clinical applicability and utility of OCTA will continue to expand and could have lasting implications in the way we image the retinal vasculature. Moreover, application of machine learning to OCTA will yield insights into new pathologic signals that were previously overlooked that could greatly impact the clinical management of retinal disease [ 89 , 90 ].…”

Section: The Future Of Octamentioning

confidence: 99%

A practical guide to optical coherence tomography angiography interpretation

2020

View full text Add to dashboard Cite

Background Optical coherence tomography angiography (OCTA) can image the retinal vasculature in vivo, without the need for contrast dye. This technology has been commercially available since 2014, however, much of its use has been limited to the research setting. Over time, more clinical practices have adopted OCTA imaging. While countless publications detail OCTA’s use for the study of retinal microvasculature, few studies outline OCTA’s clinical utility. Body This review provides an overview of OCTA imaging and details tips for successful interpretation. The review begins with a summary of OCTA technology and artifacts that arise from image acquisition. New methods and best practices to prevent image artifacts are discussed. OCTA has the unique ability among retinovascular imaging modalities to individually visualize each retinal plexus. Slabs offered in standard OCTA devices are reviewed, and clinical uses for each slab are outlined. Lastly, the use of OCTA for the clinical interpretation of retinal pathology, such as diabetic retinopathy and age-related macular degeneration, is discussed. Conclusion OCTA is evolving from a scientific tool to a clinical imaging device. This review provides a toolkit for successful image interpretation in a clinical setting.

show abstract

Section: The Future Of Octamentioning

confidence: 99%

A practical guide to optical coherence tomography angiography interpretation

2020

View full text Add to dashboard Cite

show abstract

“…Deep learning algorithms have also been applied recently to retinal optical coherence tomography (OCT) and OCT angiography (OCTA) images for automated diagnosis of DR, because these imaging techniques provide higher sensitivity to detect early diabetic retinal changes [28]. Diagnostic accuracy studies have not been published yet, but preliminary internal validation tests show comparable diagnostic accuracy to the one using fundus images: Sandhu et al [29] reported their algorithm to have sensitivity of 93% and specificity of 95%, and the work of Li et al [30] achieved a sensitivity of 90% and specificity of 95%; using OCTA images, sensitivity of 98% and specificity of 87% were reported by Sandhu et al [31], and the system of Le et al [32] achieved 84% sensitivity and 91% specificity.…”

Section: Discussionmentioning

confidence: 99%

Screening for Diabetic Retinopathy Using an Automated Diagnostic System Based on Deep Learning: Diagnostic Accuracy Assessment

et al. 2020

View full text Add to dashboard Cite

Purpose: To evaluate the diagnostic accuracy of a diagnostic system software for the automated screening of diabetic retinopathy (DR) on digital colour fundus photographs, the 2019 Convolutional Neural Network (CNN) model with Inception-V3. Methods: In this cross-sectional study 295 fundus images were analysed by the CNN model and compared to a panel of ophthalmologists. Images were obtained from a dataset acquired within a screening programme. Diagnostic accuracy measures and respective 95% confidence intervals (CI) were calculated. Results: The sensitivity and specificity of the CNN model in diagnosing referable DR was 81% [95% confidence interval (CI), 66%−90%] and 97% (95% CI, 95%−99%), respectively. Positive predictive value was 86% (95% CI, 72%−94%) and negative predictive value 96% (95% CI, 93%−98%). The positive likelihood ratio was 33 (95% CI, 15−75) and the negative was 0.20 (95% CI, 0.11−0.35). Its clinical impact is demonstrated by the change observed in the pre-test probability of referable DR (assuming a prevalence of 16%) to a post-test probability for a positive test result of 86% and for a negative test result of 4%. Conclusion: A CNN model negative test result safely excludes DR and its use may significantly reduce the burden of ophthalmologists at reading centres.

show abstract

“…Most of the existing works focused on the diagnosis of AMD using OCT or Color Fundus Photography. Moreover, published works on OCTA images involved other retinal diseases such as Diabetic Retinopathy (DR) [17].…”

Section: Cnn Architecture and Transfer Learningmentioning

confidence: 99%

“…Results showed a ROC-AUC of 0.89 at the B-scan levels and 0.91 for volumes. Hwang et al [22] In what concerns the use of OCTA in DL, Le et al [17] tested the feasibility of using DL for DR detection from OCTA including 77 patients and 20 control subjects. The authors applied transfer learning on a VGG16 network for robust OCTA classification.…”

Section: Cnn Architecture and Transfer Learningmentioning

confidence: 99%

Choroidal Neovascularization Screening on OCT-Angiography Choriocapillaris Images by Convolutional Neural Networks

et al. 2021

View full text Add to dashboard Cite

Choroidal Neovascularization (CNV) is the advanced stage of Age-related Macular Degeneration (AMD), which is the leading cause of irreversible visual loss for elder people in developed countries. Optical Coherence Tomography Angiography (OCTA) is a recent non-invasive imaging technique widely used nowadays in diagnosis and follow-up of CNV. In this study, an automatic screening of CNV based on deep learning is performed using OCTA choriocapillaris images. CNV eyes (advanced wet AMD) are diagnosed among healthy eyes (no AMD) and eyes with drusen (intermediate AMD). An OCTA dataset of 1396 images is used to train and evaluate the model. A pre-trained convolutional neural network (CNN) is fine-tuned and validated on 80% of the dataset while the remaining 20% is used independently for predictions. The model can accurately detect CNV on the test set with an accuracy of 89.74%, precision of 0.96 and 0.99 area under the curve of the receiver operating characteristic. A good overall classification accuracy of 88.46% is obtained on a balanced test set. Detailed analysis of misclassified images shows that they are also considered ambiguous images for expert clinicians. This novel CNN-based application is truly a breakthrough to assist clinicians in the challenging task of screening for neovascular complications.

show abstract

Transfer Learning for Automated OCTA Detection of Diabetic Retinopathy

Cited by 104 publications

References 39 publications

A practical guide to optical coherence tomography angiography interpretation

A practical guide to optical coherence tomography angiography interpretation

Screening for Diabetic Retinopathy Using an Automated Diagnostic System Based on Deep Learning: Diagnostic Accuracy Assessment

Choroidal Neovascularization Screening on OCT-Angiography Choriocapillaris Images by Convolutional Neural Networks

Contact Info

Product

Resources

About