Artificial intelligence and deep learning in ophthalmology

Ting, Daniel Shu Wei; Pasquale, Louis R.; Peng, Lily; Campbell, J. Peter; Lee, Aaron; Raman, Rajiv; Tan, Gavin Siew Wei; Schmetterer, Leopold; Keane, Pearse A.; Wong, Tien Yin

doi:10.1136/bjophthalmol-2018-313173

Cited by 852 publications

(606 citation statements)

References 66 publications

Supporting

Mentioning

573

Contrasting

Unclassified

Order By: Relevance

“…Transfer learning is a training method to adopt some weights of a pre-trained CNN and appropriately re-train the CNN to optimize the weights for a specific task, i.e., AI classification of retinal images [31]. In fundus photography, transfer learning has been explored to conduct artery-vein segmentation [32], glaucoma detection [33,34], and diabetic macular thinning assessment [35]. Recently, transfer learning has also been explored in OCT for detecting choroidal neovascularization (CNV) and diabetic macular edema (DME) [31], and AMD [36].…”

Section: Introductionmentioning

confidence: 99%

Deep learning for objective OCTA detection of diabetic retinopathy

Alam

Lim

et al. 2020

Ophthalmic Technologies XXX

View full text Add to dashboard Cite

Purpose:To test the feasibility of using deep learning for optical coherence tomography angiography (OCTA) detection of diabetic retinopathy (DR). Methods:A deep learning convolutional neural network (CNN) architecture VGG16 was employed for this study. A transfer learning process was implemented to re-train the CNN for robust OCTA classification.In order to demonstrate the feasibility of using this method for artificial intelligence (AI) screening of DR in clinical environments, the re-trained CNN was incorporated into a custom developed GUI platform which can be readily operated by ophthalmic personnel. Results:With last nine layers re-trained, CNN architecture achieved the best performance for automated OCTA classification. The overall accuracy of the re-trained classifier for differentiating healthy, NoDR, and NPDR was 87.27%, with 83.76% sensitivity and 90.82% specificity. The AUC metrics for binary classification of healthy, NoDR and DR 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. Conclusion:With a transfer leaning process to adopt the early layers for simple feature analysis and to retrain the upper layers for fine feature analysis, the CNN architecture VGG16 can be used for robust OCTA classification of healthy, NoDR, and NPDR eyes. Translational Relevance: OCTA can capture microvascular changes in early DR. A transfer learning process enables robust implementation of convolutional neural network (CNN) for automated OCTA classification of DR. detection and adequate treatment, more than 95% of DR related vision loss can be preventable [2]. Retinal vascular abnormalities, such as microaneurysms, hard exudates, retinal edema, venous beading, intraretinal microvascular anomalies and retinal hemorrhages are common DR findings [3]. Therefore, imaging examination of retinal vasculature is important for DR diagnosis and treatment evaluation. Traditional fundus photography provides limited sensitivity to reveal subtle abnormality correlated with early DR [4][5][6][7]. Fluorescein angiography (FA) can be used to improve imaging sensitivity of retinal vascular distortions in DR [8,9], but FA requires intravenous dye injections which may produce side effects and requires following monitoring and management carefully. Optical coherence tomography angiography (OCTA) provides a noninvasive method for better visualization of retinal vasculatures [10]. OCTA allows visualization of multiple retinal layers with high resolution, and thus it is more sensitive than FA in detecting subtle vascular distortions correlated with early eye conditions [11,12].Recent development of quantitative OCTA opens a unique opportunity to enable computer-aided disease detection and AI classification of eye conditions. Quantitative OCTA analysis has been explored for objective assessment of DR [13][14][15][16], age-related macular degeneration (AMD) [17,18], vein occlusion (VO) [19][20][21][22], SCR [23][24][25], etc. Supervised machine learning h...

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning for objective OCTA detection of diabetic retinopathy

Alam

Lim

et al. 2020

Ophthalmic Technologies XXX

View full text Add to dashboard Cite

show abstract

“…Over the last few years, deep learning (DL) has been proposed for automated analysis of retinal fundus images. 5 DR is relatively unambiguous and DL models have shown excellent detection performance. For example, Gulshan et al 6 obtained an area under the receiver operating curve (ROC-AUC) of 0.99 for detection of referable DR.…”

Section: Introductionmentioning

confidence: 99%

Direct classification of type 2 diabetes from retinal fundus images in a population-based sample from The Maastricht Study

Heslinga

Pluim

Houben

et al. 2020

Medical Imaging 2020: Computer-Aided Diagnosis

View full text Add to dashboard Cite

Type 2 Diabetes (T2D) is a chronic metabolic disorder that can lead to blindness and cardiovascular disease. Information about early stage T2D might be present in retinal fundus images, but to what extent these images can be used for a screening setting is still unknown. In this study, deep neural networks were employed to differentiate between fundus images from individuals with and without T2D. We investigated three methods to achieve high classification performance, measured by the area under the receiver operating curve (ROC-AUC). A multi-target learning approach to simultaneously output retinal biomarkers as well as T2D works best (AUC = 0.746 [±0.001]). Furthermore, the classification performance can be improved when images with high prediction uncertainty are referred to a specialist. We also show that the combination of images of the left and right eye per individual can further improve the classification performance (AUC = 0.758 [±0.003]), using a simple averaging approach. The results are promising, suggesting the feasibility of screening for T2D from retinal fundus images.

show abstract

“…To date, most AI applications have focused on adult ophthalmic diseases, as discussed by several reviews [4][5][6][7][8][9][10][11]. Comparatively little progress has been made in applying AI and ML techniques to pedi-atric ophthalmology, despite the pressing need.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence for pediatric ophthalmology

Reid

Eaton

2019

Current Opinion in Ophthalmology

View full text Add to dashboard Cite

Purpose of reviewDespite the impressive results of recent artificial intelligence (AI) applications to general ophthalmology, comparatively less progress has been made toward solving problems in pediatric ophthalmology using similar techniques. This article discusses the unique needs of pediatric ophthalmology patients and how AI techniques can address these challenges, surveys recent applications of AI to pediatric ophthalmology, and discusses future directions in the field. Recent findingsThe most significant advances involve the automated detection of retinopathy of prematurity (ROP), yielding results that rival experts. Machine learning (ML) has also been successfully applied to the classification of pediatric cataracts, prediction of post-operative complications following cataract surgery, detection of strabismus and refractive error, prediction of future high myopia, and diagnosis of reading disability via eye tracking. In addition, ML techniques have been used for the study of visual development, vessel segmentation in pediatric fundus images, and ophthalmic image synthesis. SummaryAI applications could significantly benefit clinical care for pediatric ophthalmology patients by optimizing disease detection and grading, broadening access to care, furthering scientific discovery, and improving clinical efficiency. These methods need to match or surpass physician performance in clinical trials before deployment with patients. Due to widespread use of closed-access data sets and software implementations, it is difficult to directly compare the performance of these approaches, and reproducibility is poor. Open-access data sets and software implementations could alleviate these issues, and encourage further AI applications to pediatric ophthalmology.

show abstract

Artificial intelligence and deep learning in ophthalmology

Cited by 852 publications

References 66 publications

Deep learning for objective OCTA detection of diabetic retinopathy

Deep learning for objective OCTA detection of diabetic retinopathy

Direct classification of type 2 diabetes from retinal fundus images in a population-based sample from The Maastricht Study

Artificial intelligence for pediatric ophthalmology

Contact Info

Product

Resources

About