Internal Carotid Artery Stenosis and Ipsilateral Subretinal Drusenoid Deposits.

Purpose: Subretinal drusenoid deposits (SDDs) in age-related macular degeneration (AMD) are strongly associated with vasculopathies such as myocardial infarction and ischemic stroke. This study evaluates ischemic stroke subjects for SDDs to determine whether ocular hypoperfusion from internal carotid artery (ICA) stenosis is associated with ipsilateral SDDs. Methods: A cross-sectional study at Mount Sinai Hospital recruited 39 subjects with ischemic stroke (aged 52-90; 18 women, 21 men); 28 completed all study procedures. Computed tomography (CT) of the head and neck evaluated 54/56 ICAs for stenosis criteria: none (n = 33), mild (n = 12), moderate (n = 3), severe (n = 3), and complete (n = 3). Spectral-domain optical coherence tomography (SD-OCT) scans were read to consensus by two masked graders for soft drusen, SDDs and choroidal thickness (CTh; choroidal thinning = CTh < 250 µm). Univariate testing was done with Fisher's exact test. Multivariate logistic regression models tested age, gender, and ICA stenosis as covariates. Results: Moderate or more ICA stenosis (≥50%-69%) was significantly associated with ipsilateral choroidal thinning (P = 0.021) and ipsilateral SDDs (P = 0.005); the latter were present distal to six of nine stenosed ICAs versus five of 33 normal ICAs. Mild ICA stenosis (≥1%-49%) was not significantly associated with ipsilateral SDDs. Multivariate regression found that older age (P = 0.015) and moderate or more ICA stenosis (P = 0.011) remained significant independent risks for ipsilateral SDDs. Conclusions: At least moderate ICA stenosis (≥50%-69%) is strongly associated with ipsilateral SDDs and choroidal thinning, supporting downstream ophthalmic artery and choroidal hypoperfusion from ICA stenosis as the mechanism for SDD formation. SDDs may thus serve as sensitive biomarkers for ischemic stroke and other vascular diseases.

SUBRETINAL DRUSENOID DEPOSITS AND SOFT DRUSEN: Are They Markers for Distinct Retinal Diseases?

PURPOSE: Soft drusen and subretinal drusenoid deposits (SDDs) characterize two pathways to advanced age-related macular degeneration (AMD), with distinct genetic risks, serum risks, and associated systemic diseases. METHODS: One hundred and twenty-six subjects with AMD were classified as SDD (with or without soft drusen) or non-SDD (drusen only) by retinal imaging, with serum risks, genetic testing, and histories of cardiovascular disease (CVD) and stroke. RESULTS: There were 62 subjects with SDD and 64 non-SDD subjects, of whom 51 had CVD or stroke. SDD correlated significantly with lower mean serum high-density lipoprotein (61 ± 18 vs. 69 ± 22 mg/dL, P = 0.038, t-test), CVD and stroke (34 of 51 SDD, P = 0.001, chi square), ARMS2 risk allele (P = 0.019, chi square), but not with CFH risk allele (P = 0.66). Non-SDD (drusen only) correlated/trended with APOE2 (P = 0.032) and CETP (P = 0.072) risk alleles (chi square). Multivariate independent risks for SDD were CVD and stroke (P = 0.008) and ARMS2 homozygous risk (P = 0.038). CONCLUSION: Subjects with subretinal drusenoid deposits and non-SDD subjects have distinct systemic associations and serum and genetic risks. Subretinal drusenoid deposits are associated with CVD and stroke, ARMS2 risk, and lower high-density lipoprotein; non-SDDs are associated with higher high-density lipoprotein, CFH risk, and two lipid risk genes. These and other distinct associations suggest that these lesions are markers for distinct diseases.

Optimized Prediction Models from Fundus Imaging and Genetics for Late Age-Related Macular Degeneration.

Age-related macular degeneration (AMD) is a leading cause of blindness in the developed world. In this study, we compare the performance of retinal fundus images and genetic-information-based machine learning models for the prediction of late AMD. Using data from the Age-related Eye Disease Study, we built machine learning models with various combinations of genetic, socio-demographic/clinical, and retinal image data to predict late AMD using its severity and category in a single visit, in 2, 5, and 10 years. We compared their performance in sensitivity, specificity, accuracy, and unweighted kappa. The 2-year model based on retinal image and socio-demographic (S-D) parameters achieved a sensitivity of 91.34%, specificity of 84.49% while the same for genetic and S-D-parameters-based model was 79.79% and 66.84%. For the 5-year model, the retinal image and S-D-parameters-based model also outperformed the genetic and S-D parameters-based model. The two 10-year models achieved similar sensitivities of 74.24% and 75.79%, respectively, but the retinal image and S-D-parameters-based model was otherwise superior. The retinal-image-based models were not further improved by adding genetic data. Retinal imaging and S-D data can build an excellent machine learning predictor of developing late AMD over 2-5 years; the retinal imaging model appears to be the preferred prognostic tool for efficient patient management.

Combined automated screening for age-related macular degeneration and diabetic retinopathy in primary care settings.

BACKGROUND: Age-related macular degeneration (AMD) and diabetic retinopathy (DR) are among the leading causes of blindness in the United States and other developed countries. Early detection is the key to prevention and effective treatment. We have built an artificial intelligence-based screening system which utilizes a cloud-based platform for combined large scale screening through primary care settings for early diagnosis of these diseases. METHODS: iHealthScreen Inc., an independent medical software company, has developed automated AMD and DR screening systems utilizing a telemedicine platform based on deep machine learning techniques. For both diseases, we prospectively imaged both eyes of 340 unselected non-dilated subjects over 50 years of age. For DR specifically, 152 diabetic patients at New York Eye and Ear faculty retina practices, ophthalmic and primary care clinics in New York city with color fundus cameras. Following the initial review of the images, 308 images with other confounding conditions like high myopia and vascular occlusion, and poor quality were excluded, leaving 676 eligible images for AMD and DR evaluation. Three ophthalmologists evaluated each of the images, and after adjudication, the patients were determined referrable or non-referable for AMD DR. Concerning AMD, 172 were labeled referable (intermediate or late), and 504 were non-referable (no or early). Concurrently, regarding DR, 33 were referable (moderate or worse), and 643 were non-referable (none or mild). All images were uploaded to iHealthScreen's telemedicine platform and analyzed by the automated systems for both diseases. The system performances are tested on per eye basis with sensitivity, specificity, accuracy, and kappa scores with respect to the professional graders. RESULTS: In identifying referable DR, the system achieved a sensitivity of 97.0% and a specificity of 96.3%, and a kappa score of 0.70 on this prospective dataset. For AMD, the sensitivity was 86.6%, the specificity of 92.1%, and a kappa score of 0.76. CONCLUSIONS: The AMD and DR screening tools achieved excellent performance operating together to identify two retinal diseases prospectively in mixed datasets, demonstrating the feasibility of such tools in the early diagnosis of eye diseases. These early screening tools will help create an even more comprehensive system capable of being trained on other retinal pathologies, a goal within reach for public health deployment.

An Artificial-Intelligence- and Telemedicine-Based Screening Tool to Identify Glaucoma Suspects from Color Fundus Imaging.

RESULTS: The system achieved an accuracy of 89.67% (sensitivity, 83.33%; specificity, 93.89%; and AUC, 0.93). For external validation, the Retinal Fundus Image Database for Glaucoma Analysis dataset, which has 638 gradable quality images, was used. Here, the model achieved an accuracy of 83.54% (sensitivity, 80.11%; specificity, 84.96%; and AUC, 0.85). CONCLUSIONS: Having demonstrated an accurate and fully automated glaucoma-suspect screening system that can be deployed on telemedicine platforms, we plan prospective trials to determine the feasibility of the system in primary-care settings.

Automated diabetic retinopathy screening for primary care settings using deep learning.

Diabetic Retinopathy (DR) is one of the leading causes of blindness in the United States and other high-income countries. Early detection is key to prevention, which could be achieved effectively with a fully automated screening tool performing well on clinically relevant measures in primary care settings. We have built an artificial intelligence-based tool on a cloud-based platform for large-scale screening of DR as referable or non-referable. In this paper, we aim to validate this tool built using deep learning based techniques. The cloud-based screening model was developed and tested using deep learning techniques with 88702 images from the Kaggle dataset and externally validated using 1748 high-resolution images of the retina (or fundus images) from the Messidor-2 dataset. For validation in the primary care settings, 264 images were taken prospectively from two diabetes clinics in Queens, New York. The images were uploaded to the cloud-based software for testing the automated system as compared to expert ophthalmologists' evaluations of referable DR. Measures used were area under the curve (AUC), sensitivity, and specificity of the screening model with respect to professional graders. The screening system achieved a high sensitivity of 99.21% and a specificity of 97.59% on the Kaggle test dataset with an AUC of 0.9992. The system was also externally validated in Messidor-2, where it achieved a sensitivity of 97.63% and a specificity of 99.49% (AUC, 0.9985). On primary care data, the sensitivity was 92.3% overall (12/13 referable images are correctly identified), and overall specificity was 94.8% (233/251 non-referable images). The proposed DR screening tool achieves state-of-the-art performance among the publicly available datasets: Kaggle and Messidor-2 to the best of our knowledge. The performance on various clinically relevant measures demonstrates that the tool is suitable for screening and early diagnosis of DR in primary care settings.

Artificial Intelligence to Stratify Severity of Age-Related Macular Degeneration (AMD) and Predict Risk of Progression to Late AMD.

Purpose: To build and validate artificial intelligence (AI)-based models for AMD screening and for predicting late dry and wet AMD progression within 1 and 2 years. Methods: The dataset of the Age-related Eye Disease Study (AREDS) was used to train and validate our prediction model. External validation was performed on the Nutritional AMD Treatment-2 (NAT-2) study. First Step: An ensemble of deep learning screening methods was trained and validated on 116,875 color fundus photos from 4139 participants in the AREDS study to classify them as no, early, intermediate, or advanced AMD and further stratified them along the AREDS 12 level severity scale. Second step: the resulting AMD scores were combined with sociodemographic clinical data and other automatically extracted imaging data by a logistic model tree machine learning technique to predict risk for progression to late AMD within 1 or 2 years, with training and validation performed on 923 AREDS participants who progressed within 2 years, 901 who progressed within 1 year, and 2840 who did not progress within 2 years. For those found at risk of progression to late AMD, we further predicted the type (dry or wet) of the progression of late AMD. Results: For identification of early/none vs. intermediate/late (i.e., referral level) AMD, we achieved 99.2% accuracy. The prediction model for a 2-year incident late AMD (any) achieved 86.36% accuracy, with 66.88% for late dry and 67.15% for late wet AMD. For the NAT-2 dataset, the 2-year late AMD prediction accuracy was 84%. Conclusions: Validated color fundus photo-based models for AMD screening and risk prediction for late AMD are now ready for clinical testing and potential telemedical deployment. Translational Relevance: Noninvasive, highly accurate, and fast AI methods to screen for referral level AMD and to predict late AMD progression offer significant potential improvements in our care of this prevalent blinding disease.

A New and Improved Method for Automated Screening of Age-Related Macular Degeneration Using Ensemble Deep Neural Networks.

In this paper, we provide a new framework on deep learning based automated screening method for finding individuals at risk of developing Age-related Macular Degeneration (AMD). We studied the appropriateness of using the transfer learning to screen AMD by using color fundus images. We make use of the Age-Related Eye Disease Study (AREDS) dataset with nearly 150,000 images, which also provided qualitative grading information by expert graders and ophthalmologists. We use ensemble learning technique with two deep neural networks, namely, Inception-ResNet-V2 and Xception with a custom fine-tuning approach. For our study, we have identified two experiments that are most useful in the screening of AMD. First, we have categorized the images into two classes based on the clinical significance: None or early AMD and Intermediate or Advanced AMD. Second, we have categorized the images into four classes: No AMD, early AMD, Intermediate AMD and Advanced AMD. On AREDS dataset, we have achieved an accuracy of over 95.3% for two-class experiment with our ensemble method. With accuracies ranging from 86% (for four-class) to 95.3% (for two-class), we have demonstrated that the training of a deep neural network with the transfer of learned features with a sufficient number of images fares very well and is comparable to human grading.