Color Fundus Images Research Articles

Objective evaluation of choroidal melanin loss in patients with Vogt\u2013Koyanagi\u2013Harada disease using polarization-sensitive optical coherence tomography

In this study, sunset glow fundus was evaluated in patients with Vogt–Koyanagi–Harada (VKH) disease using polarization-sensitive optical coherence tomography (PS-OCT). We evaluated 40 VKH eyes (20 patients) and 59 healthy eyes (59 age-matched controls). VKH eyes were divided into three groups according to color fundus images: sunset (17 eyes), potential sunset (13 eyes), and non-sunset (10 eyes). Choroidal melanin thickness (ChMeT) and the choroidal melanin thickness ratio (ChMeTratio) were calculated based on the degree of polarization uniformity from PS-OCT. ChMeT was significantly lower in sunset eyes than in non-sunset or control eyes (P = 0.003). The ChMeTratios of sunset or potential sunset eyes were significantly lower than those of non-sunset or control eyes (P = 0.04). Regional evaluation of ChMeT and the ChMeTratio showed that choroidal depigmentation predominantly occurred in the macula’s outer ring area (P = 0.002). The areas under receiver operating characteristic curves discriminating combined sunset (sunset and potential sunset) from non-sunset eyes were 0.983 and 0.997 for ChMeT and the ChMeTratio, respectively. Time course evaluation of 12 eyes from disease onset showed that ChMeT and the ChMeTratio significantly decreased over time. PS-OCT may be useful for objectively evaluating choroidal depigmentation in patients with VKH disease.

Dual-Branch Network With Dual-Sampling Modulated Dice Loss for Hard Exudate Segmentation in Color Fundus Images

Automated segmentation of hard exudates in colour fundus images is a challenge task due to issues of extreme class imbalance and enormous size variation. This paper aims to tackle these issues and proposes a dual-branch network with dual-sampling modulated Dice loss. It consists of two branches: large hard exudate biased segmentation branch and small hard exudate biased segmentation branch. Both of them are responsible for their own duties separately. Furthermore, we propose a dual-sampling modulated Dice loss for the training such that our proposed dual-branch network is able to segment hard exudates in different sizes. In detail, for the first branch, we use a uniform sampler to sample pixels from predicted segmentation mask for Dice loss calculation, which leads to this branch naturally be biased in favour of large hard exudates as Dice loss generates larger cost on misidentification of large hard exudates than small hard exudates. For the second branch, we use a re-balanced sampler to oversample hard exudate pixels and undersample background pixels for loss calculation. In this way, cost on misidentification of small hard exudates is enlarged, which enforces the parameters in the second branch fit small hard exudates well. Considering that large hard exudates are much easier to be correctly identified than small hard exudates, we propose an easy-to-difficult learning strategy by adaptively modulating the losses of two branches. We evaluate our proposed method on two public datasets and the results demonstrate that ours achieves state-of-the-art performance.

Graph-Based Region and Boundary Aggregation for Biomedical Image Segmentation.

Segmentation is a fundamental task in biomedical image analysis. Unlike the existing region-based dense pixel classification methods or boundary-based polygon regression methods, we build a novel graph neural network (GNN) based deep learning framework with multiple graph reasoning modules to explicitly leverage both region and boundary features in an end-to-end manner. The mechanism extracts discriminative region and boundary features, referred to as initialized region and boundary node embeddings, using a proposed Attention Enhancement Module (AEM). The weighted links between cross-domain nodes (region and boundary feature domains) in each graph are defined in a data-dependent way, which retains both global and local cross-node relationships. The iterative message aggregation and node update mechanism can enhance the interaction between each graph reasoning module's global semantic information and local spatial characteristics. Our model, in particular, is capable of concurrently addressing region and boundary feature reasoning and aggregation at several different feature levels due to the proposed multi-level feature node embeddings in different parallel graph reasoning modules. Experiments on two types of challenging datasets demonstrate that our method outperforms state-of-the-art approaches for segmentation of polyps in colonoscopy images and of the optic disc and optic cup in colour fundus images. The trained models will be made available at: https://github.com/smallmax00/Graph_Region_Boudnary.

Retinal Blood Vessels and Optic Disc Segmentation Using U-Net

A color fundus image is a photograph obtained using a fundus camera of the inner wall of the eyeball. In the image, doctors may see changes in the retinal vessels, which can be used to diagnose various dangerous disorders such as arteriosclerosis, some macular degeneration related to age, and glaucoma. To diagnose certain disorders as early as possible, automatic segmentation of retinal arteries is used to help the doctors. Also, it is a challenge for the medical community to analyze the image with the right procedure to diagnose the disorders with high accuracy. Furthermore, this will help the doctor to make the right decision on effective treatment. Hence, the authors have implemented an enhanced architecture called U-Net to segment retinal vessels in this paper. The proposed conventional U-Net permits using all the accessible spatial setting information by adding the multiscale input layer and a thick square to the conventional U-Net in terms of improving the accuracy level of image segmentation. It achieved 95.6% accuracy with a comparatively traditional U-Net model. Moreover, the segmentation results have proved that the proposed approach outperformed in detecting most complex low-contrast blood vessels even when they are very thin. The task of segmenting vessels in retinal images is known as retinal vessel segmentation. Blood vessel density can be assessed using dense pixel values. Data augmentation and analytics play a major role in building the true value of eye blood vessels for medical diagnosis. The proposed method is very promising in the automatic segmentation of retinal arteries.

Comparison of early diabetic retinopathy staging in asymptomatic patients between autonomous AI-based screening and human-graded ultra-widefield colour fundus images

Learning ObjectivesUpon completion of this activity, participants will:Compare diabetic retinopathy (DR) severity scores of ophthalmologically asymptomatic people with diabetes between outputs from an artificial intelligence (AI)-based system and human-graded ultra-widefield (UWF) color fundus imaging, according to a clinical study.Compare manual 7F-mask gradings vs UWF full-field gradings and describe the correlation with patient characteristics, according to a clinical study.Describe clinical implications of the comparison between the DR severity scores of ophthalmologically asymptomatic people with diabetes outputs using outputs from an AI-based system and human-graded UWF color fundus imaging, according to a clinical study.Accreditation StatementsIn support of improving patient care, this activity has been planned and implemented by Medscape, LLC and Springer Nature. Medscape, LLC is jointly accredited by the Accreditation Council for Continuing Medical Education (ACCME), the Accreditation Council for Pharmacy Education (ACPE), and the American Nurses Credentialing Center (ANCC), to provide continuing education for the healthcare team.Medscape, LLC designates this Journal-based CME activity for a maximum of 1.0 AMA PRA Category 1 Credit(s)™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.Successful completion of this CME activity, which includes participation in the evaluation component, enables the participant to earn up to 1.0 MOC points in the American Board of Internal Medicine’s (ABIM) Maintenance of Certification (MOC) program. Participants will earn MOC points equivalent to the amount of CME credits claimed for the activity. It is the CME activity provider’s responsibility to submit participant completion information to ACCME for the purpose of granting ABIM MOC credit.All other clinicians completing this activity will be issued a certificate of participation. To participate in this journal CME activity: (1) review the learning objectives and author disclosures; (2) study the education content; (3) take the post-test with a 75% minimum passing score and complete the evaluation at www.medscape.org/journal/eye; (4) view/print certificate.Credit hours1.0Release date:Expiration date:Post-test link:https://www.medscape.org/eye/posttest964708Authors/Editors disclosure informationS.S. has disclosed the following relevant financial relationships: Served as consultant or advisor for Allergan, Inc.; Bayer HealthCare Pharmaceuticals; Boehringer Ingelheim Pharmaceuticals, Inc.; Heidelberg Pharma GmbH; Novartis Pharmaceuticals Corporation; Optos; Roche; Served as a speaker or a member of a speakers bureau for Allergan, Inc.; Bayer HealthCare Pharmaceuticals; Boehringer Ingelheim Pharmaceuticals, Inc.; Novartis Pharmaceuticals Corporation; Optos; Roche; Received research funding from Bayer HealthCare Pharmaceuticals; Boehringer Ingelheim Pharmaceuticals, Inc.; Novartis Pharmaceuticals Corporation; Optos; Is employed by or has an executive role as Data Monitoring Chair for Phase 2 study sponsored by Bayer HealthCare Pharmaceuticals; Scientific Committee Member of EyeBio Steering Committee for FOCUS sponsored by Novo Nordisk. Other: Trustee member for Macular Society Scientific/Research Advisory Committee Member for Sight UK, Retina UK, Macular Society.Journal CME author disclosure informationLaurie Barclay has disclosed no relevant financial relationships.

A Novel Approach for Identification of Biomakers in Diabetic Retinopathy Recognition

In the emergence of anti-Antivascular endothelial growth factor (VEGF) drugs such as ranibizumab and bevacizumab, it has become obvious that the presence of outer retinal and subretinal fluid is the primary signal of the need for anti-VEGF therapy, and used to identify disease activity and assist diabetic retinopathy treatment. Despite advancements in diabetic retinopathy (DR) treatments, early detection is critical for DR management and remains a significant barrier. Clinical DR can be distinguished from non proliferative DR without visible vision loss and vision-threatening consequences such as macular edoema and proliferative retinopathy by retinal alterations in diabetes. The proposed method aggrandize the process of accurate detection of biomakers responsible for higher risk of diabetic retinopathy development in color fundus images. Furthermore, the proposed approach could be employed to quantify these lesions and their distributions efficientively as evident in the experimentation results.

Multimodal Imaging, OCT B-Scan Localization, and En Face OCT Detection of Macular Hyperpigmentation in Eyes with Intermediate Age-Related Macular Degeneration.

PurposeMultimodal imaging was used to identify and characterize the cause of hyperpigmentation seen on color fundus images (CFIs) of eyes with intermediate age-related macular degeneration (iAMD).DesignRetrospective review of a prospective study.ParticipantsPatients with iAMD.MethodsColor fundus images with macular hyperpigmentation were compared with same-day images obtained using fundus autofluorescence (FAF), near infrared reflectance (NIR), and swept-source (SS) OCT imaging. Two SS OCT en face slabs were generated: a retinal slab to identify hyperreflective foci within the retina and a slab from beneath the retinal pigment epithelium (RPE; the sub-RPE slab) that was used to detect regions that cause decreased light transmission into the choroid, also known as hypotransmission defects. All images were registered to allow for qualitative comparisons by 2 independent graders.Main Outcome MeasuresComparison between foci of macular hyperpigmentation seen on CFIs with the detection of these regions on FAF, NIR, and SS OCT en face images.ResultsCompared with CFIs, FAF imaging seemed to be the least sensitive method for the detection of hyperpigmentation, whereas NIR and SS OCT imaging reliably detected these hyperpigmented areas. Although NIR imaging detected most of the hyperpigmentation seen in CFIs, SS OCT imaging detected all the areas of hyperpigmentation and anatomically localized these areas by using both en face and B-scan images. En face OCT slabs of the retina and sub-RPE region were registered to the CFIs, and areas of hyperpigmentation were shown to correspond to hyperreflective foci in the retina and regions of thickened RPE seen on OCT B-scans. Although both hyperpigmentation and early atrophic lesions appeared bright on NIR imaging, en face SS OCT imaging was able to distinguish these lesions because hyperpigmentary changes appeared dark and early atrophic lesions appeared bright on the sub-RPE slab.ConclusionsEn face OCT imaging in conjunction with OCT B-scans were able to identify and localize the hyperpigmentation seen in CFIs reliably. This hyperpigmentation was not only associated with intraretinal hyperreflective foci, but also corresponded to areas with a thickened RPE.

A Review on Recent Techniques For grading the Severity of Diabetic Retinopathy in Retinal Colour Fundus Images

Diabetic retinopathy (DR) is an eye disease, which is caused by the development of retinal microvascularization following diabetes. It is a problem of diabetes mellitus, which produces lesions in the surface of the retina due to which eye vision gets affected. Severe, uncontrolled cases of diabetic retinopathy will result in blindness. Since DR cannot be reversed, it can lead to blindness, and only early treatment maintains vision. Early diagnosis and treatment of DR can significantly reduce The risk of losing the vision. Fundus images are manually examined for morphological changes in retinal lesions such as micro aneurysms, exudates, blood vessels, hemorrhages. They are a tedious and time-consuming job. It is often easily accomplished with the help of a computer-assisted system. The identification and classification of the severity of diabetic retinopathy requires adequate segmentation of the retinal lesions. In this article, various techniques for detecting retinal lesions are discussed for the final detection and classification of nonproliferative diabetic retinopathy. Blood vessel detection techniques for diagnosing proliferative diabetic retinopathy are also discussed. In addition, the available datasets for the fundus colored retina were also examined. This work will be useful for researchers and technicians who wish to use ongoing research in this area. Several challenging topics are also discussed that require further investigation.

Automatic detection of exudates and hemorrhages in low‐contrast color fundus images using multi semantic convolutional neural network

AbstractDiabetic retinopathy (DR) is a pathology occurring in the optic nerve due to an excessive blood sugar level in human body. It is one of the major reasons for visual impairment in the developed and developing countries. Patients with DR usually suffer from visual damages due to a high blood sugar level in retinal blood vessel walls. These damages may also leak into other retinal layers of the eye within time. As a result of these leakages and nutritional disorders, a number of lesions such as excudate, edema, microaneurysm, and hemorrhage may occur. In this respect, an accurate and effective detection of these lesions in earlier stages of DR plays an important role in the progression of the disease. In the proposed study, exudate and hemorrhages, which are important clinical findings for DR, were automatically detected from low contrast colored fundus images. Exudate and hemorrhages are lesions with different characteristics. However, in this study, high performance was achieved by making a three‐class semantic segmentation. In addition, a color space transformation was performed and the classical U‐Net algorithm was provided to achieve stable high performance in low contrast images. Finally, lesion images which were manually detected by a physician were matched with automatically segmented excudate and hemorrhage images using the proposed method. Thus, both segmentation and lesion detection performances of the proposed method were measured. The findings demonstrated that Dice and Jaccard similarity indexes were calculated nearly as 0.95 for the segmentation performance. A sensitivity of 98% and specificity value of 91% were measured for detection performance. It can be inferred from these figures that the proposed method can be effectively used as a supporting system by physicians for the detection and classification of lesions in the color fundus images for the diagnosis of DR.

Review of Machine Learning Applications Using Retinal Fundus Images.

Automating screening and diagnosis in the medical field saves time and reduces the chances of misdiagnosis while saving on labor and cost for physicians. With the feasibility and development of deep learning methods, machines are now able to interpret complex features in medical data, which leads to rapid advancements in automation. Such efforts have been made in ophthalmology to analyze retinal images and build frameworks based on analysis for the identification of retinopathy and the assessment of its severity. This paper reviews recent state-of-the-art works utilizing the color fundus image taken from one of the imaging modalities used in ophthalmology. Specifically, the deep learning methods of automated screening and diagnosis for diabetic retinopathy (DR), age-related macular degeneration (AMD), and glaucoma are investigated. In addition, the machine learning techniques applied to the retinal vasculature extraction from the fundus image are covered. The challenges in developing these systems are also discussed.

Segmentation of retinal features in colour fundus images

Segmentation of retinal features in colour fundus images

Automated Glaucoma Assessment from Color Fundus Images Using Structural and Texture Features

Automated Glaucoma Assessment from Color Fundus Images Using Structural and Texture Features

Incidence, progression and risk factors of age-related macular degeneration in 35–95-year-old individuals from three jointly designed German cohort studies

ObjectiveTo estimate age-related macular degeneration (AMD) incidence/progression across a wide age range.Methods and analysisAMD at baseline and follow-up (colour fundus imaging, Three Continent AMD Consortium Severity Scale, 3CACSS, clinical classification,...

Deep Learning-Based Glaucoma Detection With Cropped Optic Cup and Disc and Blood Vessel Segmentation

Glaucoma is an irreversible neurodegenerative disease, where intraocular hypertension is developed due to the increased aqueous humor and blockage of the drainage system between the iris and cornea. As a result, the optic nerve head, which sends visual stimulus from our eyes to the brain, is damaged, causing visual field loss and ultimately blindness. Glaucoma is considered as the sneak thief of vision because it is difficult to diagnose early, and its regular screening is highly recommended to distinguish the neurological disorder. The detection of glaucoma is costly and time-consuming and not only there always remains a good possibility of human error but also this detection method is dependent upon the availability of the resources (experienced ophthalmologists and expensive instruments). In this work, an automatic glaucoma classification technique has been developed by utilizing multiple deep learning approaches. First, a new private dataset of 634 color fundus images has been collected and annotated by two eye specialists, a pediatric ophthalmologist and a glaucoma and refractive surgeon, from Bangladesh Eye Hospital, Bangladesh. Next, various deep learning models (EfficientNet, MobileNet, DenseNet, and GoogLeNet) have been used to detect glaucoma from fundus images. The model with EfficientNet-b3 architecture achieved the best results with test accuracy, F1-score, and ROC AUC of 0.9652, 0.9512, and 0.9574, respectively, for the cropped optic cup and disc fundus photographs. We also constructed a new dataset by segmenting the blood vessels from retinal fundus images employing a U-net model trained on High-Resolution Fundus Image Database. The MobileNet v3 model trained on this dataset achieved a satisfactory test accuracy of 0.8348 and an F1-score of 0.7957. This impressive result suggests that blood vessel segmentation of fundus images can be utilized as an alternative to detect glaucoma automatically.

Hybrid Retinal Image Enhancement Algorithm for Diabetic Retinopathy Diagnostic Using Deep Learning Model

Diabetic Retinopathy (DR) is a prevalent acute stage of diabetes mellitus that causes vision-effecting abnormalities on the retina. This will cause blindness if not identified early. Because DR not an irreversible procedure, and only vision is preserved via care. Consequently, Early diagnosis and care with DR will significantly minimize the chance of vision loss. In modern ophthalmology, retinal image analysis has become a popular approach to disease diagnosis. The ophthalmologists and computerized systems extensively employ fundus angiography to detect DR-based clinical signs for early detection of DR. fundus photographs are commonly prone to low contrast, noise, and irregular illumination issues due to the complexity of imaging environments such as imaging variety of angles and light conditions. This research presents an Algorithm for improving the quality of images to strengthen the standard of color fundus images by reducing the noise and improving the contrast. The approach includes two main stages: cropping the images to remove insignificant content, then applying the shape crop and gaussian blurring for noise reduction and contrast improvement. The experimental results are evaluated using two standard datasets EyePACS and MESSIDOR. It’s clearly shown that the outcomes of feature extraction and classification of enhanced images is outperform the results without applying the enhancement approach. The improved algorithm is also tested in smart hospitals as an IoMT application.

MSGANet-RAV: A multiscale guided attention network for artery-vein segmentation and classification from optic disc and retinal images

BackgroundRetinal and optic disc images are used to assess changes in the retinal vasculature. These can be changes associated with diseases such as diabetic retinopathy and glaucoma or induced using ophthalmodynamometry to measure arterial and venous pressure. Key steps toward automating the assessment of these changes are the segmentation and classification of the veins and arteries. However, such segmentation and classification are still required to be manually labelled by experts. Such automated labelling is challenging because of the complex morphology, anatomical variations, alterations due to disease and scarcity of labelled data for algorithm development. We present a deep machine learning solution called the multiscale guided attention network for retinal artery and vein segmentation and classification (MSGANet-RAV). MethodsMSGANet-RAV was developed and tested on 383 colour clinical optic disc images from LEI-CENTRAL, constructed in-house and 40 colour fundus images from the AV-DRIVE public dataset. The datasets have a mean optic disc occupancy per image of 60.6% and 2.18%, respectively. MSGANet-RAV is a U-shaped encoder-decoder network, where the encoder extracts multiscale features, and the decoder includes a sequence of self-attention modules. The self-attention modules explore, guide and incorporate vessel-specific structural and contextual feature information to segment and classify central optic disc and retinal vessel pixels. ResultsMSGANet-RAV achieved a pixel classification accuracy of 93.15%, sensitivity of 92.19%, and specificity of 94.13% on LEI-CENTRAL, outperforming several reference models. It similarly performed highly on AV-DRIVE with an accuracy, sensitivity and specificity of 95.48%, 93.59% and 97.27%, respectively. ConclusionThe results show the efficacy of MSGANet-RAV for identifying central optic disc and retinal arteries and veins. The method can be used in automated systems designed to assess vascular changes in retinal and optic disc images quantitatively.

Intelligent Deep Learning Based Multi-Retinal Disease Diagnosis and Classification Framework

In past decades, retinal diseases have become more common and affect people of all age grounds over the globe. For examining retinal eye disease, an artificial intelligence (AI) based multilabel classification model is needed for automated diagnosis. To analyze the retinal malady, the system proposes a multiclass and multi-label arrangement method. Therefore, the classification frameworks based on features are explicitly described by ophthalmologists under the application of domain knowledge, which tends to be time-consuming, vulnerable generalization ability, and unfeasible in massive datasets. Therefore, the automated diagnosis of multi-retinal diseases becomes essential, which can be solved by the deep learning (DL) models. With this motivation, this paper presents an intelligent deep learning-based multi-retinal disease diagnosis (IDL-MRDD) framework using fundus images. The proposed model aims to classify the color fundus images into different classes namely AMD, DR, Glaucoma, Hypertensive Retinopathy, Normal, Others, and Pathological Myopia. Besides, the artificial flora algorithm with Shannon’s function (AFA-SF) based multi-level thresholding technique is employed for image segmentation and thereby the infected regions can be properly detected. In addition, SqueezeNet based feature extractor is employed to generate a collection of feature vectors. Finally, the stacked sparse Autoencoder (SSAE) model is applied as a classifier to distinguish the input images into distinct retinal diseases. The efficacy of the IDL-MRDD technique is carried out on a benchmark multi-retinal disease dataset, comprising data instances from different classes. The experimental values pointed out the superior outcome over the existing techniques with the maximum accuracy of 0.963.

Self-Supervised Rigid Registration for Multimodal Retinal Images.

The ability to accurately overlay one modality retinal image to another is critical in ophthalmology. Our previous framework achieved the state-of-the-art results for multimodal retinal image registration. However, it requires human-annotated labels due to the supervised approach of the previous work. In this paper, we propose a self-supervised multimodal retina registration method to alleviate the burdens of time and expense to prepare for training data, that is, aiming to automatically register multimodal retinal images without any human annotations. Specially, we focus on registering color fundus images with infrared reflectance and fluorescein angiography images, and compare registration results with several conventional and supervised and unsupervised deep learning methods. From the experimental results, the proposed self-supervised framework achieves a comparable accuracy comparing to the state-of-the-art supervised learning method in terms of registration accuracy and Dice coefficient.

Diabetic and Hypertensive Retinopathy Screening in Fundus Images Using Artificially Intelligent Shallow Architectures.

Retinal blood vessels are considered valuable biomarkers for the detection of diabetic retinopathy, hypertensive retinopathy, and other retinal disorders. Ophthalmologists analyze retinal vasculature by manual segmentation, which is a tedious task. Numerous studies have focused on automatic retinal vasculature segmentation using different methods for ophthalmic disease analysis. However, most of these methods are computationally expensive and lack robustness. This paper proposes two new shallow deep learning architectures: dual-stream fusion network (DSF-Net) and dual-stream aggregation network (DSA-Net) to accurately detect retinal vasculature. The proposed method uses semantic segmentation in raw color fundus images for the screening of diabetic and hypertensive retinopathies. The proposed method’s performance is assessed using three publicly available fundus image datasets: Digital Retinal Images for Vessel Extraction (DRIVE), Structured Analysis of Retina (STARE), and Children Heart Health Study in England Database (CHASE-DB1). The experimental results revealed that the proposed method provided superior segmentation performance with accuracy (Acc), sensitivity (SE), specificity (SP), and area under the curve (AUC) of 96.93%, 82.68%, 98.30%, and 98.42% for DRIVE, 97.25%, 82.22%, 98.38%, and 98.15% for CHASE-DB1, and 97.00%, 86.07%, 98.00%, and 98.65% for STARE datasets, respectively. The experimental results also show that the proposed DSA-Net provides higher SE compared to the existing approaches. It means that the proposed method detected the minor vessels and provided the least false negatives, which is extremely important for diagnosis. The proposed method provides an automatic and accurate segmentation mask that can be used to highlight the vessel pixels. This detected vasculature can be utilized to compute the ratio between the vessel and the non-vessel pixels and distinguish between diabetic and hypertensive retinopathies, and morphology can be analyzed for related retinal disorders.

A New Method for Visualizing Drusen and Their Progression in Flood-Illumination Adaptive Optics Ophthalmoscopy.

PurposeDrusen are dynamic sub-RPE deposits that are risk factors for late-stage age-related macular degeneration (AMD). Here we show a new imaging method using flood-illumination adaptive optics (FIAO) that reveal drusen with high contrast and resolution.MethodsA fovea-centered 4° × 4° FIAO image and eight surrounding images with gaze displaced by ±2° vertically and horizontally were acquired. Clinical color fundus and spectral-domain optical coherence tomography were acquired for clinical grading and comparison. Custom software registered overlapping FIAO images and fused the data statistically to generate a fovea-centered 4° × 4° gaze-dependent image. Our dataset included 15 controls (aged 31–72) and 182 eyes from 104 AMD patients (aged 56–92), graded as either normal aging (n = 7), and early (n = 12), intermediate (n = 108) and late AMD (n = 42); 27 had subretinal drusenoid deposits (SDDs), and 83 were imaged longitudinally.ResultsNo gaze varying structures were detected in young eyes. In aging eyes with no evidence of age-related changes, putative drusen <20 µm in diameter were visible. Gaze-dependent images revealed more drusen and many smaller drusen than visible in color fundus images. Longitudinal images showed expansion and fusion of drusen. SDDs were lower contrast, and RPE atrophy did not yield a consistent signal.ConclusionsGaze-dependent imaging in a commercially available FIAO fundus camera combined with image registration and postprocessing permits visualization of drusen and their progression with high contrast and resolution.Translational RelevanceThis new technique offers promise as a robust and sensitive method to detect, map, quantify, and monitor the dynamics of drusen in aging and AMD.