-
Cureus Jul 2023Background Age-related macular degeneration (AMD), diabetic retinopathy (DR), drusen, choroidal neovascularization (CNV), and diabetic macular edema (DME) are...
Background Age-related macular degeneration (AMD), diabetic retinopathy (DR), drusen, choroidal neovascularization (CNV), and diabetic macular edema (DME) are significant causes of visual impairment globally. Optical coherence tomography (OCT) imaging has emerged as a valuable diagnostic tool for these ocular conditions. However, subjective interpretation and inter-observer variability highlight the need for standardized diagnostic approaches. Methods This study aimed to develop a robust deep learning model using artificial intelligence (AI) techniques for the automated detection of drusen, CNV, and DME in OCT images. A diverse dataset of 1,528 OCT images from Kaggle.com was used for model training. The performance metrics, including precision, recall, sensitivity, specificity, F1 score, and overall accuracy, were assessed to evaluate the model's effectiveness. Results The developed model achieved high precision (0.99), recall (0.962), sensitivity (0.985), specificity (0.987), F1 score (0.971), and overall accuracy (0.987) in classifying diseased and healthy OCT images. These results demonstrate the efficacy and efficiency of the model in distinguishing between retinal pathologies. Conclusion The study concludes that the developed deep learning model using AI techniques is highly effective in the automated detection of drusen, CNV, and DME in OCT images. Further validation studies and research efforts are necessary to evaluate the generalizability and integration of the model into clinical practice. Collaboration between clinicians, policymakers, and researchers is essential for advancing diagnostic tools and management strategies for AMD and DR. Integrating this technology into clinical workflows can positively impact patient care, particularly in settings with limited access to ophthalmologists. Future research should focus on collecting independent datasets, addressing potential biases, and assessing real-world effectiveness. Overall, the use of machine learning algorithms in conjunction with OCT imaging holds great potential for improving the detection and management of drusen, CNV, and DME, leading to enhanced patient outcomes and vision preservation.
PubMed: 37565126
DOI: 10.7759/cureus.41615 -
Survey of Ophthalmology 2016Age-related macular degeneration is the leading cause of adult blindness in the developed world. Thus, major endeavors to understand the risk factors and pathogenesis of... (Review)
Review
Age-related macular degeneration is the leading cause of adult blindness in the developed world. Thus, major endeavors to understand the risk factors and pathogenesis of this disease have been undertaken. Reticular macular disease is a proposed subtype of age-related macular degeneration correlating histologically with subretinal drusenoid deposits located between the retinal pigment epithelium and the inner segment ellipsoid zone. Reticular lesions are more prevalent in females and in older age groups and are associated with a higher mortality rate. Risk factors for developing age-related macular degeneration include hypertension, smoking, and angina. Several genes related to increased risk for age-related macular degeneration and reticular macular disease are also associated with cardiovascular disease. Better understanding of the clinical and genetic risk factors for age-related macular degeneration and reticular macular disease has led to the hypothesis that these eye diseases are systemic. A systemic origin may help to explain why reticular disease is diagnosed more frequently in females as males suffer cardiovascular mortality at an earlier age, before the age of diagnosis of reticular macular disease and age-related macular degeneration.
Topics: Cardiovascular Diseases; Fluorescein Angiography; Fundus Oculi; Humans; Macular Degeneration; Ophthalmoscopy; Retinal Drusen; Retinal Pigment Epithelium; Risk Factors; Tomography, Optical Coherence
PubMed: 26518628
DOI: 10.1016/j.survophthal.2015.10.003 -
Translational Vision Science &... Dec 2020To investigate the structure-function relationship in eyes with drusen with mesopic and scotopic microperimetry.
PURPOSE
To investigate the structure-function relationship in eyes with drusen with mesopic and scotopic microperimetry.
METHODS
We analyzed structural and functional data from 43 eyes with drusen. Functional data were acquired with mesopic and scotopic two-color (red and cyan) microperimetry. Normative values were calculated using data from 56 healthy eyes. Structural measurements were green autofluorescence and dense macular optical coherence tomography scans. The latter were used to calculate the retinal pigment epithelium elevation (RPE-E) and the photoreceptor reflectivity ratio (PRR). The pointwise structure-function relationship was measured with linear mixed models having the log-transformed structural parameters as predictors and the sensitivity loss (SL, deviation from normal) as the response variable.
RESULTS
In the univariable analysis, the structural predictors were all significantly correlated ( < 0.05) with the SL in the mesopic and scotopic tests. In a multivariable model, mesopic microperimetry yielded the best structure-function relationship. All predictors were significant ( < 0.05), but the predictive power was weak (best = 0.09). The relationship was improved when analyzing locations with abnormal RPE-E (best = 0.18).
CONCLUSIONS
Mesopic microperimetry shows better structure-function relationship compared to scotopic microperimetry; the relationship is weak, likely due to the early functional damage and the small number of tested locations affected by drusen. The relationship is stronger when locations with drusen are isolated for the mesopic and scotopic cyan test.
TRANSLATIONAL RELEVANCE
These results could be useful to devise integrated structure-function methods to detect disease progression in intermediate age-related macular degeneration.
Topics: Humans; Macular Degeneration; Retina; Retinal Drusen; Tomography, Optical Coherence; Visual Field Tests
PubMed: 33442497
DOI: 10.1167/tvst.9.13.43 -
Ophthalmology Jun 2022To determine the prognostic significance and impact on visual function of the cuticular drusen phenotype in a cohort with intermediate age-related macular degeneration... (Observational Study)
Observational Study
PURPOSE
To determine the prognostic significance and impact on visual function of the cuticular drusen phenotype in a cohort with intermediate age-related macular degeneration (AMD).
DESIGN
Longitudinal, observational study.
PARTICIPANTS
Participants aged 50 years or older, with bilateral large conventional drusen, without late AMD.
METHODS
Multimodal imaging (MMI) and microperimetry were performed at baseline and then every 6 months for up to 3 years. Eyes were graded for the MMI-based presence of cuticular drusen at baseline. Color fundus photographs were used to grade for the presence of pigmentary abnormalities. OCT scans were used to calculate drusen volume. The associations between cuticular drusen and progression to MMI-defined late AMD (including OCT signs of atrophy) and the impact on visual sensitivity were examined with and without adjustment for the confounders of baseline age, pigmentary abnormalities, and drusen volume.
MAIN OUTCOME MEASURES
Time to develop MMI-defined late AMD and change in mean visual sensitivity.
RESULTS
A total of 280 eyes from 140 participants were included, with 70 eyes from 35 individuals (25%) having cuticular drusen at baseline. Cuticular drusen were not significantly associated with an increased rate of progression to late AMD with and without adjustment for confounders (P ≥ 0.784 for both). In an adjusted model, cuticular drusen were not associated with lower baseline visual sensitivity (P = 0.758) or a faster rate of visual sensitivity decline (P = 0.196).
CONCLUSIONS
In a cohort with bilateral large conventional drusen, individuals with the cuticular drusen phenotype had neither a higher nor lower risk of developing late AMD over 3 years and were not associated with a difference in rate of visual sensitivity decline compared with those without this phenotype. As such, individuals with this phenotype currently warrant similar monitoring strategies as those with conventional drusen.
Topics: Bruch Membrane; Disease Progression; Eye Diseases, Hereditary; Humans; Macular Degeneration; Retinal Drusen; Tomography, Optical Coherence
PubMed: 35120992
DOI: 10.1016/j.ophtha.2022.01.028 -
Retina (Philadelphia, Pa.) Feb 2020Cuticular drusen (CD) have been associated with manifestations of age-related macular degeneration such as atrophy and neovascularization in the macula. In this study,...
PURPOSE
Cuticular drusen (CD) have been associated with manifestations of age-related macular degeneration such as atrophy and neovascularization in the macula. In this study, eyes with CD were followed and investigated for the estimated 5-year risk of progression to sequelae of age-related macular degeneration such as geographic atrophy (GA) and macular neovascularization (MNV).
METHODS
A consecutive series of patients with CD were followed for the development of GA and MNV. Whenever possible, they were also studied retrospectively. The patients with CD were categorized into three phenotypic groups. Phenotype 1: eyes had concentrated, densely populated CD in the macular and paramacular area, Phenotype 2: eyes showed scattered CD in the posterior fundus, and Phenotype 3: involved eyes with CD mixed with large drusen (>200 µm). The 5-year incidence of progression was then estimated using a Kaplan-Meier estimator.
RESULTS
A total of 63 eyes from 38 patients (35 women with a mean age at presentation of 58.9 ± 14.2 years) were studied and followed for a mean of 40 ± 18 months. Thirteen patients had single eyes with GA (84.5%; 11/13) or MNV (15.5%; 2/13) in one eye at presentation and were subsequently excluded. Geographic atrophy developed in 19.0% (12/63) of eyes and MNV in 4.8% (3/63) of eyes. The cumulative estimated 5-year risk of GA and MNV was 28.4% and 8.7%, respectively. The estimated 5-year incidence of MNV or GA was 12.6%, 50.0%, and 51.6% in Phenotype 1, Phenotype 2, and Phenotype 3, respectively (P = 0.0015, log-rank test). No difference in risk was found in the development of GA or MNV (P = 0.11) between the subgroup of patients presenting with GA or MNV in their fellow eye and those with both eyes included.
CONCLUSION
When patients with CD are followed longitudinally, there was a significant risk of progression to GA or MNV for Phenotype 2 and Phenotype 3. Patients with CD are commonly first diagnosed in the fifth decade of life, and there is a female predominance. Clinicians should use multimodal imaging to detect and be aware of the risk of progression to manifestations of GA and MNV. These risks of GA and MNV suggest that patients with CD may be part of the overall spectrum of age-related macular degeneration.
Topics: Adult; Aged; Aged, 80 and over; Bruch Membrane; Eye Diseases, Hereditary; Female; Fluorescein Angiography; Follow-Up Studies; Fundus Oculi; Geographic Atrophy; Humans; Incidence; Macula Lutea; Male; Middle Aged; New York; Retinal Drusen; Retrospective Studies; Risk Assessment; Risk Factors; Time Factors; Tomography, Optical Coherence; Wet Macular Degeneration
PubMed: 31972795
DOI: 10.1097/IAE.0000000000002399 -
Journal of Biological Engineering May 2022Age-related macular degeneration (AMD) is a progressive, degenerative disease of the macula, leading to severe visual loss in the elderly population. There are two types... (Review)
Review
Age-related macular degeneration (AMD) is a progressive, degenerative disease of the macula, leading to severe visual loss in the elderly population. There are two types of AMD: non-exudative ('dry') AMD and exudative ('wet') AMD. Non-exudative AMD is characterized by drusen formation and macular atrophy, while the blood vessels are not leaky. Exudative AMD is a more advanced form of the disease, featured with abnormal blood vessel growth and vascular leakage. Even though anti-angiogenic therapies have been effective in treating wet AMD by normalizing blood vessels, there is no treatment available to prevent or treat dry AMD. Currently, the mechanisms of drusen formation and macular atrophy in the dry AMD are poorly understood, in part because the currently available in vivo models of AMD could not decouple and isolate the complex biological and biophysical factors in the macular region for a detailed mechanism study, including the complement system, angiogenesis factors, extracellular matrix, etc. In the present review article, we describe the biological background of AMD and the key cells and structures in AMD, including retinal epithelium, photoreceptor, Bruch's membrane, and choriocapillaris. We also discuss pre-clinical animal models of AMD and in vivo tissue-engineered approaches, including cell suspension injection and organoid-derived cell sheet transplantation. We also discuss in vitro tissue-engineered models for AMD research. Specifically, we evaluate and compare currently available two- and three-dimensional AMD tissue-engineered models that mimic key anatomical players in AMD progression, including pathophysiological characteristics in Bruch's membrane, photoreceptor, and choriocapillaris. Finally, we discuss the limitation of current AMD models and future directions.
PubMed: 35578246
DOI: 10.1186/s13036-022-00291-y -
Clinical & Experimental Optometry Sep 2019Reticular pseudodrusen (RPD), also known as subretinal drusenoid deposits, represent a morphological change to the retina distinct from other subtypes of drusen by being... (Review)
Review
Reticular pseudodrusen (RPD), also known as subretinal drusenoid deposits, represent a morphological change to the retina distinct from other subtypes of drusen by being located above the level of the retinal pigment epithelium. Although they can infrequently appear in individuals with no other apparent pathology, their highest rates of occurrence are in association with age-related macular degeneration (AMD), for which they hold clinical significance by being highly correlated with end-stage disease sub-types, choroidal neovascularisation and geographic atrophy. Reticular pseudodrusen are also found in other diseases, most notably Sorsby's fundus dystrophy, pseudoxanthoma elasticum and acquired vitelliform lesions. They are found more frequently in females, with increased age and more commonly bilaterally than unilaterally. Increased risk of RPD formation is conveyed by genetic variants known to increase risk of AMD development, including complement factor H, age-related maculopathy susceptibility 2, and high-temperature requirement A serine peptidase 1; however, to date, no genetic factor has been found to predispose to RPD independent of those that carry risks for AMD. They have typical features visible on multimodal imaging, identifiable either as single lesions or more commonly in yellowish-white net-like patterns on colour fundus photography and are particularly distinguishable using spectral domain optical coherence tomography, fundus auto-fluorescence, and near infrared reflectance imaging. On histological examination, RPD have been shown to have distinct compositions in comparison to typical drusen, suggesting different pathways of pathogenesis. Although their aetiology remains unclear, presence of opsin within lesions, a high topographic association with areas of highest rod-photoreceptor concentration and functional deficits most pronounced within the scotopic range, has implicated rod photoreceptor dysfunction as a component of RPD.
Topics: Choroidal Neovascularization; Geographic Atrophy; Humans; Macular Degeneration; Multimodal Imaging; Retinal Drusen
PubMed: 30298528
DOI: 10.1111/cxo.12842 -
Ophthalmic & Physiological Optics : the... Jul 2023The purpose of this study was to build an automated age-related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates...
INTRODUCTION
The purpose of this study was to build an automated age-related macular degeneration (AMD) colour fundus photography (CFP) recognition method that incorporates confounders (other ocular diseases) and normal age-related changes by using drusen masks for spatial feature supervision.
METHODS
A range of clinical sources were used to acquire 7588 CFPs. Contrast limited adaptive histogram equalisation was used for pre-processing. ResNet50 was used as the backbone network, and a spatial attention block was added to integrate prior knowledge of drusen features into the backbone. The evaluation metrics used were sensitivity, specificity and F1 score, which is the harmonic mean of precision and recall (sensitivity) and area under the receiver-operating characteristic (AUC). Fivefold cross-validation was performed, and the results compared with four other methods.
RESULTS
Excellent discrimination results were obtained with the algorithm. On the public dataset (n = 6565), the proposed method achieved a mean (SD) sensitivity of 0.54 (0.09), specificity of 0.99 (0.00), F1 score of 0.62 (0.06) and AUC of 0.92 (0.02). On the private dataset (n = 1023), the proposed method achieved a sensitivity of 0.92 (0.02), specificity of 0.98 (0.01), F1 score of 0.92 (0.01) and AUC of 0.98 (0.01).
CONCLUSION
The proposed drusen-aware model outperformed baseline and other vessel feature-based methods in F1 and AUC on the AMD/normal CFP classification task and achieved comparable results on datasets that included other diseases that often confound classification. The method also improved results when a five-category grading protocol was used, thereby reflecting discriminative ability of the algorithm within a real-life clinical setting.
Topics: Humans; Retinal Drusen; Macular Degeneration; Retina; Algorithms; ROC Curve
PubMed: 36786498
DOI: 10.1111/opo.13108 -
Annals of Eye Science Mar 2021Soft drusen and basal linear deposit (BLinD) are two forms of the same extracellular lipid rich material that together make up an Oil Spill on Bruch's membrane (BrM)....
BACKGROUND
Soft drusen and basal linear deposit (BLinD) are two forms of the same extracellular lipid rich material that together make up an Oil Spill on Bruch's membrane (BrM). Drusen are focal and can be recognized clinically. In contrast BLinD is thin and diffusely distributed, and invisible clinically, even on highest resolution OCT, but has been detected on hyperspectral autofluorescence (AF) imaging . We sought to optimize histologic hyperspectral AF imaging and image analysis for recognition of drusen and sub-RPE deposits (including BLinD and basal laminar deposit), for potential clinical application.
METHODS
Twenty locations specifically with drusen and 12 additional locations specifically from fovea, perifovea and mid-periphery from RPE/BrM flatmounts from 4 AMD donors underwent hyperspectral AF imaging with 4 excitation wavelengths (λ 436, 450, 480 and 505 nm), and the resulting image cubes were simultaneously decomposed with our published non-negative matrix factorization (NMF). Rank 4 recovery of 4 emission spectra was chosen for each excitation wavelength.
RESULTS
A composite emission spectrum, sensitive and specific for drusen and presumed sub-RPE deposits (the SDr spectrum) was recovered with peak at 510-520 nm in all tissues with drusen, with greatest amplitudes at excitations λ 436, 450 and 480 nm. The RPE spectra of combined sources Lipofuscin (LF)/Melanolipofuscin (MLF) were of comparable amplitude and consistently recapitulated the spectra S1, S2 and S3 previously reported from all tissues: tissues with drusen, foveal and extra-foveal locations.
CONCLUSIONS
A clinical hyperspectral AF camera, with properly chosen excitation wavelengths in the blue range and a hyperspectral AF detector, should be capable of detecting and quantifying drusen and sub-RPE deposits, the earliest known lesions of AMD, before any other currently available imaging modality.
PubMed: 33791592
DOI: 10.21037/aes-20-12 -
Clinical Ophthalmology (Auckland, N.Z.) 2021Cuticular drusen are part of the spectrum of age-related macular degeneration (AMD) with particular clinical and multimodal imaging characteristics. This drusen... (Review)
Review
Cuticular drusen are part of the spectrum of age-related macular degeneration (AMD) with particular clinical and multimodal imaging characteristics. This drusen subpopulation shares several high-risk single nucleotide polymorphisms with AMD. Despite this feature, they can manifest at a relatively young age, presenting with a female preponderance. Multimodal imaging is essential for characterizing such lesions, using a combination of color fundus photographs, optical coherence tomography (OCT), fluorescein angiography (FA), and fundus autofluorescence (FAF). The classic starry-sky pattern visible on FA and the typical central hypoautofluorescent lesion with hyperautofluorescent rim on FAF is considered the result of a central retinal pigment epithelium (RPE) erosion from these triangular elevations of the RPE-basal lamina. This finding may also be responsible for the typical choroidal hypertransmission appreciated through OCT. The clinical course of cuticular drusen may be relatively benign at early stages, with small drusen presenting at a young age. However, the presence of clinical phenotypes characterized by diffuse involvement and/or accompanying large drusen in patients older than 60 years may confer a significant risk for either macular neovascularization or geographic atrophy.
PubMed: 34584401
DOI: 10.2147/OPTH.S272345