-
Graefe's Archive For Clinical and... Jan 2024Subretinal drusenoid deposits (SDDs) are distinct extracellular alteration anterior to the retinal pigment epithelium (RPE). Given their commonly uniform phenotype, a...
PURPOSE
Subretinal drusenoid deposits (SDDs) are distinct extracellular alteration anterior to the retinal pigment epithelium (RPE). Given their commonly uniform phenotype, a hereditary predisposition seems likely. Hence, we aim to investigate prevalence and determinants in patients' first-degree relatives.
METHODS
We recruited SDD outpatients at their visits to our clinic and invited their relatives. We performed a full ophthalmic examination including spectral domain-optical coherence tomography (SD-OCT) and graded presence, disease stage of SDD as well as percentage of infrared (IR) en face area affected by SDD. Moreover, we performed genetic sequencing and calculated a polygenic risk score (PRS) for AMD. We conducted multivariable regression models to assess potential determinants of SDD and associations of SDD with PRS.
RESULTS
We included 195 participants, 123 patients (mean age 81.4 ± 7.2 years) and 72 relatives (mean age 52.2 ± 14.2 years), of which 7 presented SDD, resulting in a prevalence of 9.7%. We found older age to be associated with SDD presence and area in the total cohort and a borderline association of higher body mass index (BMI) with SDD presence in the relatives. Individuals with SDD tended to have a higher PRS, which, however, was not statistically significant in the multivariable regression.
CONCLUSION
Our study indicates a potential hereditary aspect of SDD and confirms the strong association with age. Based on our results, relatives of SDD patients ought to be closely monitored for retinal alterations, particularly at an older age. Further longitudinal studies with larger sample size and older relatives are needed to confirm or refute our findings.
Topics: Humans; Aged; Aged, 80 and over; Adult; Middle Aged; Retinal Drusen; Prevalence; Retinal Pigment Epithelium; Genetic Risk Score; Tomography, Optical Coherence; Fluorescein Angiography
PubMed: 37672102
DOI: 10.1007/s00417-023-06221-y -
SLAS Technology Jun 2024Age-Related Macular Degeneration (AMD) is a highly prevalent form of retinal disease amongst Western communities over 50 years of age. A hallmark of AMD pathogenesis is...
Age-Related Macular Degeneration (AMD) is a highly prevalent form of retinal disease amongst Western communities over 50 years of age. A hallmark of AMD pathogenesis is the accumulation of drusen underneath the retinal pigment epithelium (RPE), a biological process also observable in vitro. The accumulation of drusen has been shown to predict the progression to advanced AMD, making accurate characterisation of drusen in vitro models valuable in disease modelling and drug development. More recently, deposits above the RPE in the subretinal space, called reticular pseudodrusen (RPD) have been recognized as a sub-phenotype of AMD. While in vitro imaging techniques allow for the immunostaining of drusen-like deposits, quantification of these deposits often requires slow, low throughput manual counting of images. This further lends itself to issues including sampling biases, while ignoring critical data parameters including volume and precise localization. To overcome these issues, we developed a semi-automated pipeline for quantifying the presence of drusen-like deposits in vitro, using RPE cultures derived from patient-specific induced pluripotent stem cells (iPSCs). Using high-throughput confocal microscopy, together with three-dimensional reconstruction, we developed an imaging and analysis pipeline that quantifies the number of drusen-like deposits, and accurately and reproducibly provides the location and composition of these deposits. Extending its utility, this pipeline can determine whether the drusen-like deposits locate to the apical or basal surface of RPE cells. Here, we validate the utility of this pipeline in the quantification of drusen-like deposits in six iPSCs lines derived from patients with AMD, following their differentiation into RPE cells. This pipeline provides a valuable tool for the in vitro modelling of AMD and other retinal disease, and is amenable to mid and high throughput screenings.
Topics: Humans; Induced Pluripotent Stem Cells; Retinal Pigment Epithelium; Retinal Drusen; Macular Degeneration; Image Processing, Computer-Assisted; Microscopy, Confocal
PubMed: 37657710
DOI: 10.1016/j.slast.2023.08.006 -
Translational Vision Science &... Sep 2023The purpose of this study was to determine the impact of prophylactic ranibizumab (PR) injections given every 3 months in eyes with intermediate nonexudative... (Randomized Controlled Trial)
Randomized Controlled Trial
PURPOSE
The purpose of this study was to determine the impact of prophylactic ranibizumab (PR) injections given every 3 months in eyes with intermediate nonexudative age-related macular degeneration (AMD) on drusen volume, macular layer thicknesses, and progression of geographic atrophy (GA) area over 24 months in the PREVENT trial.
METHODS
This post hoc analysis of the prospective PREVENT trial compared eyes with intermediate AMD randomized to PR versus sham injections to determine rates of conversion to neovascular AMD over 24 months. Drusen area and volume, macular thickness and volume, and retinal layer thicknesses were measured on spectral-domain optical coherence tomography images and analyzed. Masked grading of GA area and subretinal drusenoid deposits (SDDs) using fundus autofluorescence images was performed.
RESULTS
There were no statistical differences in drusen area and volumes between groups, and similar reductions in central subfield thickness, mean cube thickness, cube volume, and retinal sublayer thickness from baseline to 24 months (P = 0.018 to < 0.001), with no statistical differences between groups in any of these anatomic parameters. These findings were not impacted by the presence or absence of SDD. Among the 9 eyes with GA in this study, mean GA growth rate from baseline to 24 months was 1.34 +/- 0.79 mm2/year after PR and 1.95 +/- 1.73 mm2/year in sham-treated eyes (P = 0.49), and similarly showed no statistical difference with square root transformation (P = 0.61).
CONCLUSIONS
Prophylactic ranibizumab given every 3 months did not appear to affect drusen volume, macular thinning, or GA progression in eyes with intermediate AMD.
TRANSLATIONAL RELEVANCE
This work investigates the impact of PR on progressive retinal degeneration in a clinical trial.
Topics: Humans; Child, Preschool; Ranibizumab; Angiogenesis Inhibitors; Prospective Studies; Vascular Endothelial Growth Factor A; Visual Acuity; Wet Macular Degeneration; Retina; Geographic Atrophy
PubMed: 37656449
DOI: 10.1167/tvst.12.9.1 -
Frontiers in Medicine 2023The implementation of deep learning models for medical image classification poses significant challenges, including gradual performance degradation and limited...
BACKGROUND
The implementation of deep learning models for medical image classification poses significant challenges, including gradual performance degradation and limited adaptability to new diseases. However, frequent retraining of models is unfeasible and raises concerns about healthcare privacy due to the retention of prior patient data. To address these issues, this study investigated privacy-preserving continual learning methods as an alternative solution.
METHODS
We evaluated twelve privacy-preserving non-storage continual learning algorithms based deep learning models for classifying retinal diseases from public optical coherence tomography (OCT) images, in a class-incremental learning scenario. The OCT dataset comprises 108,309 OCT images. Its classes include normal (47.21%), drusen (7.96%), choroidal neovascularization (CNV) (34.35%), and diabetic macular edema (DME) (10.48%). Each class consisted of 250 testing images. For continuous training, the first task involved CNV and normal classes, the second task focused on DME class, and the third task included drusen class. All selected algorithms were further experimented with different training sequence combinations. The final model's average class accuracy was measured. The performance of the joint model obtained through retraining and the original finetune model without continual learning algorithms were compared. Additionally, a publicly available medical dataset for colon cancer detection based on histology slides was selected as a proof of concept, while the CIFAR10 dataset was included as the continual learning benchmark.
RESULTS
Among the continual learning algorithms, Brain-inspired-replay (BIR) outperformed the others in the continual learning-based classification of retinal diseases from OCT images, achieving an accuracy of 62.00% (95% confidence interval: 59.36-64.64%), with consistent top performance observed in different training sequences. For colon cancer histology classification, Efficient Feature Transformations (EFT) attained the highest accuracy of 66.82% (95% confidence interval: 64.23-69.42%). In comparison, the joint model achieved accuracies of 90.76% and 89.28%, respectively. The finetune model demonstrated catastrophic forgetting in both datasets.
CONCLUSION
Although the joint retraining model exhibited superior performance, continual learning holds promise in mitigating catastrophic forgetting and facilitating continual model updates while preserving privacy in healthcare deep learning models. Thus, it presents a highly promising solution for the long-term clinical deployment of such models.
PubMed: 37644987
DOI: 10.3389/fmed.2023.1227515 -
BioRxiv : the Preprint Server For... Aug 2023Age-related macular degeneration (AMD), the leading cause of geriatric blindness, is a multi-factorial disease with retinal-pigmented epithelial (RPE) cell dysfunction...
Age-related macular degeneration (AMD), the leading cause of geriatric blindness, is a multi-factorial disease with retinal-pigmented epithelial (RPE) cell dysfunction as a central pathogenic driver. With RPE degeneration, lysosomal function is a core process that is disrupted. Transcription factors EB/E3 (TFEB/E3) tightly control lysosomal function; their disruption can cause aging disorders, such as AMD. Here, we show that induced pluripotent stem cells (iPSC)-derived RPE cells with the complement factor H variant [ (Y402H)] have increased AKT2, which impairs TFEB/TFE3 nuclear translocation and lysosomal function. Increased AKT2 can inhibit PGC1α, which downregulates SIRT5, an AKT2 binding partner. SIRT5 and AKT2 co-regulate each other, thereby modulating TFEB-dependent lysosomal function in the RPE. Failure of the AKT2/SIRT5/TFEB pathway in the RPE induced abnormalities in the autophagy-lysosome cellular axis by upregulating secretory autophagy, thereby releasing a plethora of factors that likely contribute to drusen formation, a hallmark of AMD. Finally, overexpressing AKT2 in RPE cells in mice led to an AMD-like phenotype. Thus, targeting the AKT2/SIRT5/TFEB pathway could be a potential therapy for atrophic AMD.
PubMed: 37609254
DOI: 10.1101/2023.08.08.552343 -
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 -
Frontiers in Medicine 2023The aim of this study is to apply deep learning techniques for the development and validation of a system that categorizes various phases of dry age-related macular...
PURPOSE
The aim of this study is to apply deep learning techniques for the development and validation of a system that categorizes various phases of dry age-related macular degeneration (AMD), including nascent geographic atrophy (nGA), through the analysis of optical coherence tomography (OCT) images.
METHODS
A total of 3,401 OCT macular images obtained from 338 patients admitted to Shenyang Aier Eye Hospital in 2019-2021 were collected for the development of the classification model. We adopted a convolutional neural network (CNN) model and introduced hierarchical structure along with image enhancement techniques to train a two-step CNN model to detect and classify normal and three phases of dry AMD: atrophy-associated drusen regression, nGA, and geographic atrophy (GA). Five-fold cross-validation was used to evaluate the performance of the multi-label classification model.
RESULTS
Experimental results obtained from five-fold cross-validation with different dry AMD classification models show that the proposed two-step hierarchical model with image enhancement achieves the best classification performance, with a f1-score of 91.32% and a kappa coefficients of 96.09% compared to the state-of-the-art models. The results obtained from the ablation study demonstrate that the proposed method not only improves accuracy across all categories in comparison to a traditional flat CNN model, but also substantially enhances the classification performance of nGA, with an improvement from 66.79 to 81.65%.
CONCLUSION
This study introduces a novel two-step hierarchical deep learning approach in categorizing dry AMD progression phases, and demonstrates its efficacy. The high classification performance suggests its potential for guiding individualized treatment plans for patients with macular degeneration.
PubMed: 37547613
DOI: 10.3389/fmed.2023.1221453 -
Ophthalmology and Therapy Oct 2023To describe subclinical angioid streaks (AS) as a frequent, peculiar age-related macular degeneration (AMD) phenotype, comparing features of eyes with subclinical AS...
INTRODUCTION
To describe subclinical angioid streaks (AS) as a frequent, peculiar age-related macular degeneration (AMD) phenotype, comparing features of eyes with subclinical AS with those of eyes with AMD without AS.
METHODS
This was a retrospective, observational study. Among a patient cohort with AMD, we selected patients without known causes for AS whose eyes showed signs of angioid streaks (AS) on structural optical coherence tomography (OCT) but not on fundus examination. Selected OCT features of AS were Bruch's membrane (BM) breaks and large BM dehiscences.
RESULTS
Among 543 eyes of 274 patients with AMD (mean ± standard deviation: 82 ± 7 years), 73 eyes of 46 patients (81 ± 7 years; p = 0.432) showed AS features on OCT (OCT AS) that were not visible on fundus examination. Estimated prevalence of subclinical age-related AS was 13.4% (95% confidence interval 10.3-16.3%) in this AMD population. Fifty-three eyes (73%) with AS features were affected by peripapillary atrophy, often with a "petaloid-like" pattern, similar to typical features of AS disease. Almost all cases (97%) presented reticular pseudodrusen (RPD), with (41%) or without (59%) drusen showing a significant difference in RPD prevalence in OCT AS eyes in comparison to AMD eyes without subclinical AS using generalized estimating equations (P < 0.001). Among the 73 subclinical AS cases, 71 were affected by late AMD (57 with macular neovascularization, 14 with geographic atrophy), showing a more advanced AMD stage in comparison with AMD eyes without subclinical AS (P < 0.001). The following OCT features were disclosed: BM breaks in 100% of cases and BM dehiscences in 37%.
CONCLUSIONS
Subclinical AS in eyes with AMD is a peculiar phenotype of the disease, with features suggesting a primary involvement of Bruch's membrane and clinical similarities with mild, late-onset pseudoxanthoma elasticum.
PubMed: 37542615
DOI: 10.1007/s40123-023-00778-x -
Sensors (Basel, Switzerland) Jul 2023Deposition of calcium-containing minerals such as hydroxyapatite and whitlockite in the subretinal pigment epithelial (sub-RPE) space of the retina is linked to the...
Deposition of calcium-containing minerals such as hydroxyapatite and whitlockite in the subretinal pigment epithelial (sub-RPE) space of the retina is linked to the development of and progression to the end-stage of age-related macular degeneration (AMD). AMD is the most common eye disease causing blindness amongst the elderly in developed countries; early diagnosis is desirable, particularly to begin treatment where available. Calcification in the sub-RPE space is also directly linked to other diseases such as Pseudoxanthoma elasticum (PXE). We found that these mineral deposits could be imaged by fluorescence using tetracycline antibiotics as specific stains. Binding of tetracyclines to the minerals was accompanied by increases in fluorescence intensity and fluorescence lifetime. The lifetimes for tetracyclines differed substantially from the known background lifetime of the existing natural retinal fluorophores, suggesting that calcification could be visualized by lifetime imaging. However, the excitation wavelengths used to excite these lifetime changes were generally shorter than those approved for retinal imaging. Here, we show that tetracycline-stained drusen in human retinas may be imaged by fluorescence lifetime contrast using multiphoton (infrared) excitation. For this pilot study, ten eyes from six anonymous deceased donors (3 female, 3 male, mean age 83.7 years, range 79-97 years) were obtained with informed consent from the Maryland State Anatomy Board with ethical oversight and approval by the Institutional Review Board.
Topics: Male; Humans; Female; Aged; Aged, 80 and over; Tetracycline; Pilot Projects; Retina; Macular Degeneration; Anti-Bacterial Agents
PubMed: 37514920
DOI: 10.3390/s23146626 -
Bioengineering (Basel, Switzerland) Jul 2023Accurate noninvasive diagnosis of retinal disorders is required for appropriate treatment or precision medicine. This work proposes a multi-stage classification network...
Accurate noninvasive diagnosis of retinal disorders is required for appropriate treatment or precision medicine. This work proposes a multi-stage classification network built on a multi-scale (pyramidal) feature ensemble architecture for retinal image classification using optical coherence tomography (OCT) images. First, a scale-adaptive neural network is developed to produce multi-scale inputs for feature extraction and ensemble learning. The larger input sizes yield more global information, while the smaller input sizes focus on local details. Then, a feature-rich pyramidal architecture is designed to extract multi-scale features as inputs using DenseNet as the backbone. The advantage of the hierarchical structure is that it allows the system to extract multi-scale, information-rich features for the accurate classification of retinal disorders. Evaluation on two public OCT datasets containing normal and abnormal retinas (e.g., diabetic macular edema (DME), choroidal neovascularization (CNV), age-related macular degeneration (AMD), and Drusen) and comparison against recent networks demonstrates the advantages of the proposed architecture's ability to produce feature-rich classification with average accuracy of 97.78%, 96.83%, and 94.26% for the first (binary) stage, second (three-class) stage, and all-at-once (four-class) classification, respectively, using cross-validation experiments using the first dataset. In the second dataset, our system showed an overall accuracy, sensitivity, and specificity of 99.69%, 99.71%, and 99.87%, respectively. Overall, the tangible advantages of the proposed network for enhanced feature learning might be used in various medical image classification tasks where scale-invariant features are crucial for precise diagnosis.
PubMed: 37508850
DOI: 10.3390/bioengineering10070823