Quantitative Analysis of OCT for Neovascular Age-Related Macular Degeneration Using Deep Learning

Quantifying Changes on OCT in Eyes Receiving Treatment for Neovascular Age-Related Macular Degeneration

Purpose

Application of artificial intelligence (AI) to macular OCT scans to segment and quantify volumetric change in anatomical and pathological features during intravitreal treatment for neovascular age-related macular degeneration (AMD).

Design

Retrospective analysis of OCT images from the Moorfields Eye Hospital AMD Database.

Participants

A total of 2115 eyes from 1801 patients starting anti-VEGF treatment between June 1, 2012, and June 30, 2017.

Methods

The Moorfields Eye Hospital neovascular AMD database was queried for first and second eyes receiving anti-VEGF treatment and had an OCT scan at baseline and 12 months. Follow-up scans were input into the AI system and volumes of OCT variables were studied at different time points and compared with baseline volume groups. Cross-sectional comparisons between time points were conducted using Mann-Whitney U test.

Main Outcome Measures

Volume outputs of the following variables were studied: intraretinal fluid, subretinal fluid, pigment epithelial detachment (PED), subretinal hyperreflective material (SHRM), hyperreflective foci, neurosensory retina, and retinal pigment epithelium.

Results

Mean volumes of analyzed features decreased significantly from baseline to both 4 and 12 months, in both first-treated and second-treated eyes. Pathological features that reflect exudation, including pure fluid components (intraretinal fluid and subretinal fluid) and those with fluid and fibrovascular tissue (PED and SHRM), displayed similar responses to treatment over 12 months. Mean PED and SHRM volumes showed less pronounced but also substantial decreases over the first 2 months, reaching a plateau postloading phase, and minimal change to 12 months. Both neurosensory retina and retinal pigment epithelium volumes showed gradual reductions over time, and were not as substantial as exudative features.

Conclusions

We report the results of a quantitative analysis of change in retinal segmented features over time, enabled by an AI segmentation system. Cross-sectional analysis at multiple time points demonstrated significant associations between baseline OCT-derived segmented features and the volume of biomarkers at follow-up. Demonstrating how certain OCT biomarkers progress with treatment and the impact of pretreatment retinal morphology on different structural volumes may provide novel insights into disease mechanisms and aid the personalization of care. Data will be made public for future studies.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Wavelet-based selection-and-recalibration network for Parkinson's disease screening in OCT images

BACKGROUND AND OBJECTIVE

Parkinson's disease (PD) is one of the most prevalent neurodegenerative brain diseases worldwide. Therefore, accurate PD screening is crucial for early clinical intervention and treatment. Recent clinical research indicates that changes in pathology, such as the texture and thickness of the retinal layers, can serve as biomarkers for clinical PD diagnosis based on optical coherence tomography (OCT) images. However, the pathological manifestations of PD in the retinal layers are subtle compared to the more salient lesions associated with retinal diseases.

METHODS

Inspired by textural edge feature extraction in frequency domain learning, we aim to explore a potential approach to enhance the distinction between the feature distributions in retinal layers of PD cases and healthy controls. In this paper, we introduce a simple yet novel wavelet-based selection and recalibration module to effectively enhance the feature representations of the deep neural network by aggregating the unique clinical properties, such as the retinal layers in each frequency band. We combine this module with the residual block to form a deep network named Wavelet-based Selection and Recalibration Network (WaveSRNet) for automatic PD screening.

RESULTS

The extensive experiments on a clinical PD-OCT dataset and two publicly available datasets demonstrate that our approach outperforms state-of-the-art methods. Visualization analysis and ablation studies are conducted to enhance the explainability of WaveSRNet in the decision-making process.

CONCLUSIONS

Our results suggest the potential role of the retina as an assessment tool for PD. Visual analysis shows that PD-related elements include not only certain retinal layers but also the location of the fovea in OCT images.

Toward Precision Diagnosis: Machine Learning in Identifying Malignant Orbital Tumors With Multiparametric 3 T MRI

BACKGROUND

Orbital tumors present a diagnostic challenge due to their varied locations and histopathological differences. Although recent advancements in imaging have improved diagnosis, classification remains a challenge. The integration of artificial intelligence in radiology and ophthalmology has demonstrated promising outcomes.

PURPOSE

This study aimed to evaluate the performance of machine learning models in accurately distinguishing malignant orbital tumors from benign ones using multiparametric 3 T magnetic resonance imaging (MRI) data.

MATERIALS AND METHODS

In this single-center prospective study, patients with orbital masses underwent presurgery 3 T MRI scans between December 2015 and May 2021. The MRI protocol comprised multiparametric imaging including dynamic contrast-enhanced (DCE), diffusion-weighted imaging (DWI), intravoxel incoherent motion (IVIM), as well as morphological imaging acquisitions. A repeated nested cross-validation strategy using random forest classifiers was used for model training and evaluation, considering 8 combinations of explanatory features. Shapley additive explanations (SHAP) values were used to assess feature contributions, and the model performance was evaluated using multiple metrics.

RESULTS

One hundred thirteen patients were analyzed (57/113 [50.4%] were women; average age was 51.5 ± 17.5 years, range: 19-88 years). Among the 8 combinations of explanatory features assessed, the performance on predicting malignancy when using the most comprehensive model, which is the most exhaustive one incorporating all 46 explanatory features-including morphology, DWI, DCE, and IVIM, achieved an area under the curve of 0.9 [0.73-0.99]. When using the streamlined "10-feature signature" model, performance reached an area under the curve of 0.88 [0.71-0.99]. Random forest feature importance graphs measured by the mean of SHAP values pinpointed the 10 most impactful features, which comprised 3 quantitative IVIM features, 4 quantitative DCE features, 1 quantitative DWI feature, 1 qualitative DWI feature, and age.

CONCLUSIONS

Our findings demonstrate that a machine learning approach, integrating multiparametric MRI data such as DCE, DWI, IVIM, and morphological imaging, offers high-performing models for differentiating malignant from benign orbital tumors. The streamlined 10-feature signature, with a performance close to the comprehensive model, may be more suitable for clinical application.

Artificial intelligence in retinal screening using OCT images: A review of the last decade (2013-2023)

BACKGROUND AND OBJECTIVES

Optical coherence tomography (OCT) has ushered in a transformative era in the domain of ophthalmology, offering non-invasive imaging with high resolution for ocular disease detection. OCT, which is frequently used in diagnosing fundamental ocular pathologies, such as glaucoma and age-related macular degeneration (AMD), plays an important role in the widespread adoption of this technology. Apart from glaucoma and AMD, we will also investigate pertinent pathologies, such as epiretinal membrane (ERM), macular hole (MH), macular dystrophy (MD), vitreomacular traction (VMT), diabetic maculopathy (DMP), cystoid macular edema (CME), central serous chorioretinopathy (CSC), diabetic macular edema (DME), diabetic retinopathy (DR), drusen, glaucomatous optic neuropathy (GON), neovascular AMD (nAMD), myopia macular degeneration (MMD) and choroidal neovascularization (CNV) diseases. This comprehensive review examines the role that OCT-derived images play in detecting, characterizing, and monitoring eye diseases.

METHOD

The 2020 PRISMA guideline was used to structure a systematic review of research on various eye conditions using machine learning (ML) or deep learning (DL) techniques. A thorough search across IEEE, PubMed, Web of Science, and Scopus databases yielded 1787 publications, of which 1136 remained after removing duplicates. Subsequent exclusion of conference papers, review papers, and non-open-access articles reduced the selection to 511 articles. Further scrutiny led to the exclusion of 435 more articles due to lower-quality indexing or irrelevance, resulting in 76 journal articles for the review.

RESULTS

During our investigation, we found that a major challenge for ML-based decision support is the abundance of features and the determination of their significance. In contrast, DL-based decision support is characterized by a plug-and-play nature rather than relying on a trial-and-error approach. Furthermore, we observed that pre-trained networks are practical and especially useful when working on complex images such as OCT. Consequently, pre-trained deep networks were frequently utilized for classification tasks. Currently, medical decision support aims to reduce the workload of ophthalmologists and retina specialists during routine tasks. In the future, it might be possible to create continuous learning systems that can predict ocular pathologies by identifying subtle changes in OCT images.

Importance of optical coherence tomography raster scans in early detection of active fellow-eye neovascularization in unilateral neovascular age-related macular degeneration

PURPOSE

To investigate the incidence of and risk factors for failure of detection of active fellow-eye neovascularization on optical coherence tomography(OCT) crosshair scans in patients with unilateral neovascular age-related macular degeneration(AMD).

METHODS

In this retrospective study, patients who experienced the development of active neovascularization in the fellow eye during the follow-up period were included(n = 75). Cases in which the neovascularization in the fellow eye could be identified solely through crosshair scans were defined as the crosshair scan detection group(n = 63). Cases in which the aforementioned findings could not be identified through crosshair scans but could be identified through raster scans were defined as the raster scan detection group(n = 12). The factors were compared between the two groups. Risk factors related to undetected neovascularization on crosshair scans were additionally identified.

RESULTS

Active fellow-eye neovascularization, was not detected on OCT crosshair scans in 12 cases(16.0%) but was identified on raster scans in all cases. There was a significant difference in the proportion of neovascularization types between the crosshair scan detection group and the raster scan detection group(P = 0.023). Among the 35 fellow-eye neovascularization cases in patients with type 3 macular neovascularization(MNV), 10(28.6%) were not detected on crosshair scans. Multivariate analysis revealed a significantly higher risk for undetectable fellow-eye neovascularization on crosshair scans in patients with type 3 MNV than in those with typical neovascular AMD(P = 0.037,β = 9.600).

CONCLUSIONS

Our findings suggest the need for routine OCT raster scans during fellow-eye examinations in patients with unilateral neovascular AMD, particularly when the first-affected eye is diagnosed with type 3 MNV.

Transformer-Based Deep Learning Prediction of 10-Degree Humphrey Visual Field Tests From 24-Degree Data

Purpose

To predict 10-2 Humphrey visual fields (VFs) from 24-2 VFs and associated non-total deviation features using deep learning.

Methods

We included 5189 reliable 24-2 and 10-2 VF pairs from 2236 patients, and 28,409 reliable pairs of macular OCT scans and 24-2 VF from 19,527 eyes of 11,560 patients. We developed a transformer-based deep learning model using 52 total deviation values and nine VF test features to predict 68 10-2 total deviation values. The mean absolute error, root mean square error, and the R2 were evaluation metrics. We further evaluated whether the predicted 10-2 VFs can improve the structure-function relationship between macular thinning and paracentral VF loss in glaucoma.

Results

The average mean absolute error and R2 for 68 10-2 VF test points were 3.30 ± 0.52 dB and 0.70 ± 0.11, respectively. The accuracy was lower in the inferior temporal region. The model placed greater emphasis on 24-2 VF points near the central fixation point when predicting the 10-2 VFs. The inclusion of nine VF test features improved the mean absolute error and R2 up to 0.17 ± 0.06 dB and 0.01 ± 0.01, respectively. Age was the most important 24-2 VF test parameter for 10-2 VF prediction. The predicted 10-2 VFs achieved an improved structure-function relationship between macular thinning and paracentral VF loss, with the R2 at the central 4, 12, and 16 locations of 24-2 VFs increased by 0.04, 0.05 and 0.05, respectively (P < 0.001).

Conclusions

The 10-2 VFs may be predicted from 24-2 data.

Translational Relevance

The predicted 10-2 VF has the potential to improve glaucoma diagnosis.

Impact of residual retinal fluid on treatment outcomes in neovascular age-related macular degeneration

Treatment decisions for neovascular age-related macular degeneration (nAMD) in the setting of individualised treatment regimens are adapted to disease activity. The main marker of disease activity and trigger for re-treatment with anti-vascular endothelial growth factor (anti-VEGF) agents is the presence of retinal fluid on optical coherence tomography (OCT). Recently, attention has focused on the impact of residual retinal fluid on nAMD management. Based on a literature review and the combined clinical experience of an international group of retinal specialists, this manuscript provides expert guidance on the treatment of nAMD according to fluid status and proposes an algorithm for determining when to administer anti-VEGF treatment according to residual fluid status. We explore the role of residual fluid in treatment decisions and outcomes in nAMD, taking into consideration fluid evaluation and, in particular, distinguishing between fluid in different anatomic compartments and at different stages during the treatment course. Current limitations to identifying and interpreting fluid on OCT, and the assumption that any residual retinal fluid reflects ongoing VEGF activity, are discussed.

Artificial intelligence for retinal diseases

PURPOSE

To discuss the worldwide applications and potential impact of artificial intelligence (AI) for the diagnosis, management and analysis of treatment outcomes of common retinal diseases.

METHODS

We performed an online literature review, using PubMed Central (PMC), of AI applications to evaluate and manage retinal diseases. Search terms included AI for screening, diagnosis, monitoring, management, and treatment outcomes for age-related macular degeneration (AMD), diabetic retinopathy (DR), retinal surgery, retinal vascular disease, retinopathy of prematurity (ROP) and sickle cell retinopathy (SCR). Additional search terms included AI and color fundus photographs, optical coherence tomography (OCT), and OCT angiography (OCTA). We included original research articles and review articles.

RESULTS

Research studies have investigated and shown the utility of AI for screening for diseases such as DR, AMD, ROP, and SCR. Research studies using validated and labeled datasets confirmed AI algorithms could predict disease progression and response to treatment. Studies showed AI facilitated rapid and quantitative interpretation of retinal biomarkers seen on OCT and OCTA imaging. Research articles suggest AI may be useful for planning and performing robotic surgery. Studies suggest AI holds the potential to help lessen the impact of socioeconomic disparities on the outcomes of retinal diseases.

CONCLUSIONS

AI applications for retinal diseases can assist the clinician, not only by disease screening and monitoring for disease recurrence but also in quantitative analysis of treatment outcomes and prediction of treatment response. The public health impact on the prevention of blindness from DR, AMD, and other retinal vascular diseases remains to be determined.

Application and progress of artificial intelligence technology in the segmentation of hyperreflective foci in OCT images for ophthalmic disease research

With the advancement of retinal imaging, hyperreflective foci (HRF) on optical coherence tomography (OCT) images have gained significant attention as potential biological biomarkers for retinal neuroinflammation. However, these biomarkers, represented by HRF, present pose challenges in terms of localization, quantification, and require substantial time and resources. In recent years, the progress and utilization of artificial intelligence (AI) have provided powerful tools for the analysis of biological markers. AI technology enables use machine learning (ML), deep learning (DL) and other technologies to precise characterization of changes in biological biomarkers during disease progression and facilitates quantitative assessments. Based on ophthalmic images, AI has significant implications for early screening, diagnostic grading, treatment efficacy evaluation, treatment recommendations, and prognosis development in common ophthalmic diseases. Moreover, it will help reduce the reliance of the healthcare system on human labor, which has the potential to simplify and expedite clinical trials, enhance the reliability and professionalism of disease management, and improve the prediction of adverse events. This article offers a comprehensive review of the application of AI in combination with HRF on OCT images in ophthalmic diseases including age-related macular degeneration (AMD), diabetic macular edema (DME), retinal vein occlusion (RVO) and other retinal diseases and presents prospects for their utilization.

Deep Learning in Neovascular Age-Related Macular Degeneration

Background and objectives: Age-related macular degeneration (AMD) is a complex and multifactorial condition that can lead to permanent vision loss once it progresses to the neovascular exudative stage. This review aims to summarize the use of deep learning in neovascular AMD. Materials and Methods: Pubmed search. Results: Deep learning has demonstrated effectiveness in analyzing structural OCT images in patients with neovascular AMD. This review outlines the role of deep learning in identifying and measuring biomarkers linked to an elevated risk of transitioning to the neovascular form of AMD. Additionally, deep learning techniques can quantify critical OCT features associated with neovascular AMD, which have prognostic implications for these patients. Incorporating deep learning into the assessment of neovascular AMD eyes holds promise for enhancing clinical management strategies for affected individuals. Conclusion: Several studies have demonstrated effectiveness of deep learning in assessing neovascular AMD patients and this has a promising role in the assessment of these patients.

A deep learning approach to explore the association of age-related macular degeneration polygenic risk score with retinal optical coherence tomography: A preliminary study

PURPOSE

Age-related macular degeneration (AMD) is a complex eye disorder affecting millions worldwide. This article uses deep learning techniques to investigate the relationship between AMD, genetics and optical coherence tomography (OCT) scans.

METHODS

The cohort consisted of 332 patients, of which 235 were diagnosed with AMD and 97 were controls with no signs of AMD. The genome-wide association studies summary statistics utilized to establish the polygenic risk score (PRS) in relation to AMD were derived from the GERA European study. A PRS estimation based on OCT volumes for both eyes was performed using a proprietary convolutional neural network (CNN) model supported by machine learning models. The method's performance was assessed using numerical evaluation metrics, and the Grad-CAM technique was used to evaluate the results by visualizing the features learned by the model.

RESULTS

The best results were obtained with the CNN and the Extra Tree regressor (MAE = 0.55, MSE = 0.49, RMSE = 0.70, R2 = 0.34). Extending the feature vector with additional information on AMD diagnosis, age and smoking history improved the results slightly, with mainly AMD diagnosis used by the model (MAE = 0.54, MSE = 0.44, RMSE = 0.66, R2 = 0.42). Grad-CAM heatmap evaluation showed that the model decisions rely on retinal morphology factors relevant to AMD diagnosis.

CONCLUSION

The developed method allows an efficient PRS estimation from OCT images. A new technique for analysing the association of OCT images with PRS of AMD, using a deep learning approach, may provide an opportunity to discover new associations between genotype-based AMD risk and retinal morphology.

Double-dose investigation of aflibercept in neovascular age-related macular degeneration (DIANA): a real-world study

BACKGROUND

To investigate the clinical effects of double-dose (4 mg) aflibercept treatment in neovascular age-related macular degeneration (nAMD), compared with the standard-dose (2 mg) treatment.

METHODS

A total of 108 eyes from 97 patients with nAMD and received intravitreal aflibercept 2 mg and/or 4 mg treatment were retrospectively reviewed. The changes of central macular thickness (CMT)/ pigmental epithelium detachment height and the recurrence rate of exudation during the 12-month follow-up were compared between the 2 mg group and the 4 mg group. Self-control comparisons (2 mg switch to 4 mg) were also made between two regimens.

RESULTS

Compared with the 2 mg group, tendencies of lower intraretinal fluid incidence and more CMT reduction were observed in the 4 mg group. The later one was also observed when eyes switching from 2 mg to 4 mg regimen. The median remission interval was 5 months in the 4 mg group, 2 months longer than the 3 months in the 2 mg group (P = 0.452). Injections needed in the 4 mg group were 3.644 ± 1.670, less than the 4.286 ± 2.334 injections in the 2 mg group within 12 months as well (P = 0.151). However, no associated vision benefits were gained from the double-douse regimen. No markedly increased-intraocular pressure events, or other adverse events were found in two groups.

CONCLUSIONS

Compared to the aflibercept 2 mg treatment in nAMD, tendencies of anatomic gains and relieving treatment burden were brought by the aflibercept 4 mg treatment. This study may have additional importance, given the further application of high-dose aflibercept in real-world settings.

AI-based support for optical coherence tomography in age-related macular degeneration

Artificial intelligence (AI) has emerged as a transformative technology across various fields, and its applications in the medical domain, particularly in ophthalmology, has gained significant attention. The vast amount of high-resolution image data, such as optical coherence tomography (OCT) images, has been a driving force behind AI growth in this field. Age-related macular degeneration (AMD) is one of the leading causes for blindness in the world, affecting approximately 196 million people worldwide in 2020. Multimodal imaging has been for a long time the gold standard for diagnosing patients with AMD, however, currently treatment and follow-up in routine disease management are mainly driven by OCT imaging. AI-based algorithms have by their precision, reproducibility and speed, the potential to reliably quantify biomarkers, predict disease progression and assist treatment decisions in clinical routine as well as academic studies. This review paper aims to provide a summary of the current state of AI in AMD, focusing on its applications, challenges, and prospects.

Ophthalmology Optical Coherence Tomography Databases for Artificial Intelligence Algorithm: A Review

BACKGROUND

Imaging plays a pivotal role in eye assessment. With the introduction of advanced machine learning and artificial intelligence (AI), the focus has shifted to imaging datasets in ophthalmology. While disparities and health inequalities hidden within data are well-documented, the ophthalmology field faces specific challenges to the creation and maintenance of datasets. Optical Coherence Tomography (OCT) is useful for the diagnosis and monitoring of retinal pathologies, making it valuable for AI applications. This review aims to identify and compare the landscape of publicly available optical coherence tomography databases for AI applications.

METHODS

We conducted a literature review on OCT and AI articles with publicly accessible datasets, using PubMed, Scopus, and Web of Science databases. The review retrieved 183 articles, and after full-text analysis, 50 articles were included. From the included articles were identified 8 publicly available OCT datasets, focusing on patient demographics and clinical details for thorough assessment and comparison.

RESULTS

The resulting datasets encompass 154,313 images collected from Spectralis, Cirrus HD, Topcon 3D, and Bioptigen devices. These datasets included normal exams, age-related macular degeneration, and diabetic maculopathy, among others. Comprehensive demographic information is available in one dataset and the USA is the most represented population.

DISCUSSION

Current publicly available OCT databases for AI applications exhibit limitations, stemming from their non-representative nature and the lack of comprehensive demographic information. Limited datasets hamper research and equitable AI development. To promote equitable AI algorithmic development in ophthalmology, there is a need for the creation and dissemination of more representative datasets.

Deep learning-based fully automated grading system for dry eye disease severity

There is an increasing need for an objective grading system to evaluate the severity of dry eye disease (DED). In this study, a fully automated deep learning-based system for the assessment of DED severity was developed. Corneal fluorescein staining (CFS) images of DED patients from one hospital for system development (n = 1400) and from another hospital for external validation (n = 94) were collected. Three experts graded the CFS images using NEI scale, and the median value was used as ground truth. The system was developed in three steps: (1) corneal segmentation, (2) CFS candidate region classification, and (3) estimation of NEI grades by CFS density map generation. Also, two images taken on different days in 50 eyes (100 images) were compared to evaluate the probability of improvement or deterioration. The Dice coefficient of the segmentation model was 0.962. The correlation between the system and the ground truth data was 0.868 (p<0.001) and 0.863 (p<0.001) for the internal and external validation datasets, respectively. The agreement rate for improvement or deterioration was 88% (44/50). The fully automated deep learning-based grading system for DED severity can evaluate the CFS score with high accuracy and thus may have potential for clinical application.

Associations of presenting visual acuity with morphological changes on OCT in neovascular age-related macular degeneration: PRECISE Study Report 2

PURPOSE

To study associations of optical coherence tomography (OCT) features with presenting visual acuity (VA) in treatment naive neovascular age-related macular degeneration (nAMD).

METHODS

Patients with nAMD initiated on aflibercept therapy were recruited from December 2019 to August 2021. Demographic and OCT (Spectralis, Heidelberg Engineering) features associated with good VA (VA ≥ 68 ETDRS letters, Snellen ≥ 6/12) and poor VA (VA < 54 letters, Snellen < 6/18) were analysed using Generalised Estimating Equations to account for inter-eye correlation.

RESULTS

Of 2274 eyes of 2128 patients enrolled, 2039 eyes of 1901 patients with complete data were analysed. Mean age was 79.4 (SD 7.8) years, female:male 3:2 and mean VA 58.0 (SD 14.5) letters. On multivariable analysis VA < 54 letters was associated with increased central subfield thickness (CST) (OR 1.40 per 100 µm; P < 0.001), foveal intraretinal fluid (OR 2.14; P < 0.001), polypoidal vasculopathy (PCV) relative to Type 1 macular neovascularisation (MNV) (OR 1.66; P = 0.049), presence of foveal subretinal hyperreflective material (SHRM) (OR 1.73; P = 0.002), foveal fibrosis (OR 3.85; P < 0.001), foveal atrophy (OR 5.54; P < 0.001), loss of integrity of the foveal ellipsoid zone (EZ) or external limiting membrane (ELM) relative to their preservation (OR 3.83; P < 0.001) and absence of subretinal drusenoid deposits (SDD) (presence vs absence; OR 0.75; P = 0.04). These features were associated with reduced odds of VA ≥ 68 letters except MNV subtypes and SDD.

CONCLUSION

Presence of baseline fovea-involving atrophy, fibrosis, intraretinal fluid, SHRM, PCV EZ/ELM loss and increased CST determine poor presenting VA. This highlights the need for early detection and treatment prior to structural changes that worsen baseline VA.

Deep Learning-Based Retinal Layer Segmentation in Optical Coherence Tomography Scans of Patients with Inherited Retinal Diseases

BACKGROUND

In optical coherence tomography (OCT) scans of patients with inherited retinal diseases (IRDs), the measurement of the thickness of the outer nuclear layer (ONL) has been well established as a surrogate marker for photoreceptor preservation. Current automatic segmentation tools fail in OCT segmentation in IRDs, and manual segmentation is time-consuming.

METHODS AND MATERIAL

Patients with IRD and an available OCT scan were screened for the present study. Additionally, OCT scans of patients without retinal disease were included to provide training data for artificial intelligence (AI). We trained a U-net-based model on healthy patients and applied a domain adaption technique to the IRD patients' scans.

RESULTS

We established an AI-based image segmentation algorithm that reliably segments the ONL in OCT scans of IRD patients. In a test dataset, the dice score of the algorithm was 98.7%. Furthermore, we generated thickness maps of the full retinal thickness and the ONL layer for each patient.

CONCLUSION

Accurate segmentation of anatomical layers on OCT scans plays a crucial role for predictive models linking retinal structure to visual function. Our algorithm for segmentation of OCT images could provide the basis for further studies on IRDs.

High-accuracy 3D segmentation of wet age-related macular degeneration via multi-scale and cross-channel feature extraction and channel attention

Wet age-related macular degeneration (AMD) is the leading cause of visual impairment and vision loss in the elderly, and optical coherence tomography (OCT) enables revolving biotissue three-dimensional micro-structure widely used to diagnose and monitor wet AMD lesions. Many wet AMD segmentation methods based on deep learning have achieved good results, but these segmentation results are two-dimensional, and cannot take full advantage of OCT's three-dimensional (3D) imaging characteristics. Here we propose a novel deep-learning network characterizing multi-scale and cross-channel feature extraction and channel attention to obtain high-accuracy 3D segmentation results of wet AMD lesions and show the 3D specific morphology, a task unattainable with traditional two-dimensional segmentation. This probably helps to understand the ophthalmologic disease and provides great convenience for the clinical diagnosis and treatment of wet AMD.

Deep-learning based automated quantification of critical optical coherence tomography features in neovascular age-related macular degeneration

PURPOSE

To validate a deep learning algorithm for automated intraretinal fluid (IRF), subretinal fluid (SRF) and neovascular pigment epithelium detachment (nPED) segmentations in neovascular age-related macular degeneration (nAMD).

METHODS

In this IRB-approved study, optical coherence tomography (OCT) data from 50 patients (50 eyes) with exudative nAMD were retrospectively analysed. Two models, A1 and A2, were created based on gradings from two masked readers, R1 and R2. Area under the curve (AUC) values gauged detection performance, and quantification between readers and models was evaluated using Dice and correlation (R2) coefficients.

RESULTS

The deep learning-based algorithms had high accuracies for all fluid types between all models and readers: per B-scan IRF AUCs were 0.953, 0.932, 0.990, 0.942 for comparisons A1-R1, A1-R2, A2-R1 and A2-R2, respectively; SRF AUCs were 0.984, 0.974, 0.987, 0.979; and nPED AUCs were 0.963, 0.969, 0.961 and 0.966. Similarly, the R2 coefficients for IRF were 0.973, 0.974, 0.889 and 0.973; SRF were 0.928, 0.964, 0.965 and 0.998; and nPED were 0.908, 0.952, 0.839 and 0.905. The Dice coefficients for IRF averaged 0.702, 0.667, 0.649 and 0.631; for SRF were 0.699, 0.651, 0.692 and 0.701; and for nPED were 0.636, 0.703, 0.719 and 0.775. In an inter-observer comparison between manual readers R1 and R2, the R2 coefficient was 0.968 for IRF, 0.960 for SRF, and 0.906 for nPED, with Dice coefficients of 0.692, 0.660 and 0.784 for the same features.

CONCLUSIONS

Our deep learning-based method applied on nAMD can segment critical OCT features with performance akin to manual grading.

Artificial intelligence-based fluid quantification and associated visual outcomes in a real-world, multicentre neovascular age-related macular degeneration national database

AIM

To explore associations between artificial intelligence (AI)-based fluid compartment quantifications and 12 months visual outcomes in OCT images from a real-world, multicentre, national cohort of naïve neovascular age-related macular degeneration (nAMD) treated eyes.

METHODS

Demographics, visual acuity (VA), drug and number of injections data were collected using a validated web-based tool. Fluid compartment quantifications including intraretinal fluid (IRF), subretinal fluid (SRF) and pigment epithelial detachment (PED) in the fovea (1 mm), parafovea (3 mm) and perifovea (6 mm) were measured in nanoliters (nL) using a validated AI-tool.

RESULTS

452 naïve nAMD eyes presented a mean VA gain of +5.5 letters with a median of 7 injections over 12 months. Baseline foveal IRF associated poorer baseline (44.7 vs 63.4 letters) and final VA (52.1 vs 69.1), SRF better final VA (67.1 vs 59.0) and greater VA gains (+7.1 vs +1.9), and PED poorer baseline (48.8 vs 57.3) and final VA (55.1 vs 64.1). Predicted VA gains were greater for foveal SRF (+6.2 vs +0.6), parafoveal SRF (+6.9 vs +1.3), perifoveal SRF (+6.2 vs -0.1) and parafoveal IRF (+7.4 vs +3.6, all p<0.05). Fluid dynamics analysis revealed the greatest relative volume reduction for foveal SRF (-16.4 nL, -86.8%), followed by IRF (-17.2 nL, -84.7%) and PED (-19.1 nL, -28.6%). Subgroup analysis showed greater reductions in eyes with higher number of injections.

CONCLUSION

This real-world study describes an AI-based analysis of fluid dynamics and defines baseline OCT-based patient profiles that associate 12-month visual outcomes in a large cohort of treated naïve nAMD eyes nationwide.

Intelligent diagnosis of retinal vein occlusion based on color fundus photographs

AIM

To develop an artificial intelligence (AI) diagnosis model based on deep learning (DL) algorithm to diagnose different types of retinal vein occlusion (RVO) by recognizing color fundus photographs (CFPs).

METHODS

Totally 914 CFPs of healthy people and patients with RVO were collected as experimental data sets, and used to train, verify and test the diagnostic model of RVO. All the images were divided into four categories [normal, central retinal vein occlusion (CRVO), branch retinal vein occlusion (BRVO), and macular retinal vein occlusion (MRVO)] by three fundus disease experts. Swin Transformer was used to build the RVO diagnosis model, and different types of RVO diagnosis experiments were conducted. The model's performance was compared to that of the experts.

RESULTS

The accuracy of the model in the diagnosis of normal, CRVO, BRVO, and MRVO reached 1.000, 0.978, 0.957, and 0.978; the specificity reached 1.000, 0.986, 0.982, and 0.976; the sensitivity reached 1.000, 0.955, 0.917, and 1.000; the F1-Sore reached 1.000, 0.955 0.943, and 0.887 respectively. In addition, the area under curve of normal, CRVO, BRVO, and MRVO diagnosed by the diagnostic model were 1.000, 0.900, 0.959 and 0.970, respectively. The diagnostic results were highly consistent with those of fundus disease experts, and the diagnostic performance was superior.

CONCLUSION

The diagnostic model developed in this study can well diagnose different types of RVO, effectively relieve the work pressure of clinicians, and provide help for the follow-up clinical diagnosis and treatment of RVO patients.

Research on an artificial intelligence-based myopic maculopathy grading method using EfficientNet

PURPOSE

We aimed to develop an artificial intelligence-based myopic maculopathy grading method using EfficientNet to overcome the delayed grading and diagnosis of different myopic maculopathy degrees.

METHODS

The cooperative hospital provided 4642 healthy and myopic maculopathy color fundus photographs, comprising the four degrees of myopic maculopathy and healthy fundi. The myopic maculopathy grading models were trained using EfficientNet-B0 to EfficientNet-B7 models. The diagnostic results were compared with those of the VGG16 and ResNet50 classification models. The leading evaluation indicators were sensitivity, specificity, F1 score, area under the receiver operating characteristic (ROC) curve area under curve (AUC), 95% confidence interval, kappa value, and accuracy. The ROC curves of the ten grading models were also compared.

RESULTS

We used 1199 color fundus photographs to evaluate the myopic maculopathy grading models. The size of the EfficientNet-B0 myopic maculopathy grading model was 15.6 MB, and it had the highest kappa value (88.32%) and accuracy (83.58%). The model's sensitivities to diagnose tessellated fundus (TF), diffuse chorioretinal atrophy (DCA), patchy chorioretinal atrophy (PCA), and macular atrophy (MA) were 96.86%, 75.98%, 64.67%, and 88.75%, respectively. The specificity was above 93%, and the AUCs were 0.992, 0.960, 0.964, and 0.989, respectively.

CONCLUSION

The EfficientNet models were used to design grading diagnostic models for myopic maculopathy. Based on the collected fundus images, the models could diagnose a healthy fundus and four types of myopic maculopathy. The models might help ophthalmologists to make preliminary diagnoses of different degrees of myopic maculopathy.

The Localization of Intraretinal Cysts Has a Clinical Role on the 2-Year Outcome of Neovascular Age-Related Macular Degeneration

OBJECTIVE

To assess the relationship between ≥ 1 localizations of intraretinal fluid (IRF) within retinal layers and the 2-year outcome in a cohort of neovascular age-related macular degeneration (AMD) eyes.

DESIGN

Retrospective case series.

PARTICIPANTS

Two hundred forty-three eyes of 243 AMD patients affected by type 1 and type 2 macular neovascularization (MNV).

METHODS

We analyzed data considering MNV onset, 1-year, and 2-year timepoints. Optical coherence tomography images were used to classify MNV types, distinguish different types of fluids and assess IRF localization within retinal layers. A subcohort of eyes were also analyzed by OCT angiography.

MAIN OUTCOME MEASURES

The association between IRF cyst localization and both visual outcome and onset of outer retinal atrophy at 2-year follow-up.

RESULTS

Macular neovascularizations were distributed as type 1 (69%) and type 2 (31%). The mean number of intravitreal injections was 7 ± 2 at 1-year follow-up and 5 ± 2 at 2-year follow-up. Baseline best-corrected visual acuity was 0.4 ± 0.3 logarithm of the minimum angle of resolution, improving to 0.3 ± 0.4 at 2-year follow-up (P < 0.01). Outer retinal atrophy occurred in 24% of cases at 1 year and 39% of cases at 2-year follow-up. Intraretinal fluid localizations at the level of IPL-INL and OPL-ONL at baseline were associated with the worst functional and anatomical outcome. Moreover, the presence of IRF at baseline was associated with greater impairment of the intraretinal vascular network.

CONCLUSIONS

The localization of IRF at the level of IPL-INL and OPL-ONL retinal layers represents a negative prognostic biomarker for the morphologic and functional outcomes of neovascular AMD.

FINANCIAL DISCLOSURE(S)

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Segmentation of paracentral acute middle maculopathy lesions in spectral-domain optical coherence tomography images through weakly supervised deep convolutional networks

BACKGROUND AND OBJECTIVES

Spectral-domain optical coherence tomography (SD-OCT) is a valuable tool for non-invasive imaging of the retina, allowing the discovery and visualization of localized lesions, the presence of which is associated with eye diseases. The present study introduces X-Net, a weakly supervised deep-learning framework for automated segmentation of paracentral acute middle maculopathy (PAMM) lesions in retinal SD-OCT images. Despite recent advances in the development of automatic methods for clinical analysis of OCT scans, there remains a scarcity of studies focusing on the automated detection of small retinal focal lesions. Additionally, most existing solutions depend on supervised learning, which can be time-consuming and require extensive image labeling, whereas X-Net offers a solution to these challenges. As far as we can determine, no prior study has addressed the segmentation of PAMM lesions in SD-OCT images.

METHODS

This study leverages 133 SD-OCT retinal images, each containing instances of paracentral acute middle maculopathy lesions. A team of eye experts annotated the PAMM lesions in these images using bounding boxes. Then, labeled data were used to train a U-Net that performs pre-segmentation, producing region labels of pixel-level accuracy. To attain a highly-accurate final segmentation, we introduced X-Net, a novel neural network made up of a master and a slave U-Net. During training, it takes the expert annotated, and pixel-level pre-segment annotated images and employs sophisticated strategies to ensure the highest segmentation accuracy.

RESULTS

The proposed method was rigorously evaluated on clinical retinal images excluded from training and achieved an accuracy of 99% with a high level of similarity between the automatic segmentation and expert annotation, as demonstrated by a mean Intersection-over-Union of 0.8. Alternative methods were tested on the same data. Single-stage neural networks proved insufficient for achieving satisfactory results, confirming that more advanced solutions, such as the proposed method, are necessary. We also found that X-Net using Attention U-net for both the pre-segmentation and X-Net arms for the final segmentation shows comparable performance to the proposed method, suggesting that the proposed approach remains a viable solution even when implemented with variants of the classic U-Net.

CONCLUSIONS

The proposed method exhibits reasonably high performance, validated through quantitative and qualitative evaluations. Medical eye specialists have also verified its validity and accuracy. Thus, it could be a viable tool in the clinical assessment of the retina. Additionally, the demonstrated approach for annotating the training set has proven to be effective in reducing the expert workload.

Recent evidence of economic evaluation of artificial intelligence in ophthalmology

PURPOSE OF REVIEW

Health economic evaluation (HEE) is essential for assessing value of health interventions, including artificial intelligence. Recent approaches, current challenges, and future directions of HEE of artificial intelligence in ophthalmology are reviewed.

RECENT FINDINGS

Majority of recent HEEs of artificial intelligence in ophthalmology were for diabetic retinopathy screening. Two models, one conducted in the rural USA (5-year period) and another in China (35-year period), found artificial intelligence to be more cost-effective than without screening for diabetic retinopathy. Two additional models, which compared artificial intelligence with human screeners in Brazil and Thailand for the lifetime of patients, found artificial intelligence to be more expensive from a healthcare system perspective. In the Thailand analysis, however, artificial intelligence was less expensive when opportunity loss from blindness was included. An artificial intelligence model for screening retinopathy of prematurity was cost-effective in the USA. A model for screening age-related macular degeneration in Japan and another for primary angle close in China did not find artificial intelligence to be cost-effective, compared with no screening. The costs of artificial intelligence varied widely in these models.

SUMMARY

Like other medical fields, there is limited evidence in assessing the value of artificial intelligence in ophthalmology and more appropriate HEE models are needed.

Diagnosis, Classification, and Assessment of the Underlying Etiology of Uveitis by Artificial Intelligence: A Systematic Review

Recent years have seen the emergence and application of artificial intelligence (AI) in diagnostic decision support systems. There are approximately 80 etiologies that can underly uveitis, some very rare, and AI may lend itself to their detection. This synthesis of the literature selected articles that focused on the use of AI in determining the diagnosis, classification, and underlying etiology of uveitis. The AI-based systems demonstrated relatively good performance, with a classification accuracy of 93-99% and a sensitivity of at least 80% for identifying the two most probable etiologies underlying uveitis. However, there were limitations to the evidence. Firstly, most data were collected retrospectively with missing data. Secondly, ophthalmic, demographic, clinical, and ancillary tests were not reliably integrated into the algorithms' dataset. Thirdly, patient numbers were small, which is problematic when aiming to discriminate rare and complex diagnoses. In conclusion, the data indicate that AI has potential as a diagnostic decision support system, but clinical applicability is not yet established. Future studies and technologies need to incorporate more comprehensive clinical data and larger patient populations. In time, these should improve AI-based diagnostic tools and help clinicians diagnose, classify, and manage patients with uveitis.

Ocular images-based artificial intelligence on systemic diseases

PURPOSE

To provide a summary of the research advances on ocular images-based artificial intelligence on systemic diseases.

METHODS

Narrative literature review.

RESULTS

Ocular images-based artificial intelligence has been used in a variety of systemic diseases, including endocrine, cardiovascular, neurological, renal, autoimmune, and hematological diseases, and many others. However, the studies are still at an early stage. The majority of studies have used AI only for diseases diagnosis, and the specific mechanisms linking systemic diseases to ocular images are still unclear. In addition, there are many limitations to the research, such as the number of images, the interpretability of artificial intelligence, rare diseases, and ethical and legal issues.

CONCLUSION

While ocular images-based artificial intelligence is widely used, the relationship between the eye and the whole body should be more clearly elucidated.

Retinal fluid is associated with cytokines of aqueous humor in age-related macular degeneration using automatic 3-dimensional quantification

Background: To explain the biological role of cytokines in the eye and the possible role of cytokines in the pathogenesis of neovascular age-related macular degeneration (nAMD) by comparing the correlation between cytokine of aqueous humor concentration and optical coherence tomography (OCT) retinal fluid. Methods: Spectral-domain OCT (SD-OCT) images and aqueous humor samples were collected from 20 nAMD patient's three clinical visits. Retinal fluid volume in OCT was automatically quantified using deep learning--Deeplabv3+. Eighteen cytokines were detected in aqueous humor using the Luminex technology. OCT fluid volume measurements were correlated with changes in aqueous humor cytokine levels using Pearson's correlation coefficient (PCC). Results: The patients with intraretinal fluid (IRF) showed significantly lower levels of cytokines, such as C-X-C motif chemokine ligand 2 (CXCL2) (p = 0.03) and CXCL11 (p = 0.009), compared with the patients without IRF. And the IRF volume was negatively correlated with CXCL2 (r = -0.407, p = 0.048) and CXCL11 (r = -0.410, p = 0.046) concentration in the patients with IRF. Meanwhile, the subretinal fluid (SRF) volume was positively correlated with vascular endothelial growth factor (VEGF) concentration (r = 0.299, p = 0.027) and negatively correlated with interleukin (IL)-36β concentration (r = -0.295, p = 0.029) in the patients with SRF. Conclusion: Decreased level of VEGF was associated with decreased OCT-based retinal fluid volume in nAMD patients, while increased levels of CXCL2, CXCL11, and IL-36β were associated with decreased OCT-based retinal fluid volume in nAMD patients, which may suggest a role for inflammatory cytokines in retinal morphological changes and pathogenesis of nAMD patients.

Polypoidal Choroidal Vasculopathy: Updates on Risk Factors, Diagnosis, and Treatments

There have been recent advances in basic research and clinical studies in polypoidal choroidal vasculopathy (PCV). A recent, large-scale, population-based study found systemic factors, such as male gender and smoking, were associated with PCV, and a recent systematic review reported plasma C-reactive protein, a systemic biomarker, was associated with PCV. Growing evidence points to an association between pachydrusen, recently proposed extracellular deposits associated with the thick choroid, and the risk of development of PCV. Many recent studies on diagnosis of PCV have focused on applying criteria from noninvasive multimodal retinal imaging without requirement of indocyanine green angiography. There have been attempts to develop deep learning models, a recent subset of artificial intelligence, for detecting PCV from different types of retinal imaging modality. Some of these deep learning models were found to have high performance when they were trained and tested on color retinal images with corresponding images from optical coherence tomography. The treatment of PCV is either a combination therapy using verteporfin photodynamic therapy and anti-vascular endothelial growth factor (VEGF), or anti-VEGF monotherapy, often used with a treat-and-extend regimen. New anti-VEGF agents may provide more durable treatment with similar efficacy, compared with existing anti-VEGF agents. It is not known if they can induce greater closure of polypoidal lesions, in which case, combination therapy may still be a mainstay. Recent evidence supports long-term follow-up of patients with PCV after treatment for early detection of recurrence, particularly in patients with incomplete closure of polypoidal lesions.

Latest Development on Genetics of Common Retinal Diseases

Many complex forms of retinal diseases are common and pan-ethnic in occurrence. Among them, neovascular age-related macular degeneration, polypoidal choroidal vasculopathy, and central serous choroid retinopathy involve both choroidopathy and neovascularization with multifactorial etiology. They are sight-threatening and potentially blinding. Early treatment is crucial to prevent disease progression. To understand their genetic basis, candidate gene mutational and association analyses, linkage analysis, genome-wide association studies, transcriptome analysis, next-generation sequencing, which includes targeted deep sequencing, whole-exome sequencing, and whole genome sequencing have been conducted. Advanced genomic technologies have led to the identification of many associated genes. But their etiologies are attributed to complicated interactions of multiple genetic and environmental risk factors. Onset and progression of neovascular age-related macular degeneration and polypoidal choroidal vasculopathy are affected by aging, smoking, lifestyle, and variants in over 30 genes. Although some genetic associations have been confirmed and validated, individual genes or polygenic risk markers of clinical value have not been established. The genetic architectures of all these complex retinal diseases that involve sequence variant quantitative trait loci have not been fully delineated. Recently artificial intelligence is making an impact in the collection and advanced analysis of genetic, investigative, and lifestyle data for the establishment of predictive factors for the risk of disease onset, progression, and prognosis. This will contribute to individualized precision medicine for the management of complex retinal diseases.

Practical guidance for imaging biomarkers in exudative age-related macular degeneration

We provide an overview of current macular imaging techniques and identify and describe biomarkers that may be of use in the routine management of macular diseases, particularly exudative age-related macular degeneration (n-AMD). This perspective includes sections on macular imaging techniques including optical coherence tomography (OCT) and OCT angiography (OCTA), classification of exudative AMD, and biomarkers in structural OCT and OCTA. Fluorescein angiography remains a vital tool for assessing the activity of neovascular lesion, while indocyanine green angiography is the preferred option for choroidal vessels imaging in neovascular AMD. OCT provides a non-invasive three-dimensional visualization of retinal architecture in vivo and is useful in the diagnosis of many imaging biomarkers of AMD-related neovascular lesions including lesion activity. OCTA is a recent advance in OCT technology that allows accurate visualization of retinal and choroidal vascular flow. OCT and OCTA have led to an updated classification of exudative AMD lesions and provide several biomarkers that help to establish a diagnosis and the disease activity status of neovascular lesions. Individualization of therapy guided by OCT and OCTA biomarkers has the potential to further improve visual outcomes in exudative AMD. Moving forwards, integration of technologically advanced imaging equipment with AI software will help ophthalmologists to provide patients with the best possible care.

Safety and efficacy of an artificial intelligence-enabled decision tool for treatment decisions in neovascular age-related macular degeneration and an exploration of clinical pathway integration and implementation: protocol for a multi-methods validation study

INTRODUCTION

Neovascular age-related macular degeneration (nAMD) management is one of the largest single-disease contributors to hospital outpatient appointments. Partial automation of nAMD treatment decisions could reduce demands on clinician time. Established artificial intelligence (AI)-enabled retinal imaging analysis tools, could be applied to this use-case, but are not yet validated for it. A primary qualitative investigation of stakeholder perceptions of such an AI-enabled decision tool is also absent. This multi-methods study aims to establish the safety and efficacy of an AI-enabled decision tool for nAMD treatment decisions and understand where on the clinical pathway it could sit and what factors are likely to influence its implementation.

METHODS AND ANALYSIS

Single-centre retrospective imaging and clinical data will be collected from nAMD clinic visits at a National Health Service (NHS) teaching hospital ophthalmology service, including judgements of nAMD disease stability or activity made in real-world consultant-led-care. Dataset size will be set by a power calculation using the first 127 randomly sampled eligible clinic visits. An AI-enabled retinal segmentation tool and a rule-based decision tree will independently analyse imaging data to report nAMD stability or activity for each of these clinic visits. Independently, an external reading centre will receive both clinical and imaging data to generate an enhanced reference standard for each clinic visit. The non-inferiority of the relative negative predictive value of AI-enabled reports on disease activity relative to consultant-led-care judgements will then be tested. In parallel, approximately 40 semi-structured interviews will be conducted with key nAMD service stakeholders, including patients. Transcripts will be coded using a theoretical framework and thematic analysis will follow.

ETHICS AND DISSEMINATION

NHS Research Ethics Committee and UK Health Research Authority approvals are in place (21/NW/0138). Informed consent is planned for interview participants only. Written and oral dissemination is planned to public, clinical, academic and commercial stakeholders.

Quantitative approaches in multimodal fundus imaging: State of the art and future perspectives

When it first appeared, multimodal fundus imaging revolutionized the diagnostic workup and provided extremely useful new insights into the pathogenesis of fundus diseases. The recent addition of quantitative approaches has further expanded the amount of information that can be obtained. In spite of the growing interest in advanced quantitative metrics, the scientific community has not reached a stable consensus on repeatable, standardized quantitative techniques to process and analyze the images. Furthermore, imaging artifacts may considerably affect the processing and interpretation of quantitative data, potentially affecting their reliability. The aim of this survey is to provide a comprehensive summary of the main multimodal imaging techniques, covering their limitations as well as their strengths. We also offer a thorough analysis of current quantitative imaging metrics, looking into their technical features, limitations, and interpretation. In addition, we describe the main imaging artifacts and their potential impact on imaging quality and reliability. The prospect of increasing reliance on artificial intelligence-based analyses suggests there is a need to develop more sophisticated quantitative metrics and to improve imaging technologies, incorporating clear, standardized, post-processing procedures. These measures are becoming urgent if these analyses are to cross the threshold from a research context to real-life clinical practice.

Comprehensive Review on the Use of Artificial Intelligence in Ophthalmology and Future Research Directions

BACKGROUND

Having several applications in medicine, and in ophthalmology in particular, artificial intelligence (AI) tools have been used to detect visual function deficits, thus playing a key role in diagnosing eye diseases and in predicting the evolution of these common and disabling diseases. AI tools, i.e., artificial neural networks (ANNs), are progressively involved in detecting and customized control of ophthalmic diseases. The studies that refer to the efficiency of AI in medicine and especially in ophthalmology were analyzed in this review.

MATERIALS AND METHODS

We conducted a comprehensive review in order to collect all accounts published between 2015 and 2022 that refer to these applications of AI in medicine and especially in ophthalmology. Neural networks have a major role in establishing the demand to initiate preliminary anti-glaucoma therapy to stop the advance of the disease.

RESULTS

Different surveys in the literature review show the remarkable benefit of these AI tools in ophthalmology in evaluating the visual field, optic nerve, and retinal nerve fiber layer, thus ensuring a higher precision in detecting advances in glaucoma and retinal shifts in diabetes. We thus identified 1762 applications of artificial intelligence in ophthalmology: review articles and research articles (301 pub med, 144 scopus, 445 web of science, 872 science direct). Of these, we analyzed 70 articles and review papers (diabetic retinopathy (N = 24), glaucoma (N = 24), DMLV (N = 15), other pathologies (N = 7)) after applying the inclusion and exclusion criteria.

CONCLUSION

In medicine, AI tools are used in surgery, radiology, gynecology, oncology, etc., in making a diagnosis, predicting the evolution of a disease, and assessing the prognosis in patients with oncological pathologies. In ophthalmology, AI potentially increases the patient's access to screening/clinical diagnosis and decreases healthcare costs, mainly when there is a high risk of disease or communities face financial shortages. AI/DL (deep learning) algorithms using both OCT and FO images will change image analysis techniques and methodologies. Optimizing these (combined) technologies will accelerate progress in this area.

Classification of dry and wet macular degeneration based on the ConvNeXT model

Purpose

To assess the value of an automated classification model for dry and wet macular degeneration based on the ConvNeXT model.

Methods

A total of 672 fundus images of normal, dry, and wet macular degeneration were collected from the Affiliated Eye Hospital of Nanjing Medical University and the fundus images of dry macular degeneration were expanded. The ConvNeXT three-category model was trained on the original and expanded datasets, and compared to the results of the VGG16, ResNet18, ResNet50, EfficientNetB7, and RegNet three-category models. A total of 289 fundus images were used to test the models, and the classification results of the models on different datasets were compared. The main evaluation indicators were sensitivity, specificity, F1-score, area under the curve (AUC), accuracy, and kappa.

Results

Using 289 fundus images, three-category models trained on the original and expanded datasets were assessed. The ConvNeXT model trained on the expanded dataset was the most effective, with a diagnostic accuracy of 96.89%, kappa value of 94.99%, and high diagnostic consistency. The sensitivity, specificity, F1-score, and AUC values for normal fundus images were 100.00, 99.41, 99.59, and 99.80%, respectively. The sensitivity, specificity, F1-score, and AUC values for dry macular degeneration diagnosis were 87.50, 98.76, 90.32, and 97.10%, respectively. The sensitivity, specificity, F1-score, and AUC values for wet macular degeneration diagnosis were 97.52, 97.02, 96.72, and 99.10%, respectively.

Conclusion

The ConvNeXT-based category model for dry and wet macular degeneration automatically identified dry and wet macular degeneration, aiding rapid, and accurate clinical diagnosis.

A retrospective analysis on comparison of optical coherence tomography manifestations among AMD, CEC, PM and ICN and its relationship with vision

Background

Both macular choroidal neovascularization (MCN) and visual changes can occur in age-related macular degeneration (AMD), central exudative chorioretinopathy (CEC), pathological myopia (PM) and idiopathic choroidal neovascularization (ICN), but whether the optical coherence tomography (OCT) manifestations of the four diseases are different and their relationships with vision are not clear. This study clarifies this problem and can guide clinicians to prevent vision changes of patients according to OCT performance.

Methods

76 patients with MCN, included 25 AMD, 21 CEC, 18 PM and 12 ICN [refer to Chinese Ophthalmology (3rd Edition)], detected by OCT instrument, were enrolled in this study from June 2020 to June 2022. The OCT manifestations and indexes were observed. A comprehensive refractometer was used for detection of best corrected visual acuity (BCVA) and axial length (AL). Pearson chi squared and 1 way analysis of variance were used for enumeration data and continuous data test, and Pearson correlation coefficient was used for relationship analysis.

Results

(I) Macular edema proportions in the MCN eyes among AMD, CEC, PM and ICN groups were 96.00% and 94.12%, 14.29% and 14.29%, 44.44% and 32.00%, 33.33% and 28.57%, with statistical differences (both P<0.001). (II) Patients with macular edema had a significantly higher loose and thickened tissue reflex of the neuroepithelial layer (100.00% vs. 4.26%) and limited non-reflective dark area (100.00% vs. 4.26%) (both P<0.001). (III) PM had the lowest width, height and central fovea thickness (CFT) [(1,403.43±114.41), (210.74±21.22) and (250.70±41.36) μm], and the highest distance to the fovea, BCVA and AL [(234.44±288.69) μm, (0.30±0.08) Log minimal angle of resolution (MAR), (28.48±5.72) mm] (all P<0.001). (IV) The width and height of patients with macular edema were lower than those of patients without macular edema [(1,738.43±348.71) vs. (2,493.95±771.53) μm, P<0.001; (305.71±81.22) vs. (367.29±107.91) μm, P=0.002] (P<0.05). (V) The width and height, CFT were negatively correlated to BCVA (r=-0.635, -0.712, -0.724, all P<0.001), and height, CFT were negatively correlated to AL (r=-0.244, -0.275, P=0.018, 0.007). The distance to the fovea was positively correlated to BCVA and AL (r=0.241, P=0.019; r=0.267, P=0.007).

Conclusions

Most of the OCT indexes were related to the BCVA and AL in MCN patients, and MCN patients with OCT changes should be reminded to protect their vision.

Artificial intelligence and deep learning in ophthalmology: Current status and future perspectives

Background

The ophthalmology field was among the first to adopt artificial intelligence (AI) in medicine. The availability of digitized ocular images and substantial data have made deep learning (DL) a popular topic.

Main text

At the moment, AI in ophthalmology is mostly used to improve disease diagnosis and assist decision-making aiming at ophthalmic diseases like diabetic retinopathy (DR), glaucoma, age-related macular degeneration (AMD), cataract and other anterior segment diseases. However, most of the AI systems developed to date are still in the experimental stages, with only a few having achieved clinical applications. There are a number of reasons for this phenomenon, including security, privacy, poor pervasiveness, trust and explainability concerns.

Conclusions

This review summarizes AI applications in ophthalmology, highlighting significant clinical considerations for adopting AI techniques and discussing the potential challenges and future directions.

Deep learning: applications in retinal and optic nerve diseases

Deep learning (DL) represents a paradigm-shifting, burgeoning field of research with emerging clinical applications in optometry. Unlike traditional programming, which relies on human-set specific rules, DL works by exposing the algorithm to a large amount of annotated data and allowing the software to develop its own set of rules (i.e. learn) by adjusting the parameters inside the model (network) during a training process in order to complete the task on its own. One major limitation of traditional programming is that, with complex tasks, it may require an extensive set of rules to accurately complete the assignment. Additionally, traditional programming can be susceptible to human bias from programmer experience. With the dramatic increase in the amount and the complexity of clinical data, DL has been utilised to automate data analysis and thus to assist clinicians in patient management. This review will present the latest advances in DL, for managing posterior eye diseases as well as DL-based solutions for patients with vision loss.

Three-Dimensional Volume Calculation of Intrachoroidal Cavitation Using Deep-Learning-Based Noise Reduction of Optical Coherence Tomography

Purpose

Intrachoroidal cavitations (ICCs) are peripapillary pathological lesions generally associated with high myopia that can cause visual field (VF) defects. The current study aimed to evaluate a three-dimensional (3D) volume parameter of ICCs segmented from volumetric swept-source optical coherence tomography (SS-OCT) images processed using deep learning (DL)-based noise reduction and to investigate its correlation with VF sensitivity.

Methods

Thirteen eyes of 12 consecutive patients with peripapillary ICCs were enrolled. DL-based denoising and further analyses were applied to parapapillary 6 × 6-mm volumetric SS-OCT scans. Then, 3D ICC volume and two-dimensional depth and length measurements of the ICCs were calculated. The correlations between ICC parameters and VF sensitivity were investigated.

Results

The ICCs were located in the inferior hemiretina in all eyes. ICC volume (P = 0.02; regression coefficient [RC], −0.007) and ICC length (P = 0.04; RC, −4.51) were negatively correlated with the VF mean deviation, whereas ICC depth (P = 0.15) was not. All of the parameters, including ICC volume (P = 0.01; RC, −0.004), ICC depth (P = 0.02; RC, −0.008), and ICC length (P = 0.045; RC, −2.11), were negatively correlated with the superior mean total deviation.

Conclusions

We established the volume of ICCs as a new 3D parameter, and it reflected their influence on visual function. The automatic delineation and 3D rendering may lead to improved detection and pathological understanding of ICCs.

Translational Relevance

This study demonstrated the correlation between the 3D volume of ICCs and VF sensitivity.

Association Between Visual Acuity and Fluid Compartments with Treat-and-Extend Intravitreal Aflibercept in Neovascular Age-Related Macular Degeneration: An ARIES Post Hoc Analysis

INTRODUCTION

Recently, there has been growing interest in exploring the relationship between visual acuity and fluid localization in different retinal compartments. This post hoc analysis of the ARIES study explores the relationship between the presence of intraretinal fluid (IRF) and subretinal fluid (SRF), both at baseline and throughout treatment, and best-corrected visual acuity (BCVA) in patients with neovascular age-related macular degeneration (nAMD) treated with intravitreal aflibercept (IVT-AFL) in a treat-and-extend regimen.

METHODS

ARIES (NCT02581891) was a multicenter, randomized, phase 3b/4 study comparing the efficacy of two IVT-AFL treat-and-extend regimens over 2 years in patients with treatment-naïve nAMD. This post hoc analysis explores the relationship between the presence of SRF/IRF and absolute BCVA (letter score) at baseline and fixed visits.

RESULTS

In 210 patients (treat-and-extend treatment arms combined), SRF presence at baseline was associated at every time point with a numerically higher mean BCVA than if absent, with 10 more letters at week 104. IRF presence at baseline was associated at all but one time point with a numerically lower mean BCVA than if absent (week 104, 8-letter difference). Baseline SRF+IRF was associated with lower BCVA (week 104, 7-letter difference) than if only SRF was present, but higher BCVA (week 104, 8-letter difference) than if only IRF was present. Absence of SRF+IRF was not associated with better BCVA at any time point during the study.

CONCLUSION

In ARIES, in patients with nAMD treated with IVT-AFL, the presence of SRF was associated with better visual acuity, whereas IRF was associated with poorer visual acuity. The findings of this post hoc analysis suggest that differentiating IRF from SRF may offer better prognostic value in guiding treatment-extension decisions than the use of combined or "any" IRF and SRF. Prospective trials are needed to validate these results and determine their clinical relevance. TRIAL REGISTRATION NUMBER (CLINICALTRIALS.GOV): NCT02581891. Association between Visual Acuity and Fluid Compartments with Treat-and-Extend Intravitreal Aflibercept in Neovascular Age-Related Macular Degeneration: An ARIES Post Hoc Analysis: A Video Abstract (MP4 308264 KB).

Genetic Association Analysis of Anti-VEGF Treatment Response in Neovascular Age-Related Macular Degeneration

Anti-VEGF treatment for neovascular age-related macular degeneration (nAMD) has been FDA-approved in 2004, and since then has helped tens of thousands of patients worldwide to preserve vision. Still, treatment responses vary widely, emphasizing the need for genetic biomarkers to robustly separate responders from non-responders. Here, we report the findings of an observational study compromising 179 treatment-naïve nAMD patients and their reaction to treatment after three monthly doses of anti-VEGF antibodies. We show that established criteria of treatment response such as visual acuity and central retinal thickness successfully divides our cohort into 128 responders and 51 non-responders. Nevertheless, retinal thickness around the fovea revealed significant reaction to treatment even in the formally categorized non-responders. To elucidate genetic effects underlying our criteria, we conducted an undirected genome-wide association study followed by a directed replication study of 30 previously reported genetic variants. Remarkably, both approaches failed to result in significant findings, suggesting study-specific effects were confounding the present and previous discovery studies. Of note, all studies so far are greatly underpowered, hampering interpretation of genetic findings. In consequence, we highlight the need for an extensive phenotyping study with sample sizes exceeding at least 15,000 to reliably assess anti-VEGF treatment responses in nAMD.

From Data to Deployment: The Collaborative Community on Ophthalmic Imaging Roadmap for Artificial Intelligence in Age-Related Macular Degeneration

OBJECTIVE

Health care systems worldwide are challenged to provide adequate care for the 200 million individuals with age-related macular degeneration (AMD). Artificial intelligence (AI) has the potential to make a significant, positive impact on the diagnosis and management of patients with AMD; however, the development of effective AI devices for clinical care faces numerous considerations and challenges, a fact evidenced by a current absence of Food and Drug Administration (FDA)-approved AI devices for AMD.

PURPOSE

To delineate the state of AI for AMD, including current data, standards, achievements, and challenges.

METHODS

Members of the Collaborative Community on Ophthalmic Imaging Working Group for AI in AMD attended an inaugural meeting on September 7, 2020, to discuss the topic. Subsequently, they undertook a comprehensive review of the medical literature relevant to the topic. Members engaged in meetings and discussion through December 2021 to synthesize the information and arrive at a consensus.

RESULTS

Existing infrastructure for robust AI development for AMD includes several large, labeled data sets of color fundus photography and OCT images; however, image data often do not contain the metadata necessary for the development of reliable, valid, and generalizable models. Data sharing for AMD model development is made difficult by restrictions on data privacy and security, although potential solutions are under investigation. Computing resources may be adequate for current applications, but knowledge of machine learning development may be scarce in many clinical ophthalmology settings. Despite these challenges, researchers have produced promising AI models for AMD for screening, diagnosis, prediction, and monitoring. Future goals include defining benchmarks to facilitate regulatory authorization and subsequent clinical setting generalization.

CONCLUSIONS

Delivering an FDA-authorized, AI-based device for clinical care in AMD involves numerous considerations, including the identification of an appropriate clinical application; acquisition and development of a large, high-quality data set; development of the AI architecture; training and validation of the model; and functional interactions between the model output and clinical end user. The research efforts undertaken to date represent starting points for the medical devices that eventually will benefit providers, health care systems, and patients.

Artificial Intelligence and Imaging Processing in Optical Coherence Tomography and Digital Images in Uveitis

INTRODUCTION

Computer vision, understood as the area of science that trains computers to interpret digital images through both artificial intelligence (AI) and classical algorithms, has significantly advanced the analysis and interpretation of optical coherence tomography (OCT) in retina research. The aim of this review is to summarise the recent advances of computer vision in imaging processing in uveitis, with a particular focus in optical coherence tomography images.

MATERIAL AND METHODS

Literature review.

RESULTS

The development of computer vision to assist uveitis diagnosis and prognosis is still undergoing, but important efforts have been made in the field.

CONCLUSION

The automatising of image processing in uveitis could be fundamental to establish objective and standardised outcomes for future clinical trials. In addition, it could help to better understand the disease and its progression.

The Role of Artificial Intelligence in the Diagnosis and Management of Glaucoma

Glaucomatous optic neuropathy is the leading cause of irreversible blindness worldwide. Diagnosis and monitoring of disease involves integrating information from the clinical examination with subjective data from visual field testing and objective biometric data that includes pachymetry, corneal hysteresis, and optic nerve and retinal imaging. This intricate process is further complicated by the lack of clear definitions for the presence and progression of glaucomatous optic neuropathy, which makes it vulnerable to clinician interpretation error. Artificial intelligence (AI) and AI-enabled workflows have been proposed as a plausible solution. Applications derived from this field of computer science can improve the quality and robustness of insights obtained from clinical data that can enhance the clinician's approach to patient care. This review clarifies key terms and concepts used in AI literature, discusses the current advances of AI in glaucoma, elucidates the clinical advantages and challenges to implementing this technology, and highlights potential future applications.

Evaluating an automated machine learning model that predicts visual acuity outcomes in patients with neovascular age-related macular degeneration

Purpose

Neovascular age-related macular degeneration (nAMD) is a major global cause of blindness. Whilst anti-vascular endothelial growth factor (anti-VEGF) treatment is effective, response varies considerably between individuals. Thus, patients face substantial uncertainty regarding their future ability to perform daily tasks. In this study, we evaluate the performance of an automated machine learning (AutoML) model which predicts visual acuity (VA) outcomes in patients receiving treatment for nAMD, in comparison to a manually coded model built using the same dataset. Furthermore, we evaluate model performance across ethnic groups and analyse how the models reach their predictions.

Methods

Binary classification models were trained to predict whether patients’ VA would be ‘Above’ or ‘Below’ a score of 70 one year after initiating treatment, measured using the Early Treatment Diabetic Retinopathy Study (ETDRS) chart. The AutoML model was built using the Google Cloud Platform, whilst the bespoke model was trained using an XGBoost framework. Models were compared and analysed using the What-if Tool (WIT), a novel model-agnostic interpretability tool.

Results

Our study included 1631 eyes from patients attending Moorfields Eye Hospital. The AutoML model (area under the curve [AUC], 0.849) achieved a highly similar performance to the XGBoost model (AUC, 0.847). Using the WIT, we found that the models over-predicted negative outcomes in Asian patients and performed worse in those with an ethnic category of Other. Baseline VA, age and ethnicity were the most important determinants of model predictions. Partial dependence plot analysis revealed a sigmoidal relationship between baseline VA and the probability of an outcome of ‘Above’.

Conclusion

We have described and validated an AutoML-WIT pipeline which enables clinicians with minimal coding skills to match the performance of a state-of-the-art algorithm and obtain explainable predictions.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00417-021-05544-y.

Optical Coherence Tomography Findings of Underlying Choroidal Neovascularization in Punctate Inner Choroidopathy

Purpose: To analyze findings on optical coherence tomography (OCT) suggestive of choroidal neovascularization (CNV) in lesions of punctate inner choroidopathy (PIC).

Methods: In this multi-center retrospective study, clinical data of patients with PIC were retrospectively analyzed. Quantitative data (height, width, and volume of PIC lesions), and qualitative data (disruption of ellipsoid zone (EZ)/Bruch's membrane (BM), outer retinal fuzziness, and choroidal back-shadowing) were compared between CNV+ and CNV– groups using Mann–Whitney U-test and Fischer's exact test.

Results: In total, 35 eyes (29 patients; 21 women; mean age: 33.3 ± 6.5 years) were selected for analysis. Of the 35 PIC lesions studied, 17 had underlying CNV. Lesions with CNV+ had larger height, width, and volume (p < 0.001) and several distinctive features, such as disruption of EZ and BM, outer retinal fuzziness, and hypo-reflective back-shadowing (p < 0.001) compared with CNV—lesions.

Conclusions: Quantitative and qualitative OCT analysis can aid in the prediction of an underlying CNV in the eyes with PIC.

Quantitative assessment of retinal fluid in neovascular age-related macular degeneration under anti-VEGF therapy

The retinal world has been revolutionized by optical coherence tomography (OCT) and anti-vascular endothelial growth factor (VEGF) therapy. The numbers of intravitreal injections are on a constant rise and management in neovascular age-related macular degeneration (nAMD) is mainly driven by the qualitative assessment of macular fluid as detected on OCT scans. The presence of macular fluid, particularly subretinal fluid (SRF) and intraretinal fluid (IRF), has been used to trigger re-treatments in clinical trials and the real world. However, large discrepancies can be found between the evaluations of different readers or experts and especially small amounts of macular fluid might be missed during this process. Pixel-wise detection of macular fluid uses an entire OCT volume to calculate exact volumes of retinal fluid. While manual annotations of such pixel-wise fluid detection are unfeasible in a clinical setting, artificial intelligence (AI) is able to overcome this hurdle by providing real-time results of macular fluid in different retinal compartments. Quantitative fluid assessments have been used for various post hoc analyses of randomized controlled trials, providing novel insights into anti-VEGF treatment regimens. Nonetheless, the application of AI-algorithms in a prospective patient care setting is still limited. In this review, we discuss the use of quantitative fluid assessment in nAMD during anti-VEGF therapy and provide an outlook to novel forms of patient care with the support of AI quantifications.

Significance of Hyperreflective Foci as an Optical Coherence Tomography Biomarker in Retinal Diseases: Characterization and Clinical Implications

Hyperreflective foci (HRF) is a term coined to depict hyperreflective dots or roundish lesions within retinal layers visualized through optical coherence tomography (OCT). Histopathological correlates of HRF are not univocal, spacing from migrating retinal pigment epithelium cells, lipid-laden macrophages, microglial cells, and extravasated proteinaceous or lipid material. Despite this, HRF can be considered OCT biomarkers for disease progression, treatment response, and prognosis in several retinal diseases, including diabetic macular edema, age-related macular degeneration (AMD), retinal vascular occlusions, and inherited retinal dystrophies. The structural features and topographic location of HRF guide the interpretation of their significance in different pathological conditions. The presence of HRF less than 30 μm with reflectivity comparable to the retinal nerve fiber layer in the absence of posterior shadowing in diabetic macular edema indicates an inflammatory phenotype with a better response to steroidal treatment. In AMD, HRF overlying drusen are associated with the development of macular neovascularization, while parafoveal drusen and HRF predispose to macular atrophy. Thus, HRF can be considered a key biomarker in several common retinal diseases. Their recognition and critical interpretation via multimodal imaging are vital to support clinical strategies and management.