Prediction of neovascular age-related macular degeneration recurrence using optical coherence tomography images with a deep neural network.

Neovascular age-related macular degeneration (nAMD) can result in blindness if left untreated, and patients often require repeated anti-vascular endothelial growth factor injections. Although, the treat-and-extend method is becoming popular to reduce vision loss attributed to recurrence, it may pose a risk of overtreatment. This study aimed to develop a deep learning model based on DenseNet201 to predict nAMD recurrence within 3 months after confirming dry-up 1 month following three loading injections in treatment-naïve patients. A dataset of 1076 spectral domain optical coherence tomography (OCT) images from 269 patients diagnosed with nAMD was used. The performance of the model was compared with that of 6 ophthalmologists, using 100 randomly selected samples. The DenseNet201-based model achieved 53.0% accuracy in predicting nAMD recurrence using a single pre-injection image and 60.2% accuracy after viewing all the images immediately after the 1st, 2nd, and 3rd injections. The model outperformed experienced ophthalmologists, with an average accuracy of 52.17% using a single pre-injection image and 53.3% after examining four images before and after three loading injections. In conclusion, the artificial intelligence model demonstrated a promising ability to predict nAMD recurrence using OCT images and outperformed experienced ophthalmologists. These findings suggest that deep learning models can assist in nAMD recurrence prediction, thus improving patient outcomes and optimizing treatment strategies.

Texture-Based Radiomic SD-OCT Features Associated With Response to Anti-VEGF Therapy in a Phase III Neovascular AMD Clinical Trial.

Purpose: The goal of this study was to evaluate the role of texture-based baseline radiomic features (Fr) and dynamic radiomics alterations (delta, FΔr) within multiple targeted compartments on optical coherence tomography (OCT) scans to predict response to anti-vascular endothelial growth factor (VEGF) therapy in neovascular age-related macular degeneration (nAMD). Methods: HAWK is a phase 3 clinical trial data set of active nAMD patients (N = 1082) comparing brolucizumab and aflibercept. This analysis included patients receiving 6 mg brolucizumab or 2 mg aflibercept and categorized as complete responders (n = 280) and incomplete responders (n = 239) based on whether or not the eyes achieved/maintained fluid resolution on OCT. A total of 481 Fr were extracted from each of the fluid, subretinal hyperreflective material (SHRM), retinal tissue, and sub-retinal pigment epithelium (RPE) compartments. Most discriminating eight baseline features, selected by the minimum redundancy, maximum relevance feature selection, were evaluated using a quadratic discriminant analysis (QDA) classifier on the training set (Str, n = 363) to differentiate between the two patient groups. Classifier performance was subsequently validated on independent test set (St, n = 156). Results: In total, 519 participants were included in this analysis from the HAWK phase 3 study. There were 280 complete responders and 219 incomplete responders. Compartmental analysis of radiomics featured identified the sub-RPE and SHRM compartments as the most distinguishing between the two response groups. The QDA classifier yielded areas under the curve of 0.78, 0.79, and 0.84, respectively, using Fr, FΔr, and combined Fr, FΔr, and Fc on St. Conclusions: Utilizing compartmental static and dynamic radiomics features, unique differences were identified between eyes that respond differently to anti-VEGF therapy in a large phase 3 trial that may provide important predictive value. Translational Relevance: Imaging biomarkers, such as radiomics features identified in this analysis, for predicting treatment response are needed to enhanced precision medicine in the management of nAMD.

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.

Deep learning to detect macular atrophy in wet age-related macular degeneration using optical coherence tomography.

Here, we have developed a deep learning method to fully automatically detect and quantify six main clinically relevant atrophic features associated with macular atrophy (MA) using optical coherence tomography (OCT) analysis of patients with wet age-related macular degeneration (AMD). The development of MA in patients with AMD results in irreversible blindness, and there is currently no effective method of early diagnosis of this condition, despite the recent development of unique treatments. Using OCT dataset of a total of 2211 B-scans from 45 volumetric scans of 8 patients, a convolutional neural network using one-against-all strategy was trained to present all six atrophic features followed by a validation to evaluate the performance of the models. The model predictive performance has achieved a mean dice similarity coefficient score of 0.706 ± 0.039, a mean Precision score of 0.834 ± 0.048, and a mean Sensitivity score of 0.615 ± 0.051. These results show the unique potential of using artificially intelligence-aided methods for early detection and identification of the progression of MA in wet AMD, which can further support and assist clinical decisions.

Evaluación de signos tomográficos no exudativos en casos de degeneración macular asociada a la edad de tipo exudativo / Evaluation of non-exudative tomographic signs in cases of exudative age-related macular degeneration

Objetivo Analizar la prevalencia de signos tomográficos no exudativos (signo de cebolla, seudoedema, tubulación de la retina externa, seudoquistes, hendiduras subretinianas y atrofia macular) en pacientes con degeneración macular asociada a la edad neovascular. Material y métodos Un total de 174 ojos de pacientes con degeneración macular asociada a la edad neovascular que no habían recibido tratamiento previo fueron incluidos en el estudio. Se valoró la agudeza visual, la actividad de la neovascularización y la aparición o no de los distintos signos objeto de estudio en los tiempos 0 (visita inicial), 4 meses, un año, año y medio y a los 2 y 3 años de seguimiento. Se evaluaron también: la edad, el sexo, el ojo afecto y el tipo de neovascularización (1, 2, 3, polipoidea o mixta). Los análisis se han realizado mediante el software estadístico R (versión 3.3.2) y el paquete glmmADMB (versión 0.8.3.3). Resultados La presencia de seudoquistes y tubulación de la retina externa va en aumento a lo largo del seguimiento. El signo de cebolla comienza con una frecuencia ascendente hasta los 12 meses, posteriormente desciende a los 18 meses y vuelve a incrementarse a los 24 meses. En cuanto al seudoedema, mantiene un incremento hasta los 18 meses para finalmente descender. Las hendiduras subretinianas son el signo más raro, presentándose en el 1,1% en la primera visita. Finalmente, la atrofia macular, presente en el 12,6% de los ojos inicialmente, se encuentra en el 25% a los 2 años. Conclusión Los seudoquistes, la tubulación de la retina externa y la atrofia macular fueron los signos más prevalentes, mientras que las hendiduras subretinianas fueron los más infrecuentes (AU)

Objective To analyze the prevalence of non-exudative tomographic signs (onion sign, pseudoswelling, external retinal tubulation, pseudocysts, subretinal clefts and macular atrophy) in patients with neovascular age-related macular degeneration. Material and methods A total of 174 eyes of patients with neovascular age-related macular degeneration who had not received previous treatment were included in the study. Visual acuity, neovascularization activity, and the appearance or not of the different signs under study were assessed at times 0 (initial visit), 4 months, one year, year and a half, and at 2 and 3 years of follow-up. The following were also evaluated: age, sex, affected eye and type of neovascularization (1, 2, 3, polypoid or mixed). The analysis were performed using the statistical software R (version 3.3.2) and the glmmADMB package (version 0.8.3.3). Results The presence of pseudocysts and external retinal tubulation increases throughout the follow-up. The onion sign begins with an ascending frequency up to 12 months, then decreases at 18 months and increases again at 24 months. Regarding pseudowelling, it maintains an increase until 18 months to finally decrease. Subretinal clefts is the rarest sign, presenting in 1.1% on the first visit. Finally, macular atrophy, present in 12.6% of the eyes initially, is found in 25% after 2 years. Conclusion Pseudocysts, external retinal tubulation and macular atrophy were the most prevalent signs, while subretinal clefts were the most infrequent (AU)

Efficacy of Aflibercept as initial treatment for neovascular age-related macular degeneration in an Iraqi patient sample.

Age-related macular degeneration (AMD) is a progressive degenerative eye disorder that primarily affects individuals over 50. It causes gradual loss of central vision and can lead to irreversible severe visual loss if left untreated. AMD is a leading cause of blindness in the developed world. This study aimed to investigate the effects of a loading dosage of intravitreal Aflibercept on functional and morphological responses in neovascular AMD, considering demographic characteristics and the link between AMD-related retinal symptoms at presentations. A prospective interventional study was conducted from November 2021 to September 2022 on a sample of Iraqi patients with neovascular AMD who had active choroidal neovascularization (CNV) lesions confirmed by OCT-A and received intravitreal Aflibercept 2mg injection as initial therapy (3 loading doses). Best-corrected visual acuity (BCVA) was used to measure functional responses, and central macular thickness (CMT) and maximum area of the retinal thickness (MART) (by SD-OCT) were used to measure morphological responses. The study included 48 patients (57 eyes) with active neovascular AMD. The mean difference of BCVA in log MAR (0.2 ± 0.7) significantly improved from 1.3±0.7 at baseline to 1.1±0.8 after loading Aflibercept (P=0.034). The mean difference in CMT 113.6 ± 125.9 was statistically significant (P<0.0001). Also, the mean change in MART significantly decreased from 444.2 ± 127.1 µm at baseline to 348.7±74.5 µm (p < 0.0001) after loading Aflibercept. This study demonstrated that Aflibercept is a functionally and anatomically successful treatment for neovascular AMD.

Prediction of treatment outcome in neovascular age-related macular degeneration using a novel convolutional neural network.

While prognosis and risk of progression are crucial in developing precise therapeutic strategy in neovascular age-related macular degeneration (nAMD), limited predictive tools are available. We proposed a novel deep convolutional neural network that enables feature extraction through image and non-image data integration to seize imperative information and achieve highly accurate outcome prediction. The Heterogeneous Data Fusion Net (HDF-Net) was designed to predict visual acuity (VA) outcome (improvement ≥ 2 line or not) at 12th months after anti-VEGF treatment. A set of pre-treatment optical coherence tomography (OCT) image and non-image demographic features were employed as input data and the corresponding 12th-month post-treatment VA as the target data to train, validate, and test the HDF-Net. This newly designed HDF-Net demonstrated an AUC of 0.989 (95% CI 0.970-0.999), accuracy of 0.936 [95% confidence interval (CI) 0.889-0.964], sensitivity of 0.933 (95% CI 0.841-0.974), and specificity of 0.938 (95% CI 0.877-0.969). By simulating the clinical decision process with mixed pre-treatment information from raw OCT images and numeric data, HDF-Net demonstrated promising performance in predicting individualized treatment outcome. The results highlight the potential of deep learning to simultaneously process a broad range of clinical data to weigh and leverage the complete information of the patient. This novel approach is an important step toward real-world personalized therapeutic strategy for typical nAMD.

EFFECT OF RETINAL THICKNESS VARIABILITY ON VISUAL OUTCOMES AND FLUID PERSISTENCE IN NEOVASCULAR AGE-RELATED MACULAR DEGENERATION: A Post Hoc Analysis of the HAWK and HARRIER Studies.

PURPOSE: To determine the association between central subfield thickness (CST) variability and visual outcomes in eyes with neovascular age-related macular degeneration treated with anti-vascular endothelial growth factor therapies. METHODS: In this post hoc, treatment-agnostic analysis, patients (N = 1,752) were grouped into quartiles of increasing CST variation. The association between CST variability and best-corrected visual acuity was measured from baseline, or from the end of the loading phase, until the end of the study using a multilevel modeling for repeated-measures model. The association between CST variability and the presence of retinal fluid was also assessed. RESULTS: Increased CST variability was associated with worse best-corrected visual acuity outcomes at the end of study, with a least-square mean difference in best-corrected visual acuity of 8.9 Early Treatment Diabetic Retinopathy Study letters between the quartiles with the lowest and highest CST variability at the final visit. Increased variability was also associated with a higher mean fraction of visits with the presence of fluid. CONCLUSION: More stable CST was associated with better visual outcomes at the end of treatment suggesting that CST variability may provide a more reliable prognostic marker of visual outcomes than the presence of fluid alone, with the potential to enhance the clinical care of neovascular age-related macular degeneration patients.

DEVELOPMENT AND VALIDATION OF AN EXPLAINABLE ARTIFICIAL INTELLIGENCE FRAMEWORK FOR MACULAR DISEASE DIAGNOSIS BASED ON OPTICAL COHERENCE TOMOGRAPHY IMAGES.

PURPOSE: To develop and validate an artificial intelligence framework for identifying multiple retinal lesions at image level and performing an explainable macular disease diagnosis at eye level in optical coherence tomography images. METHODS: A total of 26,815 optical coherence tomography images were collected from 865 eyes, and 9 retinal lesions and 3 macular diseases were labeled by ophthalmologists, including diabetic macular edema and dry/wet age-related macular degeneration. We applied deep learning to classify retinal lesions at image level and random forests to achieve an explainable disease diagnosis at eye level. The performance of the integrated two-stage framework was evaluated and compared with human experts. RESULTS: On testing data set of 2,480 optical coherence tomography images from 80 eyes, the deep learning model achieved an average area under curve of 0.978 (95% confidence interval, 0.971-0.983) for lesion classification. In addition, random forests performed accurate disease diagnosis with a 0% error rate, which achieved the same accuracy as one of the human experts and was better than the other three experts. It also revealed that the detection of specific lesions in the center of macular region had more contribution to macular disease diagnosis. CONCLUSION: The integrated method achieved high accuracy and interpretability in retinal lesion classification and macular disease diagnosis in optical coherence tomography images and could have the potential to facilitate the clinical diagnosis.

CHANGES IN SYSTEMIC LEVELS OF VASCULAR ENDOTHELIAL GROWTH FACTOR AFTER INTRAVITREAL INJECTION OF AFLIBERCEPT OR BROLUCIZUMAB FOR NEOVASCULAR AGE-RELATED MACULAR DEGENERATION.

PURPOSE: To analyze and compare the effects of intravitreal brolucizumab versus aflibercept on systemic vascular endothelial growth factor (VEGF)-A levels in patients with neovascular age-related macular degeneration. METHODS: In this prospective interventional case series study, brolucizumab (6.0 mg/50 µL) or aflibercept (2.0 mg/50 µL) was injected intravitreally in 30 patients each. Blood samples were drawn at baseline and 7 days and 28 days after the first injection. Systemic VEGF-A levels were measured using enzyme-linked immunosorbent assay. Thirty healthy individuals served as controls. RESULTS: The median baseline systemic VEGF-A levels in the brolucizumab, aflibercept, and control groups were 10.8 (8.0-13.2), 12.0 (8.0-18.5), and 10.0 (8.0-15.1) pg/mL, respectively (P = 0.315). In the brolucizumab group, VEGF-A levels significantly decreased to 8.0 (8.0-11.5) pg/mL on Day 7 (P = 0.0254) and to 8.0 (8.0-8.0) pg/mL on Day 28 (P < 0.001). In the aflibercept group, VEGF-A levels significantly decreased to 8.0 (8.0-8.0) pg/mL on Day 7 (P < 0.001) but returned to the baseline level, 12.5 (8.5-14.6) pg/mL, on Day 28 (P = 0.120). Vascular endothelial growth factor-A levels were significantly different between the treatment groups after 28 days (P < 0.001). CONCLUSION: Intravitreal brolucizumab resulted in a sustained reduction of systemic VEGF-A levels until 28 days posttreatment, which raises concerns regarding its safety and long-term effects.

Intraretinal, sub-retinal, and sub-retinal pigmented epithelium fluid in non-exudative age-related macular degeneration: follow-up with OCT imaging.

BACKGROUND/OBJECTIVES: To evaluate the presence and evolution of fluid in non-exudative age-related macular degeneration (AMD) through serial OCT. SUBJECTS/METHODS: A retrospective analysis of eyes with non-exudative AMD with a minimum of 4 year follow-up was done. Parameters including intraretinal fluid (IRF), subretinal fluid (SRF), and sub-retinal pigment epithelium (RPE) fluid (SRPEF); subfoveal choroidal thickness (SFCT) and type of drusen were evaluated using optical coherence tomography (OCT) scans at baseline and follow up visits. RESULTS: Seventy-two eyes (in 63 patients) were followed up for an average of 5.83 ± 2.17 years. A total of 26/72 (36%) and 29/65 (52%) of the non-exudative eyes had fluid during baseline and the last visit. Seven eyes (10%) out of 72 eyes converted into exudative AMD or neo-vascular AMD (nAMD) during the study period. SRPEF at baseline was most common fluid location for non-exudative eyes that eventually converted to nAMD. CONCLUSION: Non-exudative fluid including IRF, SRF, and SRPEF is seen in patients with non-exudative AMD with increasing incidence during long term follow-up.

Polypoidal Choroidal Vasculopathy Diagnosis and Neovascular Activity Evaluation Using Optical Coherence Tomography Angiography.

PURPOSE: To examine choroidal neovascularization (CNV) characteristics in patients with exudative age-related macular degeneration (AMD) and polypoidal choroidal vasculopathy (PCV), using swept-source optical coherence tomography angiography (SS-OCTA), and investigate agreement with OCT B-scan, fundus fluorescein angiography (FFA), and indocyanine green angiography (ICGA) by two different examiners. METHODS: This is a retrospective multicentric study that involved patients with a history of AMD and PCV. Examiner A, who had access to OCTA, B-scan OCT, FFA, and ICGA imaging, had to differentiate between AMD and PCV, study the activity of AMD using Coscas' criteria (active vs. quiescent), and categorize PCV subtypes, while examiner B had only access to OCTA. Then, the diagnostic concordance was assessed between both examiners. RESULTS: A total of 27 patients (11 females (40.7%) and 16 males (59.3%), P = 0.231) were included in the analysis. Among those, 13 patients presented with neovascular AMD and 14 patients with PCV. There were 92.3% of correct answers regarding appropriate diagnosis and lesion characterization among AMD patients, against 61.5% of correct answers among PCV patients. The overall interrater reliability agreement between examiners, using Cohen's kappa coefficient (κ) was 0.70 (0.5082-0.8916). Disagreement was found with one active AMD misdiagnosed as inactive AMD, three inactive PCV misdiagnosed as inactive AMD, and one inactive PCV misdiagnosed as active AMD. CONCLUSION: SS-OCTA alone remains limited in some specific phenotypes of PCV, which suggests the ongoing role of B-scan OCT associated with FFA and ICGA in the diagnosis of these conditions.

Artificial intelligence-based predictions in neovascular age-related macular degeneration.

PURPOSE OF REVIEW: Predicting treatment response and optimizing treatment regimen in patients with neovascular age-related macular degeneration (nAMD) remains challenging. Artificial intelligence-based tools have the potential to increase confidence in clinical development of new therapeutics, facilitate individual prognostic predictions, and ultimately inform treatment decisions in clinical practice. RECENT FINDINGS: To date, most advances in applying artificial intelligence to nAMD have focused on facilitating image analysis, particularly for automated segmentation, extraction, and quantification of imaging-based features from optical coherence tomography (OCT) images. No studies in our literature search evaluated whether artificial intelligence could predict the treatment regimen required for an optimal visual response for an individual patient. Challenges identified for developing artificial intelligence-based models for nAMD include the limited number of large datasets with high-quality OCT data, limiting the patient populations included in model development; lack of counterfactual data to inform how individual patients may have fared with an alternative treatment strategy; and absence of OCT data standards, impairing the development of models usable across devices. SUMMARY: Artificial intelligence has the potential to enable powerful prognostic tools for a complex nAMD treatment landscape; however, additional work remains before these tools are applicable to informing treatment decisions for nAMD in clinical practice.

Predominantly Persistent Subretinal Fluid in the Comparison of Age-Related Macular Degeneration Treatments Trials.

OBJECTIVE: To describe predominantly persistent subretinal fluid (SRF) in eyes receiving ranibizumab or bevacizumab for neovascular age-related macular degeneration and to compare visual acuity (VA) to eyes with nonpersistent SRF. DESIGN: Cohort within randomized clinical trial. PARTICIPANTS: Comparison of Age-related Macular Degeneration Treatments Trials patients assigned to pro re nata treatment. METHODS: Graders evaluated monthly OCT scans for SRF. Predominantly persistent SRF through week 12 was defined as SRF at baseline and weeks 4, 8, and 12. Predominantly persistent SRF through 1 or 2 years was defined as SRF in 80% or more of visits by years 1 or 2, respectively. Linear regression models including baseline predictors of VA and predominantly persistent intraretinal fluid (IRF) were used to evaluate mean differences in vision outcomes. PRIMARY OUTCOME MEASURES: Predominantly persistent SRF through year 1, adjusted VA score and VA change, and foveal SRF thickness. RESULTS: Among 406 eyes with baseline SRF, SRF persisted in 108 eyes (26.6%) through week 12, in 94 eyes (23.2%) through year 1, and in 77 eyes (19.0%) through year 2. Adjusted VA means at year 1 were similar between eyes with predominantly persistent versus non persistent SRF by week 12 (68.1 vs. 70.2 letters; P = 0.18), year 1 (67.6 vs. 70.2 letters; P = 0.11), and year 2 (71.4 vs. 70.9 letters; P = 0.78). Adjusted changes in mean VA at year 1 were similar between eyes with predominantly persistent versus nonpersistent SRF by week 12 (6.3 vs. 7.6 letters; P = 0.38), year 1 (5.5 vs. 7.8 letters; P = 0.14), and year 2 (8.1 vs. 7.7 letters; P = 0.78). Among eyes with predominantly persistent SRF through year 1, foveal SRF was absent in 46 eyes (48.9%), thickness was 1 to 200 µm in 48 eyes (50.0%) and more than 200 µm in 1 eye (1.1%) at year 1. CONCLUSIONS: Eyes with predominantly persistent and nonpersistent SRF through week 12, year 1, or year 2 showed similar VA outcomes after adjustment for baseline covariates and persistent IRF. At the foveal center, predominantly persistent SRF was most commonly absent or present in small quantities.

Differentiating Exudative Macular Degeneration and Polypoidal Choroidal Vasculopathy Using OCT B-Scan.

PURPOSE: Although polypoidal choroidal vasculopathy (PCV) is best diagnosed with indocyanine green angiography (ICGA), ICGA is often unavailable or not ordered. OCT is widely available, and OCT B-scan can visualize polypoidal lesions diagnostic of PCV as inverted U-shaped elevations of the retinal pigment epithelium (RPE) with heterogeneous reflectivity and sometimes ring-shaped lesions within the polypoidal lesion. This study aims to differentiate findings between eyes diagnosed with PCV or typical exudative age-related macular degeneration (AMD) using ICGA and then compares findings noted on the OCT B-scan line scan in each group. DESIGN: Retrospective, chart review. METHODS: Clinical features of eyes with PCV and typical exudative AMD were compared by using ICGA. Eyes with PCV were evaluated for inverted U-shaped polypoidal lesions, which are the main differentiating finding of PCV from typical exudative AMD. Data collected included presence of subretinal fluid (SRF), macular edema or intraretinal edema, subretinal hyperreflective material (SHRM), and retinal pigment epithelial detachment (RPED). These findings were evaluated in 2 parts: baseline and after 6 to 9 months of antiangiogenic therapy. Additionally, analysis was performed for the presence of polypoidal lesions before and after treatment. MAIN OUTCOME MEASURES: Presence of inverted U-shaped lesions on OCT B-scan following treatment. RESULTS: A total of 112 eyes of 106 patients were included. A total of 69 eyes were diagnosed with PCV, and 43 eyes were diagnosed with typical exudative AMD. Compared with AMD eyes, PCV eyes had an increased prevalence of SRF at baseline and after 6 to 9 months of treatment, but the prevalence of macular edema, SHRM, and RPED was similar at baseline and at 6 to 9 months after treatment. In PCV eyes, the presence of visible polypoidal lesions decreased from 56.5% to 24.6% after treatment. CONCLUSIONS: If PCV is suspected in an anti-vascular endothelial growth factor (VEGF)-resistant case of exudative AMD, in the absence of ICGA availability, it is important to look at the baseline OCT B-scan before therapy for evidence of polypoidal lesions. The characteristic inverted U-shaped elevation was present in more than half of PCV eyes on OCT B-scan at baseline but disappeared after antiangiogenic therapy in 56.4% of cases in which this was initially identified. Subretinal fluid was more prevalent in PCV eyes than non-PCV AMD eyes.

Non-ICGA treatment criteria for Suboptimal Anti-VEGF Response for Polypoidal Choroidal Vasculopathy: APOIS PCV Workgroup Report 2.

PURPOSE: To develop and validate OCT and color fundus photography (CFP) criteria in differentiating polypoidal choroidal vasculopathy (PCV) from typical neovascular age-related macular degeneration (nAMD) in eyes with suboptimal response to anti-vascular endothelial growth factor (VEGF) monotherapy and to determine whether OCT alone can be used to guide photodynamic therapy (PDT) treatment. DESIGN: Clinical study evaluating diagnostic accuracy. PARTICIPANTS: Patients with nAMD who received 3-month anti-VEGF monotherapy but had persistent activity defined as subretinal fluid or intraretinal fluid at month 3 assessments. METHODS: In phase 1, international retina experts evaluated OCT and CFP of eyes with nAMD to identify the presence or absence of features due to PCV. The performance of individual and combinations of these features were compared with ICGA. In phase 2, these criteria were applied to an independent image set to assess generalizability. In a separate exercise, retinal experts drew proposed PDT treatment spots using only OCT and near-infrared (NIR) images in eyes with PCV and persistent activity. The location and size of proposed spot were compared with ICGA to determine the extent of coverage of polypoidal lesions (PLs) and branching neovascular network (BNN). MAIN OUTCOME MEASURES: Sensitivity and specificity of CFP and OCT criteria to differentiate PCV from nAMD and accuracy of coverage of OCT-guided PDT compared with ICGA. RESULTS: In eyes with persistent activity, the combination of 3 non-ICGA-based criteria (sharp-peaked pigment epithelial detachment [PED], subretinal pigment epithelium [RPE] ring-like lesion, and orange nodule) to detect PCV showed good agreement compared with ICGA, with an area under the receiver operating characteristic curve of 0.85. Validation using both an independent image set and assessors achieved an accuracy of 0.77. Compared with ICGA, the OCT-guided PDT treatment spot covered 100% of PL and 90% of the BNN. CONCLUSIONS: In nAMD eyes with persistent activity, OCT and CFP can differentiate PCV from typical nAMD, which may allow the option of adjunct PDT treatment. Furthermore, OCT alone can be used to plan adjunct PDT treatment without the need for ICGA, with consistent and complete coverage of PL.

Quantification of Key Retinal Features in Early and Late Age-Related Macular Degeneration Using Deep Learning.

PURPOSE: We sought to develop and validate a deep learning model for segmentation of 13 features associated with neovascular and atrophic age-related macular degeneration (AMD). DESIGN: Development and validation of a deep-learning model for feature segmentation. METHODS: Data for model development were obtained from 307 optical coherence tomography volumes. Eight experienced graders manually delineated all abnormalities in 2712 B-scans. A deep neural network was trained with these data to perform voxel-level segmentation of the 13 most common abnormalities (features). For evaluation, 112 B-scans from 112 patients with a diagnosis of neovascular AMD were annotated by 4 independent observers. The main outcome measures were Dice score, intraclass correlation coefficient, and free-response receiver operating characteristic curve. RESULTS: On 11 of 13 features, the model obtained a mean Dice score of 0.63 ± 0.15, compared with 0.61 ± 0.17 for the observers. The mean intraclass correlation coefficient for the model was 0.66 ± 0.22, compared with 0.62 ± 0.21 for the observers. Two features were not evaluated quantitatively because of a lack of data. Free-response receiver operating characteristic analysis demonstrated that the model scored similar or higher sensitivity per false positives compared with the observers. CONCLUSIONS: The quality of the automatic segmentation matches that of experienced graders for most features, exceeding human performance for some features. The quantified parameters provided by the model can be used in the current clinical routine and open possibilities for further research into treatment response outside clinical trials.

Worth changing? Clinical effects of switching treatment in neovascular age-related macular degeneration from intravitreal ranibizumab and aflibercept to bevacizumab in a region in southern Sweden.

PURPOSE: To examine the clinical effects of switching intravitreal drug treatment from the approved vascular endothelial growth factor inhibitors, ranibizumab and aflibercept, to off label use of bevacizumab in patients with wet age-related macular degeneration. METHODS: This retrospective study scrutinized medical records of patients with wet age-related macular degeneration who switched therapy to bevacizumab due to a policy decision. Best corrected visual acuity, central retinal thickness, and number of injections before and 1 year after the switch was compared. The non-inferiority margin of best corrected visual acuity was five Early Treatment Diabetic Retinopathy Study letters. RESULTS: A switch from ranibizumab was evaluable in 93 eyes and from aflibercept in 19 eyes. Neither of the groups had a significant non-inferior visual acuity 16 month after the switch. Mean best corrected visual acuity in Early Treatment Diabetic Retinopathy Study letters was 63.8 (95% confidence interval: 61.3-66.4) before and 62.2 (95% confidence interval: 59.3-65.1) after in the ranibizumab group and 68.2 (95% confidence interval: 63.3-73.1) before and 67.7 (95% confidence interval: 62.8-72.6) after in the aflibercept group. Mean central retinal thickness in micrometers decreased from 254 (95% confidence interval: 247-261) to 250 (95% confidence interval: 225-275) in the ranibizumab group and from 265 (95% confidence interval: 255-276) to 262 (95% confidence interval: 251-273) in the aflibercept group. The treatment was changed again after the switch in 18% of the patients in the ranibizumab group and 19% in the aflibercept group and these subjects were excluded from the analyses. CONCLUSION: In patients with neovascular age-related macular degeneration, a switch from ranibizumab or aflibercept to bevacizumab seems possible without a significant decrease in visual acuity in most patients.

OCT-A characterisation of recurrent type 3 macular neovascularisation.

PURPOSE: To investigate optical coherence tomography angiography (OCT-A) findings in recurrent type 3 macular neovascularisation (MNV). METHODS: In this retrospective cohort study, consecutive patients with type 3 MNV secondary to age-related macular degeneration underwent OCT-A at three different time points: baseline, after anti-vascular endothelial growth factor treatment with complete resolution of the exudative signs (ie, non-exudative stage) and at the recurrence of exudation (ie, recurrence stage). Demographics and clinical findings were analysed, including OCT-A features of type 3 MNV recurrence. RESULTS: Twelve eyes (12 patients, mean age 78±7 years) were included. Using OCT-A, at baseline all type 3 MNVs showed the presence of detectable flow downgrowing from the deep vascular complex (DVC) to the retinal pigment epithelium (RPE)/sub-RPE space. 6/12 eyes (50%) showed anomalous flow under the RPE, while the other 6 eyes showed flow reaching the RPE without anomalous flow in the sub-RPE space. At the non-exudative stage (after treatment), BCVA and CMT significantly improved (p=0.004 and p=0.036), and flow inside the retinal lesions reduced; interestingly the connection to the RPE/sub-RPE space regressed. At the time of recurrence, all type 3 MNVs showed the presence of intra/sub-retinal exudation with restoration of the flow deepening from the DVC to the RPE/sub-RPE space. CONCLUSIONS: Detectable flow deepening from the DVC to the RPE/sub-RPE space using OCT-A is mandatory to have a new exudation secondary to recurrent type 3 MNV. Early detection of type 3 MNV recurrence by OCT-A characterisation may prompt retreatment and potentially prevent progression to late stages of the disease.

Detection of features associated with neovascular age-related macular degeneration in ethnically distinct data sets by an optical coherence tomography: trained deep learning algorithm.

BACKGROUND: The ability of deep learning (DL) algorithms to identify eyes with neovascular age-related macular degeneration (nAMD) from optical coherence tomography (OCT) scans has been previously established. We herewith evaluate the ability of a DL model, showing excellent performance on a Korean data set, to generalse onto an American data set despite ethnic differences. In addition, expert graders were surveyed to verify if the DL model was appropriately identifying lesions indicative of nAMD on the OCT scans. METHODS: Model development data set-12 247 OCT scans from South Korea; external validation data set-91 509 OCT scans from Washington, USA. In both data sets, normal eyes or eyes with nAMD were included. After internal testing, the algorithm was sent to the University of Washington, USA, for external validation. Area under the receiver operating characteristic curve (AUC) and precision-recall curve (AUPRC) were calculated. For model explanation, saliency maps were generated using Guided GradCAM. RESULTS: On external validation, AUC and AUPRC remained high at 0.952 (95% CI 0.942 to 0.962) and 0.891 (95% CI 0.875 to 0.908) at the individual level. Saliency maps showed that in normal OCT scans, the fovea was the main area of interest; in nAMD OCT scans, the appropriate pathological features were areas of model interest. Survey of 10 retina specialists confirmed this. CONCLUSION: Our DL algorithm exhibited high performance for nAMD identification in a Korean population, and generalised well to an ethnically distinct, American population. The model correctly focused on the differences within the macular area to extract features associated with nAMD.