The RAP study, report 4: morphological and topographical characteristics of multifocal macular neovascularization type 3.

PURPOSE: To report on the morphological characteristics and regional distribution of multifocal macular neovascularization type 3 (mMNV3). METHODS: Twenty-two consecutive eyes of 21 patients with mMNV3 were included using multimodal imaging. The count and stage of lesions of all MNV types and the existence of exudate and hemorrhage were determined. Also, we addressed the regional distribution of MNV3 lesions between the superior-inferior and the nasal-temporal halves of the macula, and the range of the distance of the lesions from the central fovea. Furthermore, we explored the number of feeding vessels including the cilioretinal artery. RESULTS: We found 51 lesions in 22 eyes of 21 patients. They were bifocal in 16 (73%) eyes, trifocal in 5 (23%), and quadrifocal in one (4%). No lesion of MNV1 or 2 was found. Fifteen (68%), 2 (9%), and 16 (73%) eyes were associated with retinal hard exudate, subretinal pigment epithelium exudate, and intraretinal hemorrhage, respectively. Thirty (59%) lesions were located in the temporal half of the macula, whereas 21 (41%) were located nasally (p = 0.07). One (2%) lesion was closer than 500 µm, 49 (96%) between 500 and 1500 µm, and one (2%) between 1500 and 3000 µm. The lesions were supplied by one arteriole in one (4%) eye, two arterioles in 16 (73%) eyes, and 3 arterioles in 5 (23%) eyes. The CRA contributed as a feeding vessel in 5 (23%) eyes. CONCLUSION: The multifocal variant of MNV3 has specific morphological and topographical characteristics. Multimodal imaging allows the understanding of the pathomorphological condition in more detail.

THE RAP STUDY, REPORT 5: REDISCOVERING MACULAR NEOVASCULARIZATION TYPE 3: Multimodal Imaging of Fellow Eyes over 24 months.

PURPOSE: To explore the condition of fellow eyes of patients with macular neovascularization Type 3 (MNV3) and to verify whether the retinal-choroidal anastomosis (RCA) develops equally in all MNV types. METHODS: The contralateral eyes of 94 patients with MNV3, 96 patients with MNV1, and 96 patients with MNV2 were included. Multimodal imaging was performed. The MNV3 stage including the development of fibrosis and RCA over 24 months was determined. RESULTS: In the contralateral eyes of patients of the solitary (one lesion) MNV3 group, 32 eyes (42.1%) showed early/intermediate age-related macular degeneration, 25 eyes (33%) showed MNV3, and 11 eyes (14.5%) experienced fibrosis, of which 4 eyes (5.2%) had a RCA, 7 eyes (9.2%) had atrophy after resolved MNV3, and 1 eye (1.3%) developed MNV1. In the multifocal (more than one lesion) MNV3 group, 2 eyes (11.1%) showed early/intermediate age-related macular degeneration, 9 eyes (50%) showed 15 MNV3 lesions, and 4 eyes (22.2%) showed fibrosis, of which 2 eyes (11.1%) manifested with a RCA and 3 eyes (16.7%) showed atrophy after resolved MNV3. The number of eyes with a RCA accounted for 40% of all eyes with fibrosis. The count of simultaneous bilateral multifocal MNV3 was 5 (55.6%). In the MNV1 and MNV2 groups, no eye developed a RCA. The incidence of RCAs in the scarred eyes in MNV3 was significantly higher (P < 0.0001). CONCLUSION: Retinal-choroidal anastomosis is an exclusive clinical feature of MNV3. The development of the multifocal MNV3 is usually bilateral and simultaneous. The occurrence of fibrosis in MNV3 has decreased dramatically after the introduction of the antiangiogenic therapy.

THE IMPACT OF THE VITREOMACULAR INTERFACE ON FUNCTIONAL AND ANATOMICAL OUTCOMES IN DIABETIC MACULAR EDEMA TREATED WITH THREE DIFFERENT ANTI-VEGF AGENTS: Post Hoc Analysis of The Protocol T Study.

PURPOSE: To investigate the impact of baseline vitreomacular interface status on treatment outcomes in patients treated with three different anti-vascular endothelial growth factors for diabetic macular edema. METHODS: Post hoc analysis from patients enrolled in the DRCR.net Protocol T study. Optical coherence tomography images were analyzed at baseline and at the end of follow-up to identify the presence of complete vitreomacular adhesion, partial vitreomacular adhesion, vitreomacular traction syndrome, and complete posterior vitreous detachment. RESULTS: Six hundred and twenty-nine eyes were eligible for the study based on the study criteria. Complete adhesion eyes gained on average +3.7 more ETDRS letters compared with the complete posterior vitreous detachment group at the end of the 12 months follow-up ( P < 0.001). Baseline vitreomacular interface status had no significant influence on central subfield thickness at 12 months ( P = 0.144). There was no difference between the treatment arms based on effect of baseline vitreomacular interface status on best-corrected visual acuity gain. CONCLUSION: This study provides evidence that vitreomacular interface status affects functional outcomes in diabetic macular edema patients treated with anti-vascular endothelial growth factor injections. The presence of complete or partial vitreomacular adhesion at baseline may be associated with a larger treatment benefit than those with complete posterior vitreous detachment.

VALIDATION OF AN AUTOMATED FLUID ALGORITHM ON REAL-WORLD DATA OF NEOVASCULAR AGE-RELATED MACULAR DEGENERATION OVER FIVE YEARS.

BACKGROUND/PURPOSE: To apply an automated deep learning automated fluid algorithm on data from real-world management of patients with neovascular age-related macular degeneration for quantification of intraretinal/subretinal fluid volumes in optical coherence tomography images. METHODS: Data from the Vienna Imaging Biomarker Eye Study (VIBES, 2007-2018) were analyzed. Databases were filtered for treatment-naive neovascular age-related macular degeneration with a baseline optical coherence tomography and at least one follow-up and 1,127 eyes included. Visual acuity and optical coherence tomography at baseline, Months 1 to 3/Years 1 to 5, age, sex, and treatment number were included. Artificial intelligence and certified manual grading were compared in a subanalysis of 20%. Main outcome measures were fluid volumes. RESULTS: Intraretinal/subretinal fluid volumes were maximum at baseline (intraretinal fluid: 21.5/76.6/107.1 nL; subretinal fluid 13.7/86/262.5 nL in the 1/3/6-mm area). Intraretinal fluid decreased to 5 nL at M1-M3 (1-mm) and increased to 11 nL (Y1) and 16 nL (Y5). Subretinal fluid decreased to a mean of 4 nL at M1-M3 (1-mm) and remained stable below 7 nL until Y5. Intraretinal fluid was the only variable that reflected VA change over time. Comparison with human expert readings confirmed an area under the curve of >0.9. CONCLUSION: The Vienna Fluid Monitor can precisely quantify fluid volumes in optical coherence tomography images from clinical routine over 5 years. Automated tools will introduce precision medicine based on fluid guidance into real-world management of exudative disease, improving clinical outcomes while saving resources.

IMPACT OF RESIDUAL SUBRETINAL FLUID VOLUMES ON TREATMENT OUTCOMES IN A SUBRETINAL FLUID-TOLERANT TREAT-AND-EXTEND REGIMEN.

PURPOSE: To investigate associations between residual subretinal fluid (rSRF) volumes, quantified using artificial intelligence and treatment outcomes in a subretinal fluid (SRF)-tolerant treat-and-extend (T&E) regimen in neovascular age-related macular degeneration. METHODS: Patients enrolled in the prospective, multicenter FLUID study randomized in an SRF-tolerant T&E regimen were examined by spectral-domain optical coherence tomography and tested for best-corrected visual acuity (BCVA). Intraretinal fluid and SRF volumes were quantified using artificial intelligence tools. In total, 375 visits of 98 patients were divided into subgroups: extended intervals despite rSRF and extended intervals without fluid. Associations between BCVA change, SRF volume, subgroups, and treatment intervals were estimated using linear mixed models. RESULTS: In extended intervals despite rSRF, increased SRF was associated with reduced BCVA at the next visit in the central 1 mm (-0.138 letters per nL; P = 0.014) and 6 mm (-0.024 letters per nL; P = 0.049). A negative association between increased interval and BCVA change was found for rSRF in 1 mm and 6 mm (-0.250 and -0.233 letter per week interval, respectively; both P < 0.001). Extended intervals despite rSRF had significantly higher SRF volumes in the central 6 mm at the following visit (P = 0.002). CONCLUSION: Artificial intelligence-based analysis of extended visits despite rSRF demonstrated increasing SRF volumes associated with BCVA loss at the consecutive visit. This negative association contributes to the understanding of rSRF volumes on treatment outcomes in neovascular age-related macular degeneration.

THE RAP STUDY, REPORT TWO: The Regional Distribution of Macular Neovascularization Type 3, a Novel Insight Into Its Etiology.

PURPOSE: To explore the regional distribution of macular neovascularization type 3 (MNV3). METHODS: Seventy-eight eyes of 78 patients were reviewed. We defined the location of each lesion after applying a modified ETDRS grid and the incidence of simultaneous MNV1 or 2. Also, we investigated the distribution of MNV3 at the outline of the foveal avascular zone and when the diameter of foveal avascular zone was less than 325 µm. RESULTS: The distribution of MNV3 was 4 lesions (5%) from the center to 500 µm, 72 (92%) from 500 µm to 1500 µm, and 2 (3%) from 1,500 µm to 3000 µm. The distribution in respect of the ETDRS fields was 7 (9%) nasal, 16 (20%) superior, 32 (40%) temporal, and 23 (31%) inferior. No additional MNV1 or 2 were found elsewhere. Most lesions tended to distribute along straight bands radiating from the perifoveal area, mainly in the temporal half (72%). None of the cases had MNV3 at the boundary of the foveal avascular zone. Only five cases had foveal avascular zone diameter of less than 325 µm, the closest lesion was 425 µm away from the center. CONCLUSION: MNV3 lesions are most likely neither symmetrical nor uniformly distributed. They have a higher affinity to distribute radially in the temporal perifoveal area.

MORPHOLOGICAL AND FUNCTIONAL CHARACTERISTICS AT THE ONSET OF EXUDATIVE CONVERSION IN AGE-RELATED MACULAR DEGENERATION.

PURPOSE: To characterize retinal morphology differences among different types of choroidal neovascularization and visual function changes at the onset of exudative age-related macular degeneration. METHODS: In a post hoc analysis of a prospective clinical study, 1,097 fellow eyes from subjects with choroidal neovascularization in the study eye enrolled in the HARBOR trial were evaluated. The onset of exudation was diagnosed on monthly optical coherence tomography by two masked graders. At conversion as well as 1 month earlier, pigment epithelial detachment, intraretinal cystoid fluid, subretinal fluid, subretinal hyperreflective material, as well as ellipsoid zone and external limiting membrane loss were quantitatively analyzed. Hyperreflective foci, retinal pigment epithelial defects, haze and vitreoretinal interface status were evaluated qualitatively. Main outcome measures included visual acuity and rates of morphologic features at conversion and 1 month earlier. RESULTS: New-onset exudation was detected in 92 eyes. One month before conversion, hyperreflective foci, pigment epithelial detachment, retinal pigment epithelial defects, and haze were present in the majority of eyes. At the onset of exudation, the volumes of intraretinal cystoid fluid, subretinal fluid, subretinal hyperreflective material and pigment epithelial detachment, and the areas of external limiting membrane and ellipsoid zone loss significantly increased. The mean vision loss was -2.2 letters. Pathognomonic patterns of the different choroidal neovascularization types were already apparent 1 month before conversion. CONCLUSION: Characteristic choroidal neovascularization-associated morphological changes are preceding disease conversion, while vision loss at the onset of exudation is minimal. Individual lesion types are related to specific changes in optical coherence tomography morphology already before the time of conversion. Our findings may help to elucidate the pathophysiology of neovascular age-related macular degeneration and support the diagnosis of imminent disease conversion.

Functional versus functional and anatomical criteria-guided ranibizumab treatment in patients with neovascular age-related macular degeneration - results from the randomized, phase IIIb OCTAVE study.

BACKGROUND: To evaluate the efficacy and safety of two individualized ranibizumab retreatment schemes in neovascular age-related macular degeneration. METHODS: Patients (N = 671) were randomized (1:1) to receive three initial monthly ranibizumab 0.5 mg injections, then retreatment guided by either best-corrected visual acuity (BCVA) loss (Group I) or BCVA loss and/or signs of disease activity on optical coherence tomography (OCT; Group II). The study was terminated prematurely and the decision to discontinue the study was made by the sponsor. Efficacy analyses were performed on patients who completed 12 months of the originally planned 24-month study. Safety analyses are presented for all safety analyzable patients. RESULTS: Of 671 randomized patients, 305 completed 12 months of the study. For the 12-month completers, baseline mean (standard deviation) BCVA and reading-center evaluated central subfield thickness (CSFT) were comparable [Group I: 60.9 (13.10) letters and 517.7(201.79) µm; Group II: 60.2 (12.21) letters and 515.3 (198.37) µm]. The change from baseline at Month 12 in BCVA was 6.7 (13.48) letters in Group I and 8.3 (13.53) letters in Group II and the change in CSFT was - 161.3 (163.48) µm and - 175.3 (170.45) µm, respectively. The mean number of ranibizumab injections was 8.2 in Group I and 8.4 in Group II. CONCLUSION: Ranibizumab treatment resulted in visual and anatomic gains at 12 months for both retreatment strategies, with a trend in favor of OCT-guided vs BCVA loss guided retreatment. No new safety signals were seen. TRIAL REGISTRATION: www.ClinicalTrials.gov (NCT01780935). Registered 31 January 2013.

Guidelines for the Management of Retinal Vein Occlusion by the European Society of Retina Specialists (EURETINA).

The high prevalence of cardiovascular disease particularly in the elderly population is associated with retinal vascular disease. Retinal vein occlusions represent severe disturbances of the hypoxia-sensitive neurosensory retina. Acute and excessive leakage leads to the diagnostic hallmarks of retinal hemorrhage and edema with substantial retinal thickening. Advanced diagnostic tools such as OCT angiography allow to evaluate retinal ischemia and identify the risk for late complications and will soon reach clinical routine besides fluorescein angiography. Accordingly, the duration of non-perfusion is a crucial prognostic factor requiring timely therapeutic intervention. With immediate inhibition of vascular leakage, anti-VEGF substances excel as treatment of choice. Multiple clinical trials with optimal potential for functional benefit or a lesser regenerative spectrum have evaluated aflibercept, ranibizumab, and bevacizumab. As retinal vein occlusion is a chronic disease, long-term monitoring should be individualized to combine maintenance with practicability. While steroids may be considered in patients with systemic cardiovascular risk, surgery remains advisable only for very few patients. Destructive laser treatment is an option if reliable monitoring is not feasible. Ophthalmologists are also advised to perform a basic systemic workup to recognize systemic concomitants. The current edition of the EURETINA guidelines highlights the state-of-the-art recommendations based on the literature and expert opinions in retinal vein occlusion.

Fully Automated Detection and Quantification of Macular Fluid in OCT Using Deep Learning.

PURPOSE: Development and validation of a fully automated method to detect and quantify macular fluid in conventional OCT images. DESIGN: Development of a diagnostic modality. PARTICIPANTS: The clinical dataset for fluid detection consisted of 1200 OCT volumes of patients with neovascular age-related macular degeneration (AMD, n = 400), diabetic macular edema (DME, n = 400), or retinal vein occlusion (RVO, n = 400) acquired with Zeiss Cirrus (Carl Zeiss Meditec, Dublin, CA) (n = 600) or Heidelberg Spectralis (Heidelberg Engineering, Heidelberg, Germany) (n = 600) OCT devices. METHODS: A method based on deep learning to automatically detect and quantify intraretinal cystoid fluid (IRC) and subretinal fluid (SRF) was developed. The performance of the algorithm in accurately identifying fluid localization and extent was evaluated against a manual consensus reading of 2 masked reading center graders. MAIN OUTCOME MEASURES: Performance of a fully automated method to accurately detect, differentiate, and quantify intraretinal and SRF using area under the receiver operating characteristics curves, precision, and recall. RESULTS: The newly designed, fully automated diagnostic method based on deep learning achieved optimal accuracy for the detection and quantification of IRC for all 3 macular pathologies with a mean accuracy (AUC) of 0.94 (range, 0.91-0.97), a mean precision of 0.91, and a mean recall of 0.84. The detection and measurement of SRF were also highly accurate with an AUC of 0.92 (range, 0.86-0.98), a mean precision of 0.61, and a mean recall of 0.81, with superior performance in neovascular AMD and RVO compared with DME, which was represented rarely in the population studied. High linear correlation was confirmed between automated and manual fluid localization and quantification, yielding an average Pearson's correlation coefficient of 0.90 for IRC and of 0.96 for SRF. CONCLUSIONS: Deep learning in retinal image analysis achieves excellent accuracy for the differential detection of retinal fluid types across the most prevalent exudative macular diseases and OCT devices. Furthermore, quantification of fluid achieves a high level of concordance with manual expert assessment. Fully automated analysis of retinal OCT images from clinical routine provides a promising horizon in improving accuracy and reliability of retinal diagnosis for research and clinical practice in ophthalmology.

Guidelines for the Management of Diabetic Macular Edema by the European Society of Retina Specialists (EURETINA).

Diabetic retinal disease is envisioned to become the plague of the coming decades with a steep increase of worldwide diabetes incidence followed by a substantial rise in retinal disease. Improvements in diagnostic and therapeutic care have to cope with this dilemma in a clinically and socioeconomically efficient manner. Laser treatment has found a less destructive competitor in pharmacological treatments. As a consequence of recent rigorous clinical trials, laser photocoagulation is no longer recommended for the treatment of diabetic macular edema (DME), and anti-vascular endothelial growth factor therapy has emerged as first-line therapy. Steroids have maintained a role in the management of chronically persistent DME. The paradigm shifts in therapy are accompanied by a substantial break-through in diagnostics. The following guidance for the management of DME has been composed from the best updated knowledge of leading experts in Europe and represents another volume in the series of EURETINA recommendations for the management of retinal disease.

An Automated Comparative Analysis of the Exudative Biomarkers in Neovascular Age-Related Macular Degeneration, The RAP Study: Report 6.

PURPOSE: To investigate differences in volume and distribution of the main exudative biomarkers across all types and subtypes of macular neovascularization (MNV) using artificial intelligence (AI). DESIGN: Cross-sectional study. METHODS: An AI-based analysis was conducted on 34,528 OCT B-scans consisting of 281 (250 unifocal, 31 multifocal) MNV3, 55 MNV2, and 121 (30 polypoidal, 91 non-polypoidal) MNV1 treatment-naive eyes. Means (SDs), medians and heat maps of cystic intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachments (PED), and hyperreflective foci (HRF) volumes, as well as retinal thickness (RT) were compared among MNV types and subtypes. RESULTS: MNV3 had the highest mean IRF with 291 (290) nL, RT with 357 (49) µm, and HRF with 80 (70) nL, P ≤ .05. MNV1 showed the greatest mean SRF with 492 (586) nL, whereas MNV3 exhibited the lowest with 218 (382) nL, P ≤ .05. Heat maps showed IRF confined to the center, whereas SRF was scattered in all types. SRF, HRF, and PED were more distributed in the temporal macular half in MNV3. Means of IRF, HRF, and PED were higher in the multifocal than in the unifocal MNV3 with 416 (309) nL,114 (95) nL, and 810 (850) nL, P ≤ .05. Compared to the non-polypoidal subtype, the polypoidal subtype had greater means of SRF with 695 (718) nL, HRF 69 (63) nL, RT 357 (45) µm, and PED 1115 (1170) nL, P ≤ .05. CONCLUSIONS: This novel quantitative AI analysis shows that SRF is a biomarker of choroidal origin in MNV1, whereas IRF, HRF, and RT are retinal biomarkers in MNV3. Polypoidal MNV1 and multifocal MNV3 present with higher exudation compared to other subtypes.

A systematic evaluation of human expert agreement on optical coherence tomography biomarkers using multiple devices.

OBJECTIVES: To assess the agreement in evaluating optical coherence tomography (OCT) variables in the leading macular diseases such as neovascular age-related macular degeneration (nAMD), diabetic macular oedema (DMO) and retinal vein occlusion (RVO) among OCT-certified graders. METHODS: SD-OCT volume scans of 356 eyes were graded by seven graders. The grading included presence of intra- and subretinal fluid (IRF, SRF), pigment epithelial detachment (PED), epiretinal membrane (ERM), conditions of the vitreomacular interface (VMI), central retinal thickness (CRT) at the foveal centre-point (CP) and central millimetre (CMM), as well as height and location of IRF/SRF/PED. Kappa statistics (κ) and intraclass correlation coefficient (ICC) were used to report categorical grading and measurement agreement. RESULTS: The overall agreement on the presence of IRF/SRF/PED was κ = 0.82/0.85/0.81; κ of VMI condition was 0.77, that of ERM presence 0.37. ICC for CRT measurements at CP and CMM was excellent with an ICC of 1.00. Height measurements of IRF/SRF/PED showed robust consistency with ICC = 0.85-0.93. There was substantial to almost perfect agreement in locating IRF/SRF/PED with κ = 0.67-0.86. Between diseases, κ of IRF/SRF presence was 0.69/0.80 for nAMD, 0.64/0.83 for DMO and 0.86/0.89 for RVO. CONCLUSION: Even in the optimized setting, featuring certified graders, standardized image acquisition and the use of a professional reading platform, there is a disease dependent variability in biomarker evaluation that is most pronounced for IRF in nAMD as well as DMO. Our findings highlight the variability in the performance of human expert OCT grading and the need for AI-based automated feature analyses.

Performance of retinal fluid monitoring in OCT imaging by automated deep learning versus human expert grading in neovascular AMD.

PURPOSE: To evaluate the reliability of automated fluid detection in identifying retinal fluid activity in OCT scans of patients treated with anti-VEGF therapy for neovascular age-related macular degeneration by correlating human expert and automated measurements with central retinal subfield thickness (CSFT) and fluid volume values. METHODS: We utilized an automated deep learning approach to quantify macular fluid in SD-OCT volumes (Cirrus, Spectralis, Topcon) from patients of HAWK and HARRIER Studies. Three-dimensional volumes for IRF and SRF were measured at baseline and under therapy in the central millimeter and compared to fluid gradings, CSFT and foveal centerpoint thickness (CPT) values measured by the Vienna Reading Center. RESULTS: 41.906 SD-OCT volume scans were included into the analysis. Concordance between human expert grading and automated algorithm performance reached AUC values of 0.93/0.85 for IRF and 0.87 for SRF in HARRIER/HAWK in the central millimeter. IRF volumes showed a moderate correlation with CSFT at baseline (HAWK: r = 0.54; HARRIER: r = 0.62) and weaker correlation under therapy (HAWK: r = 0.44; HARRIER: r = 0.34). SRF and CSFT correlations were low at baseline (HAWK: r = 0.29; HARRIER: r = 0.22) and under therapy (HAWK: r = 0.38; HARRIER: r = 0.45). The residual standard error (IRF: 75.90 µm; SRF: 95.26 µm) and marginal residual standard deviations (IRF: 46.35 µm; SRF: 44.19 µm) of fluid volume were high compared to the range of CSFT values. CONCLUSION: Deep learning-based segmentation of retinal fluid performs reliably on OCT images. CSFT values are weak indicators for fluid activity in nAMD. Automated quantification of fluid types, highlight the potential of deep learning-based approaches to objectively monitor anti-VEGF therapy.

Therapeutic response in the HAWK and HARRIER trials using deep learning in retinal fluid volume and compartment analysis.

OBJECTIVES: To assess the therapeutic response to brolucizumab and aflibercept by deep learning/OCT-based analysis of macular fluid volumes in neovascular age-related macular degeneration. METHODS: In this post-hoc analysis of two phase III, randomised, multi-centre studies (HAWK/HARRIER), 1078 and 739 treatment-naive eyes receiving brolucizumab or aflibercept according to protocol-specified criteria in HAWK and HARRIER, respectively, were included. Macular fluid on 41,840 OCT scans was localised and quantified using a validated deep learning-based algorithm. Volumes of intraretinal fluid (IRF), subretinal fluid (SRF), pigment epithelial detachment (PED) for all central macular areas (1, 3 and 6 mm) in nanolitres (nL) and best corrected visual acuity (BCVA) change in ETDRS letters were associated using mixed models for repeated measures. RESULTS: Baseline IRF volumes decreased by >92% following the first intravitreal injection and consistently remained low during follow-up. Baseline SRF volumes decreased by >74% following the first injection, while PED volume resolved by 68-79% of its baseline volume. Resolution of SRF and PED was dependent on the substance and regimen used. Larger residual post-loading IRF, SRF and PED volumes were all independently associated with progressive vision loss during maintenance, where the differences in mean BCVA change between high and low fluid volume subgroups for IRF, SRF and PED were 3.4 letters (p < 0.0001), 1.7 letters (p < 0.001) and 2.5 letters (p < 0.0001), respectively. CONCLUSIONS: Deep-learning methods allow an accurate assessment of substance and regimen efficacy. Irrespectively, all fluid compartments were found to be important markers of disease activity and were relevant for visual outcomes.

Segmentation of macular neovascularization and leakage in fluorescein angiography images in neovascular age-related macular degeneration using deep learning.

BACKGROUND/OBJECTIVES: We aim to develop an objective fully automated Artificial intelligence (AI) algorithm for MNV lesion size and leakage area segmentation on fluorescein angiography (FA) in patients with neovascular age-related macular degeneration (nAMD). SUBJECTS/METHODS: Two FA image datasets collected form large prospective multicentre trials consisting of 4710 images from 513 patients and 4558 images from 514 patients were used to develop and evaluate a deep learning-based algorithm to detect CNV lesion size and leakage area automatically. Manual segmentation of was performed by certified FA graders of the Vienna Reading Center. Precision, Recall and F1 score between AI predictions and manual annotations were computed. In addition, two masked retina experts conducted a clinical-applicability evaluation, comparing the quality of AI based and manual segmentations. RESULTS: For CNV lesion size and leakage area segmentation, we obtained F1 scores of 0.73 and 0.65, respectively. Expert review resulted in a slight preference for the automated segmentations in both datasets. The quality of automated segmentations was slightly more often judged as good compared to manual annotations. CONCLUSIONS: CNV lesion size and leakage area can be segmented by our automated model at human-level performance, its output being well-accepted during clinical applicability testing. The results provide proof-of-concept that an automated deep learning approach can improve efficacy of objective biomarker analysis in FA images and will be well-suited for clinical application.