OCT Biomarkers Research Articles

Analysis of Henle's fiber layer and outer retinal layers in cone dystrophy.

To evaluate Henle's Fiber Layer (HFL) thickness and volume parameters in patients with cone photoreceptor atrophy with directional optical coherence tomography (D-OCT). Macular 20°×20° standard and D-OCT images were acquired from patients diagnosed with hereditary cone dystrophy with evident foveal ellipsoid zone defect in OCT, and age-matched healthy controls. Thickness and volume parameters of HFL, outer nuclear layer (ONL) and retinal layers between ellipsoid zone and Bruch membrane complex (EZ-BM) were calculated from manual segmentation through D-OCT images and comparative analysis is performed. Twelve eyes of 6 patients were compared to 12 eyes of 6 age-matched healthy controls (mean age: 29.5±16.6 and 26.6±3.9 years respectively; P=0.162). Patients had lower total HFL volume (0.45±0.03 and 0.85±0.15 mm3; P<0.001) and mean HFL thickness (16.1±1.1 and 30.1±5.3 µm; P<0.001) than healthy controls. Central subfield, parafoveal and perifoveal ETDRS zone HFL parameters in patients were significantly lower than healthy controls. A centrifugal correlation was found between central ONL and the corresponding parafoveal HFL (Spearman's rho: 0.785; P<0.001). HFL assessment might be a useful OCT biomarker in patients with cone photoreceptor atrophy. HFL thinning is observed in foveal, parafoveal and perifoveal areas of patients with cone photoreceptor atrophy, while volume reduction in ONL and EZ-BM components were limited to central and parafoveal zones.

Sub-Internal Limiting Membrane Foveal Hemorrhage Under Tension: OCT Biomarkers Predicting Macular Hole Formation after Submacular Hemorrhage.

To identify preoperative clinical characteristics of macular hole (MH) formation after vitrectomy for submacular hemorrhage (SMH) due to ruptured retinal arterial macroaneurysm (RAM). We retrospectively analyzed eyes with SMH due to ruptured RAM in patients who underwent vitrectomy and had more than one month of follow-up. We compared background factors and imaging findings between groups classified by MH presence. The primary outcomes were best-corrected visual acuity, and fundus and optical coherence tomography findings. We identified 48 eyes with SMH due to RAM rupture. MHs were identified in 8 eyes (16.3%); 4 intraoperatively and 4 postoperatively. Preoperative OCT findings revealed that all MH cases exhibited the highest retinal thickness at the foveal lesion with sub-internal limiting membrane (ILM) hemorrhage preoperatively. We termed this finding the "foveal mountain peak" (FMP) sign, characterized by sub-ILM hemorrhage where the peak of the retinal thickness coincides with the fovea. The incidence of FMP sign (+) cases was significantly higher in the MH (+) group compared with the MH (-) group (100% vs. 47.5%, respectively; P = 0.006). The presence of the FMP sign may indicate an increased risk of SMH-associated MH.

Influence of OCT biomarkers on microperimetry intra- and interdevice repeatability in diabetic macular edema

To evaluate the intra- and interdevice repeatability of microperimetry (MP) assessments in patients with diabetic macular edema (DME) two consecutive MP testings (45 fovea-centered stimuli, 4–2 staircase strategy) were performed using MP3 (NIDEK, Aichi, Japan) and MAIA (CenterVue, Padova, Italy), respectively. Intraretinal fluid (IRF) and ellipsoid zone (EZ) thickness were automatically segmented by published deep learning algorithms. Hard exudates (HEs) were annotated semi-automatically and disorganization of retinal inner layers (DRIL) was segmented manually. Point-to-point registration of MP stimuli to corresponding spectral-domain OCT (Spectralis, Heidelberg Engineering, Germany) locations was performed for both devices. Repeatability was assessed overall and in areas of disease-specific OCT biomarkers using Bland-Altmann coefficients of repeatability (CoR). A total of 3600 microperimetry stimuli were tested in 20 eyes with DME. Global CoR was high using both devices (MP3: ± 6.55 dB, MAIA: ± 7.69 dB). Higher retest variances were observed in stimuli with IRF (MP3: CoR ± 7.4 dB vs. ± 6.0 dB, p = 0.001, MAIA: CoR ± 9.2dB vs. ± 6.8 dB, p = 0.002) and DRIL on MP3 (CoR ± 6.9 dB vs. ± 3.2 dB, p < 0.001) compared to stimuli without. Repeatabilities were reduced in areas with thinner EZ layers (both p < 0.05). Fixation (Fuji classification) was relatively unstable independent of device and run. These findings emphasize taking higher caution using MP in patients with DME.

Internal Limiting Membrane Peeling for Large Macular Holes Induces Only Structural Remodeling without Functional Impairment Over 12 Years

To evaluate the very long-term functional and structural outcomes of internal limiting membrane (ILM) peeling for full-thickness macular holes (FTMH). Observational case series nested within a multicenter, randomized, controlled clinical trial (RCT) (ClinicalTrials.gov: NCT00190190). Patients who underwent vitrectomy with or without ILM peeling for an idiopathic large FTMH in a tertiary ophthalmology center, with a minimum follow-up of 10 years after surgery. Review of charts, spectral-domain OCT (SD-OCT) scans, OCT angiography (OCTA) scans, and microperimetry of patients originally enrolled in the RCT. Primary outcome was functional assessment in both groups (ILM peeling or not) including the retinal sensitivity (RS), distance and near best-corrected visual acuity (BCVA), and number of eyes achieving ≥0.3 logarithm of the minimum angle of resolution >10 years after surgery. Secondary outcomes were structural assessment in the entire 3× 3-mm and 6× 6-mm areas, and regionally in the different areas of the ETDRS grid: OCT and OCTA biomarkers in both groups and fellow eyes. Thirteen eyes of 13 patients with a mean follow-up of 12 ± 0.73 years were included. The mean RS and BCVA, or visual improvement did not differ between ILM peeling (n= 8) and no peeling (n= 5) (all P > 0.05). The dissociated optic nerve fiber layers on en face OCT were only observed in eyes with ILM peeling, predominantly in temporal parafoveal (20%) and perifoveal (19%) rings. The mean total retinal thickness and inner retinal thickness in the parafoveal ring were significantly lower in peeled eyes (309 ± 11 μm and 94 ± 9 μm respectively) versus nonpeeled eyes (330 ± 21 μm and 108 ± 11 μm respectively; P= 0.037 and P= 0.040), without significant difference in ganglion cell or retinal nerve fiber layers. Accordingly, the mean superficial capillary plexus density in the parafoveal ring was significantly lower in eyes with peeling versus without (39.65 ± 3.76 % versus 47.22 ± 4.00; P= 0.005). The mean foveal avascular zone area was smaller in eyes with peeling versus without (0.24 ± 0.05 mm2 vs. 0.42 ± 0.13 mm2, respectively, P= 0.005). Despite persistent structural changes especially in the parafoveal ring, ILM peeling for idiopathic large FTMH did not seem to impact long-term RS or BCVA over 12 years. Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Choroidal imaging biomarkers as predictors of conversion to exudative age-related macular degeneration.

Predicting the progression of intermediate AMD (iAMD) to neovascular AMD (nAMD) will help to identify high-risk patients and improve treatment outcomes. The present study assessed whether choroidal OCT biomarkers could predict conversion to nAMD. This retrospective study included patients with clinically stable iAMD who either converted to nAMD (C group) or did not convert (NC group) during one year of follow-up. OCT parameters included subfoveal choroidal thickness (SFCT), central macular thickness (CMT), Haller vascular thickness (HVT), inner choroidal thickness (ICT), and double-layer sign (DLS). Of 116 total eyes, there were 37 in the NC group and 79 in the C group. Baseline SFCT was significantly lower in the C group compared to the NC group (169.0 ± 63.2μm vs. 218.0 ± 97.8μm, p = 0.01). Baseline HVT and ICT were lower in the C group (105.2 ± 40.6μm vs. 121.0 ± 56.6μm, p = 0.17 and 61.9 ± 35.5μm vs. 77.5 ± 41.7μm, p = 0.09). HVT was decreased at all time points in the C group vs NC (p > 0.05). The ICT was reduced in the C group at each time point except at conversion time (p > 0.05). Of all eight eyes who presented DLS at baseline, 100% converted to nAMD (p < 0.001). Lower SFCT at baseline may signal conversion to nAMD within 12months.

Evaluation of Anatomical and Tomographic Biomarkers as Predictive Visual Acuity Factors in Eyes with Retinal Vein Occlusion Treated with Dexamethasone Implant.

Background: This prospective study evaluated the impact of anatomical and tomographic biomarkers on clinical outcomes of intravitreal dexamethasone implants in patients with macular edema secondary to retinal vein occlusion (RVO). Methods: The study included 46 patients (28 with branch RVO (BRVO) and 18 with central RVO (CRVO)). Best corrected visual acuity (BCVA) significantly improved from a mean baseline of 0.817 ± 0.220 logMAR to 0.663 ± 0.267 logMAR at six months and 0.639 ± 0.321 logMAR at twelve months (p < 0.05). Central retinal thickness (CRT) showed a significant reduction from 666.2 ± 212.2 µm to 471.1 ± 215.6 µm at six months and 467 ± 175.7 µm at twelve months (p < 0.05). No significant differences were found in OCT biomarkers between baseline and follow-ups. Results: The study analysed improvements in visual acuity relative to baseline biomarkers. At six months, ellipsoid zone disruption (EZD) was significant for all subgroups. Disorganization of retinal inner layers (DRIL), external limiting membrane (ELM) disruption, macular ischemia (MI), CRT, and BRVO showed significance for any improvement, while DRIL and ELM were significant for changes greater than 0.3 logMAR (p < 0.05). At twelve months, EZD remained significant for all subgroups. ELM, MI, CRT, and BRVO were significant for any improvement, while MI and BRVO were significant for changes greater than 0.3 logMAR (p < 0.05). Hyperreflective foci were not statistically significant at either time point (p > 0.05). Conclusions: The regression model suggested that MI and CRVO could be negative predictive factors for visual outcomes, while ELM and EZD were associated with BCVA improvement one-year post-treatment.

OCT Biomarkers in Ocular CLN2 Disease in Patients Treated With Intraventricular Enzyme Replacement Therapy.

Bilateral progressive, symmetrical loss of central retinal thickness (CRT) has been described in neuronal ceroid lipofuscinosis type 2 (CLN2) disease. This study details the pattern of morphological changes underlying CRT loss and disease progression in patients receiving intracerebroventricular (ICV) enzyme replacement therapy (ERT) with cerliponase alfa. Spectral-domain optical coherence tomography macular cube scans were collected from 16 patients with classic CLN2 disease receiving ICV ERT. Detailed retinal structure analyses were performed on manually segmented horizontal B-scans through the fovea to determine the thickness of six retinal parameters and the extent of ellipsoid zone (EZ) loss. Anatomical changes primarily occurred in photoreceptor (PR)-related retinal parameters and correlated with ocular disease severity. Retinal degeneration began with initial focal parafoveal EZ discontinuities signaling the onset of rapid PR degeneration in a predictable pattern: parafoveal PR involvement with foveal sparing followed by profound parafoveal and foveal PR loss with additional thinning beyond the central retina. PR degeneration began with outer segment loss and progressed to outer nuclear layer (ONL) involvement. Longitudinal analyses confirmed these observations. The rate of PR loss was fastest at the fovea at ∼58 mm per year and became slower at locations farther away from the fovea. Retinal degeneration in CLN2 disease is primarily associated with PR loss in a predictable pattern, with EZ disruption signaling early PR stress. CRT, ONL thickness, and PR layer thickness are useful anatomical biomarkers for understanding disease progression and treatment efficacy in CLN2. Studies using en face images will further clarify CLN2-related retinal degeneration.

Evaluation of OCT biomarker changes in treatment-naive neovascular AMD using a deep semantic segmentation algorithm

ObjectivesTo determine real-life quantitative changes in OCT biomarkers in a large set of treatment naive patients in a real-life setting undergoing anti-VEGF therapy. For this purpose, we devised a novel deep learning based semantic segmentation algorithm providing the first benchmark results for automatic segmentation of 11 OCT features including biomarkers for neovascular age-related macular degeneration (nAMD).MethodsTraining of a Deep U-net based semantic segmentation ensemble algorithm for state-of-the-art semantic segmentation performance which was used to analyze OCT features prior to, after 3 and 12 months of anti-VEGF therapy.ResultsHigh F1 scores of almost 1.0 for neurosensory retina and subretinal fluid on a separate hold-out test set with unseen patients. The algorithm performed worse for subretinal hyperreflective material and fibrovascular PED, on par with drusenoid PED, and better in segmenting fibrosis. In the evaluation of treatment naive OCT scans, significant changes occurred for intraretinal fluid (mean: 0.03 µm3 to 0.01 µm3, p < 0.001), subretinal fluid (0.08 µm3 to 0.01 µm3, p < 0.001), subretinal hyperreflective material (0.02 µm3 to 0.01 µm3, p < 0.001), fibrovascular PED (0.12 µm3 to 0.09 µm3, p = 0.02) and central retinal thickness C0 (225.78 µm3 to 169.40 µm3). The amounts of intraretinal fluid, fibrovascular PED, and ERM were predictive of poor outcome.ConclusionsThe segmentation algorithm allows efficient volumetric analysis of OCT scans. Anti-VEGF provokes most potent changes in the first 3 months while a gradual loss of RPE hints at a progressing decline of visual acuity. Additional research is required to understand how these accurate OCT predictions can be leveraged for a personalized therapy regimen.

Sex Differences in Inflammation-Related Biomarkers Detected with OCT in Patients with Diabetic Macular Edema

PurposeTo investigate sex-based differences in inflammation-related biomarkers on Spectral-Domain Optical Coherence Tomography (SD-OCT). DesignCross-sectional study. ParticipantsPatients with diabetic macular edema (DME) between February 1, 2019, and March 31, 2023, without intravitreal anti–vascular endothelial growth factor (anti-VEGF) injection within the prior six months. MethodsWe reviewed each patient’s medical record for age, biological sex, race and ethnicity, most recent glycated hemoglobin level (HbA1c), visual acuity (VA), and central macular thickness (CMT). OCT biomarkers that have been found in literature to be associated with inflammation, including disorganization of retinal inner layers (DRIL), retinal hyperreflective foci (HRF), hyperreflective choroidal foci (HCF), subfoveal neuroretinal detachment (SND), and perturbation in retinal nerve fiber layer (RNFL) thickness, ganglion cell layer (GCL) thickness, and inner nuclear layer (INL) thickness were evaluated by graders masked to the clinical characteristics of the patients. We performed multivariable regression analyses with the OCT biomarkers as the outcome variables and sex, age, HbA1c, and CMT as independent variables. Main Outcome MeasuresOCT inflammation-related biomarkers as listed above ResultsFemale patients were on average two years older than male patients (P = 0.041). There were no significant differences in race and ethnicity, HbA1c, VA, or CMT between male and female patients. After controlling for age, HbA1c, and CMT, we found male sex to be associated with more HRF (incidence rate ratio [IRR] = 1.19, 95% confidence interval [CI] = 1.10 – 1.29), more HCF (odds ratio = 2.01, 95% CI = 1.12 – 3.64), and thicker INL (7 μm thicker in males, 95% CI = 2 – 12). Sex was not a significant predictor for either DRIL or SND in the multivariable regression models. Patients with higher HbA1c were more likely to have more HRF (IRR = 1.02 per 1 point increase, 95% CI = 1.00 – 1.04) after controlling for other factors. ConclusionsMale sex was correlated with more inflammation-related biomarkers on OCT including more HRF, more HCF, and thicker INL, after accounting for age, glycemic control, and amount of DME. Further studies are needed to evaluate the potential implications of these sex-based differences for individualized treatment.

Efficacy and Safety of 0.19-mg Fluocinolone Acetonide Implant in Postoperative Cystoid Macular Edema after Pars Plana Vitrectomy: The ILUvien in Postoperative CYstoid Macular eDema study

PurposeTo assess the efficacy and safety of 0.19-mg fluocinolone acetonide (FAc) intravitreal implant (Iluvien®) in treating chronic postoperative cystoid macular edema (PCME) after pars plana vitrectomy. DesignRetrospective multicentric case series in clinical settings. SubjectsPatients with chronic PCME who underwent vitrectomy in tertiary care centers in France. All eyes had a documented good response to the DEX implant prior to FAc implantation. MethodsReview of charts and OCT scans of patients treated with a FAc intravitreal implant. Main outcome measuresThe primary endpoints were the best-corrected visual acuity (BCVA) and central retinal thickness (CRT). Secondary endpoints were the intraocular pressure (IOP); proportion of patients maintaining a BCVA ≥20/40; need for additional non-study treatment; differences between eyes that underwent a single and multiple surgeries and OCT biomarkers of better BCVA. ResultsForty-nine eyes of 49 patients with a mean follow-up of 24.5 ± 3.9 months were included. The mean BCVA increased from 0.40 ± 0.26 logMAR at baseline to 0.32 ± 0.24 logMAR at month 24 (M24) (p=0.0035). The mean CRT decreased from 409.37 ± 139.43 μm at baseline to 340 ± 91 μm at M24 (p=0.0001). The mean IOP was 14.0 ± 4 mmHg at baseline and remained stable at 14.03 ± 4.1 mmHg at M24 (p=0.99). During the follow-up, the IOP exceeded 21 mmHg in 9 eyes. The IOP rise was controlled with topical therapy in all eyes except one, which required cyclophotocoagulation. The BCVA was ≥20/40 in 47% of eyes (95% CI: 34%-61%) at baseline and in 58% of eyes at M24 (95% CI: 41%-73%). At M18, the likelihood of achieving a BCVA ≥20/40 was higher in eyes with intact external limiting membrane and ellipsoid zone. Additional dexamethasone implant (DEXi) was injected in 14 eyes (28.57%). The treatment burden of 2.45 ± 1.35 DEXi/year was decreased to 0.57 ± 0.60 DEXi/year after FAc implantation (p=0.001). ConclusionFAc implant improved the BCVA and reduced the CRT in eyes with chronic PCME after vitrectomy. The IOP rise could be anticipated by the previous response to corticosteroids. FAc implant in eyes with chronic PCME also allowed reducing the treatment burden.

The Total Macular Burden of Hyperreflective Foci and the Onset of Persistent Choroidal Hypertransmission Defects in Intermediate AMD

Purpose: The association between the total macular burden of hyperreflective foci (HRF) in eyes with intermediate AMD (iAMD) and the onset of persistent choroidal hypertransmission defects (hyperTDs) was studied using swept-source optical coherence tomography (SS-OCT). DesignPost hoc subgroup analysis of a prospective study. Methods: A retrospective review of iAMD eyes from subjects enrolled in a prospective SS-OCT study was performed. All eyes underwent 6×6 mm SS-OCT angiography (SS-OCTA) imaging at baseline and follow-up visits. En face sub-retinal pigment epithelium (subRPE) slabs with segmentation boundaries positioned 64-400 µm beneath Bruch's membrane (BM) were used to identify persistent choroidal hyperTDs. None of the eyes had persistent hyperTDs at baseline. The same subRPE slab was used to identify choroidal hypotransmission defects (hypoTDs) attributable to HRF located either intraretinally (iHRF) or along the RPE (rpeHRF) based on corresponding B-scans. A semiautomated algorithm was used by two independent graders to validate and refine the HRF outlines. The HRF area and the drusen volume within a 5mm fovea-centered circle were measured at each visit. Results: The median follow-up time for the 171 eyes from 121 patients included in this study was 59.1 months (95%CI: 52.0-67.8 months). Of these, 149 eyes (87%) had HRF, and 82 (48%) developed at least one persistent hyperTD during the follow-up. Although univariable Cox regression analyses showed that both drusen volume and total HRF area were associated with the onset of the first persistent hyperTD, multivariable analysis showed that the area of total HRF was the sole significant predictor for the onset of hyperTDs (P<0.001). ROC analysis identified an HRF area ≥ 0.07 mm² to predict the onset of persistent hyperTDs within one year with an area under the curve (AUC) of 0.661 (0.570-0.753), corresponding to a sensitivity of 55% and a specificity of 74% (P<0.001). Conclusions: The total macular burden of HRF, which includes both the HRF along the RPE and within the retina, is an important predictor of disease progression from iAMD to the onset of persistent hyperTDs and should serve as a key OCT biomarker to select iAMD patients at high-risk for disease progression in future clinical trials.

Exploration on OCT biomarker candidate related to macular edema caused by diabetic retinopathy and retinal vein occlusion in SD-OCT images

To improve the understanding of potential pathological mechanisms of macular edema (ME), we try to discover biomarker candidates related to ME caused by diabetic retinopathy (DR) and retinal vein occlusion (RVO) in spectral-domain optical coherence tomography images by means of deep learning (DL). 32 eyes of 26 subjects with non-proliferative DR (NPDR), 77 eyes of 61 subjects with proliferative DR (PDR), 120 eyes of 116 subjects with branch RVO (BRVO), and 17 eyes of 15 subjects with central RVO (CRVO) were collected. A DL model was implemented to guide biomarker candidate discovery. The disorganization of the retinal outer layers (DROL), i.e., the gray value of the retinal tissues between the external limiting membrane (ELM) and retinal pigment epithelium (RPE), the disrupted and obscured rate of the ELM, ellipsoid zone (EZ), and RPE, was measured. In addition, the occurrence, number, volume, and projected area of hyperreflective foci (HRF) were recorded. ELM, EZ, and RPE are more likely to be obscured in RVO group and HRFs are observed more frequently in DR group (all P ≤ 0.001). In conclusion, the features of DROL and HRF can be possible biomarkers related to ME caused by DR and RVO in OCT modality.

Optical coherence tomography-derived texture-based radiomics features identify eyes with intraocular inflammation in the HAWK clinical trial

Background and objectiveIntravitreal injection of anti-VEGF agents is the first-line treatment for patients with neovascular-age related macular degeneration (nAMD). One unique serious adverse event that may be associated with these agents is intraocular inflammation (IOI). The main purpose of this analysis was to evaluate the potential presence of texture-based radiomics features characterizing heterogeneity within the vitreous compartment of spectral domain optical coherence tomography (SD-OCT) images that may precede or develop in association with IOI and might serve as OCT biomarkers for IOI. MethodsThis is a post-hoc analysis of a subset of cases (N = 67) involving IOI, endophthalmitis, and/or retinal vascular occlusion in the phase 3 HAWK trial. These were investigator determined diagnoses that were also confirmed by the safety review committee. Intraocular inflammation was any signs of inflammation within the eye, endophthalmitis was inflammation associated with presumed infection, and retinal vascular occlusions consisted of intraocular inflammation with concurrent vascular occlusions/vasculitis. Out of 67 eyes, 34 belonged to the Safety group with an IOI event and 33 were propensity-matched Controls. A total of 481 texture-based radiomics features were extracted from the vitreous compartment of the SD-OCT scans at pre-IOI time point (i.e., much earlier than the actual event). Most discriminating five features, selected by the Wilcoxon Rank Sum feature selection were evaluated using Random Forest (RF) classifier on the training set (Str, N = 47) to differentiate between the two patient groups. Classifier performance was subsequently validated on the independent test set (St, N = 20). Additionally, the classifier performance in discriminating the Control and Safety group was also validated on St at the IOI event timepoint. ResultsThe RF classifier yielded area under the Receiver Operating Characteristics curve (AUC) of 0.76 and 0.81 on St using texture-based radiomics features at pre-IOI and event time-point, respectively. ConclusionsIn this analysis, the presence of a pre-IOI safety signal was detected in the form of textural heterogeneity within the vitreous compartment even prior to the actual event being identified by the investigator. This finding may help the clinicians to assess for underlying posterior inflammation.

Worsening of early DME after cataract surgery. The DICAT II Study report #2.

To analyse the long anatomical and functional outcome of a subgroup of the DICAT II study cohort, consisting of 26 patients undergoing cataract surgery and withdrawn from the study for a clinically significant worsening of early diabetic macular edema (DME). Patients who underwent cataract surgery and withdrawn from the DICAT II study for a clinically significant worsening of early DME with at least 12 months follow-up after the dropout. The study population was divided into two groups according to the clinical evaluation at one-year follow-up: ongoing treatment patients for DME (Treatment group, TG) and patients no longer treated (Non Treatment group, NTG). Central foveal thickness (CFT) at baseline and dropout time were higher in TG than in the NTG, with a statistically significant difference (p < 0.05). In addition, TG patients reported a higher levels of glycated hemoglobin at time baseline compared to NTG patients (7.81 ± 1.15 vs 7.02 ± 0.56; p = 0.048). The linear regression analysis demonstrated a statistically significant relationship between the visual acuity and the ongoing treatment group at one-year follow-up (p = 0.042). The study provides parameters to be considered when assessing the risk of developing persistent DME after cataract surgery in diabetic patients. In particular, CFT at baseline and dropout time have been reported to be an effective and predictable OCT biomarkers when evaluating DME progression. During the evaluation of the systemic disease, similar results were found for the glycated hemoglobin at baseline.

Prediction of postoperative visual acuity restoration in macula off rhegmatogenous retinal detachment using artificial intelligence

PurposeTo assess feasibility of automatic segmentation of OCT biomarkers of visual acuity (VA) and the possibility of prediction of postoperative VA after successful reattachment in macula off rhegmatogenous retinal detachment (RRD) eyes using artificial intelligence (AI). Designretrospective case control study MethodsPatients operated of pars plana vitrectomy (PPV) for macula-off non-traumatic RRD with available good quality OCT acquisitions were included. Ellipsoid zone(EZ) foveal damage and reflectivity, external limiting membrane(ELM) foveal damage, foveal flattening, outer nuclear layer(ONL) thickness and the presence of cysts and hyperreflective foci(HRFs) was assessed on preoperative OCT B scan images by both a trained segmenter and human graders. Different machine learning(ML)models were tested for detection of cases with VA>0.4 logMar at 6 months from surgery.Segmentation performance of the model was compared with ground truth segmentation provided by human graders. Postoperative VA prediction based on the segmented OCT biomarkers, preoperative VA and age was compared with actual postoperative VA to assess accuracy of the model. ResultsA total of 58 eyes of 58 patients were included. A significant difference in preoperative VA, foveal flattening, foveal EZ and ELM damage, EZ reflectivity and presence of HRF in the ONL was detected between groups(all p < 0.001).The segmenter showed good agreement with human assessment in both qualitative and quantitative variables. The Optimizable Naïve Bayes model was the best performing ML model and showed an accuracy of 86.2 % in detection of cases with postoperative VA>0.4 logMar. ConclusionsThe results confirm the prognostic relevance of EZ and ELM integrity and reflectivity, foveal flattening, ONL cysts and ONL HRF in macula off RRD, and, for the first time in literature, reports feasibility of the segmentation of these factors in preoperative OCT B scan images. We also report good classification performances of Naïve Bayes models based on OCT biomarkers, preoperative VA and age in distinguishing patients that should expect a postoperative VA>0.4 logMar at 6 months from surgery.

Enhancing Diabetic Macular Edema Treatment Outcomes: Exploring the ESASO Classification and Structural OCT Biomarkers.

This study assessed the European School of Advanced Studies in Ophthalmology (ESASO) classification's prognostic value for diabetic macular edema (DME) in predicting intravitreal therapy outcomes. In this retrospective, multicenter study, patients aged > 50years with type 1 or 2 diabetes and DME received intravitreal antivascular endothelial growth factor (anti-VEGF) agents (ranibizumab, bevacizumab, and aflibercept) or steroids (dexamethasone). The primary outcome was visual acuity (VA) change post-treatment, termed as functional response, measured 4-6weeks post-third anti-VEGF or 12-16weeks post-steroid injection, stratified by initial DME stage. Of the 560 eyes studied (62% male, mean age 66.7years), 31% were classified as stage 1 (early), 50% stage 2 (advanced), 17% stage 3 (severe), and 2% stage 4 (atrophic). Visual acuity (VA; decimal) improved by 0.12-0.15 decimals in stages 1-2 but only 0.03 decimal in stage 3 (all p < 0.0001) and 0.01 in stage 4 (p = 0.38). Even in eyes with low baseline VA ≤ 0.3, improvements were significant only in stages 1 and 2 (0.12 and 0.17 decimals, respectively). Central subfield thickness (CST) improvement was greatest in stage 3 (-229µm, 37.6%, p < 0.0001), but uncorrelated with VA gains, unlike stages 1 and 2 (respectively: -142µm, 27.4%; - 5µm, 12%; both p < 0.0001). Stage 4 showed no significant CST change. Baseline disorganization of retinal inner layers and focal damage of the ellipsoid zone/external limiting membrane did not influence VA improvement in stages 1 and 2. Treatment patterns varied, with 61% receiving anti-VEGF and 39% dexamethasone, influenced by DME stage, with no significant differences between therapeutic agents. The ESASO classification, which views the retina as a neurovascular unit and integrates multiple biomarkers, surpasses single biomarkers in predicting visual outcomes. Significant functional improvement occurred only in stages 1 and 2, suggesting reversible damage, whereas stages 3 and 4 likely reflect irreversible damage.

OCT Biomarkers and Visual Acuity in the Treatment of Diabetic Macular Edema

At baseline, visual acuity and the extent of vertical intraretinal fluid were predictive of better visual outcomes for 196 patients with diabetic macular edema who received tightly controlled treatment with 2mg intravitreal aflibercept injections.

Optical coherence tomography biomarkers indicating visual enhancement in diabetic macular edema resolved through anti-VEGF therapy: OCT biomarkers in resolved DME

Purposeto investigate the structural features and extended visual results in eyes affected by diabetic retinopathy (DR) and diabetic macular edema (DME) that have been successfully treated with anti-vascular endothelial growth factor (VEGF) therapy. MethodsIndividuals (39 eyes of 39 patients) who had undergone long-term follow-up and demonstrated evidence of resolved DME after at least 2 years of follow-up following the initiation of anti-VEGF therapy were included. During the ““study visit””, structural OCT scans were examined to assess qualitative features indicative of neuroretina or retinal pigment epithelium distress. Additionally, a quantitative assessment of the inner and outer retinal thicknesses was conducted for topographical analysis. ResultsThe most robust qualitative association observed with BCVA at the “study visit” was linked to the presence of DRIL (p = 0.043) and the appearance of the ELM. (p = 0.045). Regarding quantitative parameters, a strong correlation was noted between the visual acuity during the “study visit” and the foveal and parafoveal thicknesses of both the inner and outer retina (p < 0.001). ConclusionsChanges in the status of ELM, the presence of DRIL, and the thicknesses of the foveal and parafoveal regions can act as OCT biomarkers, signifying prolonged visual improvements in eyes that have experienced resolved DME after undergoing anti-VEGF therapy.

Visual acuity prediction on real-life patient data using a machine learning based multistage system

In ophthalmology, intravitreal operative medication therapy (IVOM) is a widespread treatment for diseases related to the age-related macular degeneration (AMD), the diabetic macular edema, as well as the retinal vein occlusion. However, in real-world settings, patients often suffer from loss of vision on time scales of years despite therapy, whereas the prediction of the visual acuity (VA) and the earliest possible detection of deterioration under real-life conditions is challenging due to heterogeneous and incomplete data. In this contribution, we present a workflow for the development of a research-compatible data corpus fusing different IT systems of the department of ophthalmology of a German maximum care hospital. The extensive data corpus allows predictive statements of the expected progression of a patient and his or her VA in each of the three diseases. For the disease AMD, we found out a significant deterioration of the visual acuity over time. Within our proposed multistage system, we subsequently classify the VA progression into the three groups of therapy “winners”, “stabilizers”, and “losers” (WSL classification scheme). Our OCT biomarker classification using an ensemble of deep neural networks results in a classification accuracy (F1-score) of over 98%, enabling us to complete incomplete OCT documentations while allowing us to exploit them for a more precise VA modelling process. Our VA prediction requires at least four VA examinations and optionally OCT biomarkers from the same time period to predict the VA progression within a forecasted time frame, whereas our prediction is currently restricted to IVOM/no therapy. We achieve a final prediction accuracy of 69% in macro average F1-score, while being in the same range as the ophthalmologists with 57.8 and 50±10.7\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$50 \\pm 10.7$$\\end{document}% F1-score.

Clinical and optical coherence tomography biomarkers as prognostic factors in dexamethasone intravitreal implant for diabetic macular edema.

Aim of the study was to evaluate the efficacy of dexamethasone (DEX) 0.7 mg intravitreal implant in patients with diabetic macular edema (DME) and serous retinal detachment (SRD), and to study the prognostic factors on a follow up of 12 months. Forty eyes of twenty- six patients with centre involving DME and SRD, who underwent DEX implant, were enrolled. Best-corrected visual acuity (BCVA), Swept source OCT imaging and intraocular pressure were evaluated. Central macular thickness (CMT), vitreomacular adhesion (VMA), disorganization of retinal inner layers (DRILs), hyperreflective dots (HRD), SRD and ellipsoid zone (EZ) disruption were included in the analysis at baseline and 12 months after implant. According to our parametric analysis, at 12 months, BVCA improvement from 48.6 ± 23.4 letters to 53.3 ± 24.5 letters was statistically significant (p = 0.04), CMT decreased from 460 ± 99.52 μm to 322.9 ± 117 μm. The presence at baseline of VMA (p = 0.01), EZ disruption (p = 0.03) and DRILs (p = 0.04), were associated with poor BCVA improvement at the end of follow-up. In conclusion, OCT biomarkers can be considered significant prognostic factors for treatment outcome in patients with DME undergoing DEX intravitreal implant.