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

BACKGROUND: In optical coherence tomography (OCT) scans of patients with inherited retinal diseases (IRDs), the measurement of the thickness of the outer nuclear layer (ONL) has been well established as a surrogate marker for photoreceptor preservation. Current automatic segmentation tools fail in OCT segmentation in IRDs, and manual segmentation is time-consuming. METHODS AND MATERIAL: Patients with IRD and an available OCT scan were screened for the present study. Additionally, OCT scans of patients without retinal disease were included to provide training data for artificial intelligence (AI). We trained a U-net-based model on healthy patients and applied a domain adaption technique to the IRD patients' scans. RESULTS: We established an AI-based image segmentation algorithm that reliably segments the ONL in OCT scans of IRD patients. In a test dataset, the dice score of the algorithm was 98.7%. Furthermore, we generated thickness maps of the full retinal thickness and the ONL layer for each patient. CONCLUSION: Accurate segmentation of anatomical layers on OCT scans plays a crucial role for predictive models linking retinal structure to visual function. Our algorithm for segmentation of OCT images could provide the basis for further studies on IRDs.

Long-term ocular damage after recovery from COVID-19: lack of evidence at three months.

IMPORTANCE: A small number of COVID-19 patients has been reported to suffer from acute keratoconjunctivitis. In very rare cases, acute inflammatory retinal vein occlusion, papillophlebitis or retinopathy have been observed. OBJECTIVE: To determine possible long-term effects on the eye, especially on the retina, in patients who had suffered from COVID-19 at least 3 months after recovery. DESIGN: Prospective cross-sectional study. SETTING: Hospital of the Ludwig Maximilians University, Munich. PARTICIPANTS: Patients who had been tested positive for SARS-CoV-2 or for anti-SARS-CoV-2 IgG serum antibodies in the Hospital of the Ludwig Maximilians University, Munich between May and September. METHODS: Patients who had tested positive were either hospitalized or discharged into home quarantine via the emergency room. Three months after recovery, they were invited to participate voluntarily for this study during their follow-up in our clinic. A complete ophthalmological exam including functional and imaging end points (including optical coherence tomography (OCT), OCT angiography) was performed. MAIN OUTCOMES AND MEASURES: Visual acuity, slit lamp, bio microscopy and fundoscopy, multimodal imaging findings. RESULTS: In total, 21 patients were examined. The mean age (SD) of the patients was 48.7 (18.3) years. Of these, 14 (66.6%) were hospitalized and 7 (33.3) were discharged home. Two hospitalized patients (9.5%) received invasive ventilation. During the infection, 14 of the 21 patients (66.6%) were in regular care whereas 2 patients (9.5%) received intensive care ventilation for 8.5 (SD) (0.7) days on average in the COVID ICU. Ophthalmological examination of the previously hospitalized group took place 111.4 (23.2) days after recovery and discharge from the hospital, while non-hospitalized patients were examined after mean 123.4 (44.7) days. All patients showed normal findings for anterior and posterior segment of both eyes. OCT and OCT-A showed no evidence of retinal damage, or vascular or microvascular events. CONCLUSION AND RELEVANCE: This study with a small prospective cohort of 21 patients indicates that there might be no evidence of ocular complications at 3 months after recovery from COVID-19, without previous eye involvement. Further studies with more participants with and without acute ocular symptoms are necessary for final evidence.

COMPLIANCE AND ADHERENCE OF PATIENTS WITH DIABETIC MACULAR EDEMA TO INTRAVITREAL ANTI-VASCULAR ENDOTHELIAL GROWTH FACTOR THERAPY IN DAILY PRACTICE.

PURPOSE: We assessed differences in compliance and adherence (lateness of patients, visual acuity, reasons for abstaining) between patients with diabetic macular edema (DME) and patients with age-related macular degeneration (AMD), both under anti-vascular endothelial growth factor therapy. METHODS: We included 136 patients with DME (36% women, 65 years, 22 visits, 13.9 injections, and 29.9 months of follow-up) and 109 patients with AMD (59% women, 76 years, 20 visits, 14.7 injections, and 22.3 months of follow-up) (minimum follow-up of 12 months and at least 5 injections). We assessed missed appointments (lateness >14 days) and therapy break-offs (lateness >100 days). All delayed patients were called and interviewed for abstaining reasons. RESULTS: Forty-six percent of patients with DME and 22% of patients with AMD had at least one break-off. Thirty-five percent of patients with DME and 50% of patients with AMD were always on schedule. In patients with DME, there was significant correlation (P = 0.017) between the number of break-offs and change of visual acuity. In 60% DME and 38% AMD of break-off cases, visual acuity was worse than the before break-off. The most common reason for abstaining was comorbidities (33% AMD and 20% DME). CONCLUSION: There are significant differences between patients with AMD and DME regarding compliance and adherence, which also affects outcome. Strategies to tie patients with DME to costly intravitreal therapy need to be developed to improve outcomes and efficacy.

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

OBJECTIVES: To 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). METHODS: Training 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. RESULTS: High 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. CONCLUSIONS: The 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.

Optical coherence tomography-based misdiagnosis and morphological distinction in pachychoroid neovasculopathy vs. polypoidal choroidal vasculopathy.

PURPOSE: To evaluate the rate of misdiagnosis of aneurysmatic pachychoroid type 1 choroidal neovascularization/polypoidal choroidal vasculopathy (PAT1/PCV) among cases diagnosed as non-aneurysmatic pachychoroid neovasculopathy (PNV) and to define optical coherence tomography (OCT) features facilitating their distinction. METHODS: The database of the Department of Ophthalmology, Ludwig-Maximilians University Munich, was screened for patients diagnosed with PNV. Multimodal imaging was screened for the presence of choroidal neovascularization (CNV) and aneurysms/polyps. Imaging features facilitating the diagnosis of PAT1/PCV were analysed. RESULTS: In total, 49 eyes of 44 patients with a clinical PNV diagnosis were included, of which 42 (85.7%) had PNV and 7 (14.3%) represented misdiagnosed PAT1/PCV. SFCT was comparable (PNV: 377 ± 92 vs. PAT1/PCV: 400 ± 83 µm; p = 0.39). Whereas no difference was detected in total pigment epithelium detachment (PED) diameter (p = 0.46), maximum PED height was significantly higher in the PAT1/PCV group (199 ± 31 vs. 82 ± 46, p < 0.00001). In a receiver operating characteristic (ROC) analysis, the optimum cutoff for defining "peaking PED" was 158 µm with an area under the curve of 0.969, a sensitivity of 1.0 (95% CI: 0.59-1.0), and a specificity of 0.95 (95% CI: 0.84-0.99). Sub-retinal hyperreflective material (SHRM; p = 0.04), sub-retinal ring-like structures (SRRLS; p < 0.00001), and sub-RPE fluid (p = 0.04) were significantly more frequent in eyes with PAT1/PCV. CONCLUSION: A relevant percentage of eyes diagnosed with PNV might instead suffer from PAT1/PCV. The detection of a maximum PED height ("peaking PED") exceeding approximately 150 µm, SHRM, SRRLS, and sub-RPE fluid might greatly aid in the production of a more accurate diagnosis.

Reconstructing disease dynamics for mechanistic insights and clinical benefit.

Diseases change over time, both phenotypically and in their underlying molecular processes. Though understanding disease progression dynamics is critical for diagnostics and treatment, capturing these dynamics is difficult due to their complexity and the high heterogeneity in disease development between individuals. We present TimeAx, an algorithm which builds a comparative framework for capturing disease dynamics using high-dimensional, short time-series data. We demonstrate the utility of TimeAx by studying disease progression dynamics for multiple diseases and data types. Notably, for urothelial bladder cancer tumorigenesis, we identify a stromal pro-invasion point on the disease progression axis, characterized by massive immune cell infiltration to the tumor microenvironment and increased mortality. Moreover, the continuous TimeAx model differentiates between early and late tumors within the same tumor subtype, uncovering molecular transitions and potential targetable pathways. Overall, we present a powerful approach for studying disease progression dynamics-providing improved molecular interpretability and clinical benefits for patient stratification and outcome prediction.

Two Year Visual Acuity and Structural Outcomes in Patients with Diabetic Macular Oedema Treated with Intravitreal Aflibercept - A Retrospective Cohort Study.

PURPOSE: To assess visual and anatomical outcomes of intravitreal aflibercept for clinically significant diabetic macular oedema (DME). METHODS: For this retrospective single-center cohort study at a tertiary referral center, we performed a data warehouse query to identify 117 treatment-naive patients (139 eyes) undergoing intravitreal treatment with aflibercept for DME between January 2014 and May 2018. Changes in best-corrected visual acuity (BCVA) values (as measured with ETDRS letters), central retinal thickness (CRT) and total macular volume (TVOL) are reported over a two-year period at various time-points. RESULTS: The total number of injections per study eye was 5.5 ± 1.4 after one and 8.7 ± 2.2 injections after two years. Baseline visual acuity (VA) was 60.1 ± 14.5 letters. A gain of 4.8 and 9.2 letters from baseline was observed after one and two years, respectively (both p ≤ 0.01). In comparison to the mean CRT at baseline (419 ± 174 µm), a CRT decrease was observed after one and two years of treatment (298 ± 115 µm and 319 ± 119 µm, respectively; both p ≤ 0.01). Similarly, TVOL decreased from 10.12 ± 2.05 mm3 to 8.96 ± 0.96 mm3 and 9.01 ± 1.29 mm3 (both p ≤ 0.01). CONCLUSION: This study demonstrates that treating DME with intravitreal aflibercept yields positive functional and structural outcomes over a two-year period. However, we observed fewer injection numbers, along with inferior VA and structural outcomes than has been reported in randomized clinical trials. Our results show similar results as in patients treated with ranibizumab due to DME in real-life settings.

Gender-related differences in patients treated with intravitreal anti-vascular endothelial growth factor medication for diabetic macular oedema.

BACKGROUND: Diabetes prevalence is constantly rising, involving the eyes with damage including development of diabetic macular oedema. Since 2012, intravitreal anti-vascular endothelial growth factor medication is available for diabetic macular oedema treatment. Endocrinological studies have shown that fewer women are affected by diabetes. However, when affected, they exhibit more severe diabetic complications than men. We have investigated gender-related differences in diabetic macular oedema and outcome in an ophthalmological tertiary referral hospital. METHODS: We included 88 patients (54 males and 34 females) with 112 eyes (68 male and 44 female) having clinically significant diabetic macular oedema, treated with anti-vascular endothelial growth factor medication. A 1 year follow-up was performed in all patients (visual acuity and optical coherence tomography). Previous retinal surgery was an exclusion criterion, as were other retinal pathologies. RESULTS: The mean visual acuity and mean central retinal thickness at baseline were 0.53 logMAR (male 0.49 and female 0.595) and 469 µm (male 452 µm and female: 494 µm), respectively. After 360 days, mean visual acuity changed by -0.07 (±0.36) logMAR (male -0.11 and female +0.01) and mean central retinal thickness changed by -119 µm (male -113 µm and female -127 µm). For visual acuity, a significant difference was noted at baseline (p = 0.02) and at 1 year (p < 0.001). Males received 5.6 injections and females received 5.68 injections in 1 year. CONCLUSION: Our study showed that female patients with diabetic macular oedema were diagnosed with and treated for diabetic macular oedema at a stage when visual acuity and optical coherence tomography were worse than those in their male counterparts. This gender difference could not be reduced, despite similar numbers of injections. Female diabetic patients should therefore be assessed early for ophthalmological pathologies.