iERM: An Interpretable Deep Learning System to Classify Epiretinal Membrane for Different Optical Coherence Tomography Devices: A Multi-Center Analysis.

Background: Epiretinal membranes (ERM) have been found to be common among individuals >50 years old. However, the severity grading assessment for ERM based on optical coherence tomography (OCT) images has remained a challenge due to lacking reliable and interpretable analysis methods. Thus, this study aimed to develop a two-stage deep learning (DL) system named iERM to provide accurate automatic grading of ERM for clinical practice. Methods: The iERM was trained based on human segmentation of key features to improve classification performance and simultaneously provide interpretability to the classification results. We developed and tested iERM using a total of 4547 OCT B-Scans of four different commercial OCT devices that were collected from nine international medical centers. Results: As per the results, the integrated network effectively improved the grading performance by 1−5.9% compared with the traditional classification DL model and achieved high accuracy scores of 82.9%, 87.0%, and 79.4% in the internal test dataset and two external test datasets, respectively. This is comparable to retinal specialists whose average accuracy scores are 87.8% and 79.4% in two external test datasets. Conclusion: This study proved to be a benchmark method to improve the performance and enhance the interpretability of the traditional DL model with the implementation of segmentation based on prior human knowledge. It may have the potential to provide precise guidance for ERM diagnosis and treatment.

Acute Atypical Endophthalmitis Following Intravitreal Sustained-release Dexamethasone Implant: A Case Series.

PURPOSE: To present three cases of acute endophthalmitis following intravitreal sustained-release dexamethasone (Ozurdex®) with atypical presentation and to discuss the management of these patients. METHODS: A retrospective case series of three patients with endophthalmitis following intravitreal sustained-release dexamethasone (Ozurdex®) implantation who presented between July 2020 to August 2020. RESULTS: Two out of three patients who were treated with topical steroid and antibiotic therapy alone showed favorable outcomes and were managed without the need for intravitreal antibiotics or implant removal. One patient who showed initial response to topical therapy subsequently required pars plana vitrectomy, implant removal and a single empirical dose of intra-vitreal antibiotics and anti-fungal agent due to persistent inflammation. CONCLUSION: Post intravitreal Ozurdex® endophthalmitis although a rare entity can present with atypical features of a painless white eye and a delayed onset intraocular inflammation. Although all cases of endophthalmitis should be treated as infective until proven otherwise, it is fair to consider a trial of conservative treatment with topical steroids and antibiotics initially with close monitoring. In cases with poor response to topical therapy, pars planar vitrectomy and implant removal should be strongly considered.

Treatment outcome in patients with presumed tubercular uveitis at a tertiary referral eye care centre in Singapore.

AIM: To report the clinical features and outcome of patients with presumed tubercular uveitis (TBU). METHODS: Retrospective analysis of patients with presumed TBU at a tertiary referral eye care centre in Singapore between 2007 and 2012 was done. Main outcome measures were failure of complete resolution of uveitis or recurrence of inflammation. RESULTS: Fifty three patients with mean age of 44.18 ± 15.26 years with 54.72% being males were included. 19 (35.85%) had bilateral involvement, with panuveitis and anterior uveitis being the most common presentations. 36 (67.92%) patients received antitubercular therapy (ATT), and 28 received concurrent systemic steroids. 15 (28.30%) eyes of 11 (30.55%) patients in the ATT group and 4 (21.05%) eyes of 3 (17.64%) patients in the non-ATT group had treatment failure (p value = 0.51). CONCLUSION: The use of ATT, with or without concurrent corticosteroid, may not have a statistically significant impact in improving treatment success in patients with presumed TBU.

Immune recovery uveitis in HIV patients with cytomegalovirus retinitis in the era of HAART therapy-a 5-year study from Singapore.

BACKGROUND: The aim of this study is to analyse the clinical features of HIV patients with cytomegalovirus retinitis (CMVR) developing immune recovery uveitis (IRU) while on highly active antiretroviral therapy (HAART) and to identify the risk factors, visual outcomes and complications of IRU. RESULTS: Majority (n = 26, 86.7 %) of patients were male, with 76.7 % (n = 23) of patients having bilateral disease. Twenty-seven eyes (50.9 %) had both anterior uveitis and vitritis. The median CD4 at IRU was 210 cells/µL (IQR 140-279), with 86.7 % having CD4 >100 cells/µL. The median duration from initiation of HAART to IRU was significantly different between those <50 years old (median 763 days, IQR 174-1872 days) and those ≥50 years old (median 161 days, IQR 84.5-278 days). Fourteen eyes (26.4 %) had loss of one or more Snellen lines visual acuity at 6 months while the rest maintained or improved vision. Complications developed in 21 eyes, with cataract (66.7 %), glaucoma and ocular hypertension (33.3 %) being the most common. The risk of complications was associated with the absolute difference in CD4 counts at IRU and at HAART commencement (p = 0.041). Age was also negatively associated with the duration from HAART to IRU (p = 0.005, Spearman's rho coefficient = -0.503). CONCLUSIONS: It is common to have both anterior uveitis and vitritis in IRU. There was a positive association between the increase in CD4 from HIV to IRU diagnoses and the risk of developing complications. Younger patients appeared to develop IRU later than older patients after HAART, suggesting that long-term follow-ups are essential for these patients.

Discrepancies in assessing anterior chamber activity among uveitis specialists.

PURPOSE: To evaluate current practices in anterior chamber (AC) inflammation assessment among uveitis specialists. METHODS: Uveitis specialists were invited to participate in an electronic survey designed to understand their practice in assessing AC inflammation. RESULTS: Sixty-five ophthalmologists participated in the survey. Of them, 69.2 % (n = 45) reported using the current Standardization of Uveitis Nomenclature (SUN) guidelines of a 1 × 1-mm slit beam when grading AC cells. Only 38.5 % (n = 5) reported routinely counting the number of cells. In the management of uveitis, 98.5 % (n = 64) valued flare assessment, but 84.6 % (n = 55) did not use laser flare photometry. In total, 36.9 % (n = 24) agreed that laser flare photometry would change their management, while 16.9 % (n = 11) did not see its usefulness. The remaining participants were undecided. CONCLUSION: A number of issues limit the clinical assessment of AC inflammation. Different classifications are still being used despite efforts to standardize practice. While the value of flare is widely recognized, the role of laser flare photometry remains controversial.