Amy C. Cohn

Background: Reticular pseudodrusen (RPD) signify a critical phenotype driving vision loss in age‐related macular degeneration (AMD). This study sought to develop and externally test a deep learning (DL) model to detect RPD on optical coherence tomography (OCT) scans with expert‐level performance. Methods: RPD were manually segmented in 9800 OCT B‐scans from individuals enrolled in a multicentre randomised trial. A DL model for instance segmentation of RPD was developed and evaluated against four retinal specialists in an internal test dataset. The primary outcome was the performance of the DL model for detecting RPD in OCT volumes in five external test datasets compared to two retinal specialists. Results: In an internal test dataset consisting of 250 OCT B‐scans, the DL model produced RPD segmentations that had higher agreement with four retinal specialists (Dice similarity coefficient [DSC] = 0.76) than the agreement amongst the specialists (DSC = 0.68; p < 0.001). In the five external test datasets consisting of 1017 eyes from 812 individuals, the DL model detected RPD in OCT volumes with a similar level of performance as two retinal specialists (area under the receiver operator characteristic curve [AUC] = 0.94, 0.95 and 0.96 respectively; p ≥ 0.32). Conclusions: We present a DL model for automatic detection of RPD with expert‐level performance, which could be used to support the clinical management of AMD. This model has been made publicly available to facilitate future research to understand this critical, yet enigmatic, AMD phenotype.

As we move toward an era in which there will be treatment options for geographic atrophy (GA) secondary to age-related macular degeneration, the need to accurately understand and interpret multimodal imaging (MMI) for the condition is paramount. This review discusses the evolution of MMI in GA and how it has led to a greater understanding of different phenotypes and risk factors for progression. These advancements have allowed novel imaging biomarkers to be used as end points in large interventional studies exploring new therapies for GA treatment. Due to differences in drug approval timing, ophthalmologists in some jurisdictions are already treating patients with complement inhibiting intravitreal therapies and using MMI to guide management. Cementing knowledge of how GA appears on MMI and evolves over time will be vital for best practice as these interventions become more widely available.

To examine the association between treatment parameters and the progression to late age-related macular degeneration (AMD) in the Laser Intervention in Early Stages of Age-Related Macular Degeneration (LEAD) study, a randomized, controlled trial of a subthreshold nanosecond laser (SNL) for slowing disease progression in the early stages of AMD. The association between treatment parameters early in the trial period for participants in the SNL arm of the LEAD study and time to develop late AMD during the 3-year trial duration was examined. Parameters included treatment energy at the baseline and 6-month visits and the number of laser spots visible on fundus autofluorescence (FAF) imaging taken at 6 and 12 months (taken as a proxy measure of early, adequate delivery of the laser treatment at the baseline and 6-month visits, respectively). A multivariable analysis revealed there were no significant associations between time to develop late AMD and number of FAF-visible laser spots at 6-months (adjusted P = .537) nor laser energy used at baseline (adjusted P = .910). No significant associations were also observed when evaluating FAF-visible spots at 12-months (adjusted P = .107) and the average laser energy used at baseline and 6 months (adjusted P = .558). This study did not find any evidence to suggest that there was a dose response for the effect of laser treatment using these treatment parameters on the progression of AMD. [Ophthalmic Surg Lasers Imaging Retina. 2021;52:380–386.]

The presence of drusen is an important hallmark of age-related macular degeneration (AMD). Laser-induced regression of drusen, first observed over four decades ago, has led to much interest in the potential role of lasers in slowing the progression of the disease. In this article, we summarise the key insights from pre-clinical studies into the possible mechanisms of action of various laser interventions that result in beneficial changes in the retinal pigment epithelium/Bruch’s membrane/choriocapillaris interface. Key learnings from clinical trials of laser treatment in AMD are also summarised, concentrating on the evolution of laser technology towards short pulse, non-thermal delivery such as the nanosecond laser. The evolution in our understanding of AMD, through advances in multimodal imaging and functional testing, as well as ongoing investigation of key pathological mechanisms, have all helped to set the scene for further well-conducted randomised trials to further explore potential utility of the nanosecond and other subthreshold short pulse lasers in AMD.

The ophthalmic features are reported of a member of an Australian pedigree with three affected individuals spanning two generations with a hereditary endotheliopathy syndrome resulting in retinopathy, leukoencephalopathy and nephropathy. The index case initially presented with asymptomatic retinopathy, cerebral microvascular disease, nephropathy and raised inflammatory markers. The clinical, neuro‐radiological, biochemical and histopathological findings in this patient are consistent with a diagnosis of hereditary endotheliopathy, retinopathy, nephropathy and stroke (HERNS). Linkage analysis has identified a locus for HERNS on chromosome 3p21.1‐p21.3. This locus is shared with two other diseases: hereditary vascular retinopathy (HVR) and cerebroretinal vasculopathy (CRV). Although peripheral retinal involvement is a feature of HVR, it has not previously been described in HERNS. This case represents a novel phenotype of HERNS, and serves to blur the distinction between the vasculopathies mapping to chromosome 3p21. Although previously thought to be distinct clinical entities, it is possible that HERNS, HVR and CRV simply represent different phenotypes of the same disease. This will only be clarified with the identification of the gene or genes. This case also raises the question of how best to manage rare forms of vascular retinopathy.