Using Deep Learning to Segment Retinal Vascular Leakage and Occlusion in Retinal Vasculitis.

PURPOSE: Retinal vasculitis (RV) is characterised by retinal vascular leakage, occlusion or both on fluorescein angiography (FA). There is no standard scheme available to segment RV features. We aimed to develop a deep learning model to segment both vascular leakage and occlusion in RV. METHODS: Four hundred and sixty-three FA images from 82 patients with retinal vasculitis were used to develop a deep learning model, in 60:20:20 ratio for training:validation:testing. Parameters, including deep learning architectures (DeeplabV3+, UNet++ and UNet), were altered to find the best binary segmentation model separately for retinal vascular leakage and occlusion, using a Dice score to determine the reliability of each model. RESULTS: Our best model for vascular leakage had a Dice score of 0.6279 (95% confidence interval (CI) 0.5584-0.6974). For occlusion, the best model achieved a Dice score of 0.6992 (95% CI 0.6109-0.7874). CONCLUSION: Our RV segmentation models could perform reliable segmentation for retinal vascular leakage and occlusion in FAs of RV patients.

Microbial keratitis in Southern Malawi: a microbiological pilot study.

OBJECTIVE: Microbial keratitis (MK) is a significant cause of blindness in sub-Saharan Africa. We investigated the feasibility of using a novel corneal impression membrane (CIM) for obtaining and processing samples by culture, PCR and whole-genome sequencing (WGS) in patients presenting with suspected MK in Malawi. METHODS AND ANALYSIS: Samples were collected from patients presenting with suspected MK using a 12 mm diameter polytetrafluoroethylene CIM disc. Samples were processed using culture and PCR for Acanthamoeba, herpes simplex virus type 1 (HSV-1) and the bacterial 16S rRNA gene. Minimum inhibitory concentrations of isolates to eight antimicrobials were measured using susceptibility strips. WGS was used to characterise Staphylococcus aureus isolates. RESULTS: 71 eyes of 71 patients were included. The overall CIM isolation rate was 81.7% (58 positive samples from 71 participants). 69 (81.2%) of isolates were Gram-positive cocci. Coagulase-negative Staphylococcus 31.8% and Streptococcus species 14.1% were the most isolated bacteria. Seven (9.9%) participants were positive for HSV-1. Fungi and Acanthamoeba were not detected. Moxifloxacin and chloramphenicol offered the best coverage for both Gram-positive and Gram-negative isolates when susceptibility was determined using known antimicrobial first quartile concentrations and European Committee on Antimicrobial Susceptibility Testing breakpoints, respectively. WGS identified known virulence genes associated with S. aureus keratitis. CONCLUSIONS: In a resource-poor setting, a CIM can be used to safely sample the cornea in patients presenting with suspected MK, enabling identification of causative microorganisms by culture and PCR. Although the microbiological spectrum found was limited to the dry season, these preliminary results could be used to guide empirical treatment.

Adalimumab vs placebo as add-on to Standard Therapy for autoimmune Uveitis: Tolerability, Effectiveness and cost-effectiveness-a protocol for a randomised controlled trial (ASTUTE trial).

INTRODUCTION: Adalimumab is an effective treatment for autoimmune non-infectious uveitis (ANIU), but it is currently only funded for a minority of patients with ANIU in the UK as it is restricted by the National Institute for Health and Care Excellence guidance. Ophthalmologists believe that adalimumab may be effective in a wider range of patients. The Adalimumab vs placebo as add-on to Standard Therapy for autoimmune Uveitis: Tolerability, Effectiveness and cost-effectiveness (ASTUTE) trial will recruit patients with ANIU who do and do not meet funding criteria and will evaluate the effectiveness and cost-effectiveness of adalimumab versus placebo as an add-on therapy to standard care. METHODS AND ANALYSIS: The ASTUTE trial is a multicentre, parallel-group, placebo-controlled, pragmatic randomised controlled trial with a 16-week treatment run-in (TRI). At the end of the TRI, only responders will be randomised (1:1) to 40 mg adalimumab or placebo (both are the study investigational medicinal product) self-administered fortnightly by subcutaneous injection. The target sample size is 174 randomised participants. The primary outcome is time to treatment failure (TF), a composite of signs indicative of active ANIU. Secondary outcomes include individual TF components, retinal morphology, adverse events, health-related quality of life, patient-reported side effects and visual function, best-corrected visual acuity, employment status and resource use. In the event of TF, open-label drug treatment will be restarted as per TRI for 16 weeks, and if a participant responds again, allocation will be switched without unmasking and treatment with investigational medicinal product restarted. ETHICS AND DISSEMINATION: The trial received Research Ethics Committee (REC) approval from South Central - Oxford B REC in June 2020. The findings will be presented at international meetings, by peer-reviewed publications and through patient organisations and newsletters to patients, where available. TRIAL REGISTRATION: ISRCTN31474800. Registered 14 April 2020.

Proposing a Neurotropic Etiology for Acute Posterior Multifocal Placoid Pigment Epitheliopathy and Relentless Placoid Chorioretinitis.

Purpose: To reassess the underlying pathophysiology of acute posterior multifocal placoid pigment epitheliopathy (APMPPE) and relentless placoid chorioretinitis (RPC) through comparison with the non-inoculated eye of the von Szily animal model of neurotropic viral retinal infection. Methods: Narrative review. Results: Literature reports of isolated neurotropic viral entities and rising serological viral titers in APMPPE after presentation support a potential direct infective etiology. In general, viral transport along axons results in mitochondrial stasis and disruption of axoplasmic flow. Clinical manifestations of axoplasmic flow disruption in APMPPE/RPC may signify the passage of virus along the neuronal pathway. From a case series of 11 patients, we demonstrate a timely, spatial, and proportional association of optic disc swelling with APMPPE lesion occurrence. Signs within the inner retina appear to precede outer retinal lesions; and acute areas of outer nuclear layer (ONL) hyperreflectivity appear to be the result of coalescence of multiple hyperreflective foci resembling axonal spheroids (which occur as a consequence of axoplasmic disruption) and follow the Henle fiber layer neurons. Underlying areas of retinal pigment epithelium (RPE) hyper-autofluorescence follow ONL hyperreflectivity and may signify localized infection. Areas of apparent choriocapillaris hypoperfusion mirror areas of RPE/Bruch's membrane separation and appear secondary to tractional forces above. Increases in choroidal thickness with lesion occurrence and focal areas of choriocapillaris hypoperfusion are observed in both APMPPE/RPC and the von Szily model. Conclusions: The neurotrophic infection model provides significant advantages over the existing primary choriocapillaris ischemia hypothesis to account for the range of imaging signs observed in APMPPE and RPC.