Background/aimsHuman grading of digital images from diabetic retinopathy (DR) screening programmes represents a significant challenge, due to the increasing prevalence of diabetes. We evaluate the performance of an automated artificial intelligence (AI) algorithm to triage retinal images from the English Diabetic Eye Screening Programme (DESP) into test-positive/technical failure versus test-negative, using human grading following a standard national protocol as the reference standard.MethodsRetinal images from 30 405 consecutive screening episodes from three English DESPs were manually graded following a standard national protocol and by an automated process with machine learning enabled software, EyeArt v2.1. Screening performance (sensitivity, specificity) and diagnostic accuracy (95% CIs) were determined using human grades as the reference standard.ResultsSensitivity (95% CIs) of EyeArt was 95.7% (94.8% to 96.5%) for referable retinopathy (human graded ungradable, referable maculopathy, moderate-to-severe non-proliferative or proliferative). This comprises sensitivities of 98.3% (97.3% to 98.9%) for mild-to-moderate non-proliferative retinopathy with referable maculopathy, 100% (98.7%,100%) for moderate-to-severe non-proliferative retinopathy and 100% (97.9%,100%) for proliferative disease. EyeArt agreed with the human grade of no retinopathy (specificity) in 68% (67% to 69%), with a specificity of 54.0% (53.4% to 54.5%) when combined with non-referable retinopathy.ConclusionThe algorithm demonstrated safe levels of sensitivity for high-risk retinopathy in a real-world screening service, with specificity that could halve the workload for human graders. AI machine learning and deep learning algorithms such as this can provide clinically equivalent, rapid detection of retinopathy, particularly in settings where a trained workforce is unavailable or where large-scale and rapid results are needed.

Invasive fungal sinusitis causes painful orbital apex syndrome with ophthalmoplegia and visual loss; the mechanism is unclear. We report an immunocompromised patient with invasive fungal sinusitis in whom the visual loss was due to posterior ischaemic optic neuropathy, shown on diffusion-weighted MRI, presumably from fungal invasion of small meningeal-based arteries at the orbital apex. After intensive antifungal drugs, orbital exenteration and immune reconstitution, the patient survived, but we were uncertain if the exenteration helped. We suggest that evidence of acute posterior ischaemic optic neuropathy should be a contra-indication to the need for orbital exenteration in invasive fungal sinusitis.

No abstract

Purpose: To present the first reported case of presumptive intraocular recurrence of lymphoma following Chimeric Antigen Receptor (CAR) T-cell therapy despite systemic control by CD19-CAR T cells.Methods: Observational case report.Results: A 59-year-old man with diffuse, large, B-cell lymphoma subsequently developed secondary central nervous system disease despite chemotherapy. He underwent stem cell transplantation but relapsed again and was scheduled to receive CAR T-cell therapy. He developed vitritis several weeks before treatment, with vitreous biopsy showing non-Hodgkin B-cell lymphoma. He received CAR T-cell therapy following the vitrectomy. He presented 3 months following CAR T-cell therapy with nonspecific right eye floaters and discomfort, with the optical coherence tomography revealing subretinal saw-tooth deposits in the right eye, highly suggestive of lymphoma. This is despite having good systemic control with no other disease elsewhere in the body. He received intravitreal methotrexate to good effect.Conclusion: To our knowledge, this is the first case of a vitreoretinal lymphoma nonresponsive to CAR T-cell therapy, despite good central nervous system and systemic control. This is suggestive of anti-CD19 CAR T cells not trafficking into the eye in sufficient numbers to eliminate CD19-expressing neoplastic B cells. We suggest regular ophthalmic follow-up after CAR-T-cell therapy for patients where there is evidence of ocular involvement.