Thrombolytic Therapy for Central Retinal Artery Occlusion in an Academic Multi-Site Stroke Centre.

Central retinal artery occlusion (CRAO) is a subtype of acute ischaemic stroke leading to severe visual loss. A recent American Heart Association scientific statement proposed time-windows for thrombolysis in CRAO similar to acute ischaemic cerebral strokes. We aimed to review our academic multi-site stroke centre experience with intravenous (IVT) and intra-arterial thrombolysis (IAT) in CRAO between 1997 and 2022. Demographic, clinical characteristics, thrombolysis timeline, concurrent therapies, complications, and 3-month follow-up visual acuity (VA) were collected. The thrombolysed cohort follow-up VA was compared with an age, gender and baseline VA matched cohort of CRAO patients that received conservative therapies. Thrombolytic therapy was administered to 3.55% (n = 20) of CRAO admissions; 13 IVT (mean age 68, 61.5% male, 12 alteplase and 1 tenecteplase, all embolic aetiology, 1 CRAO mimic) and 7 IAT (mean age 55, 85.7% male, 3 post-operative and 3 embolic). Additional conservative CRAO-targeting therapies was received by 60%. The median time from onset of visual loss to IVT was 158 minutes (range 67-260). Improvement by at least two Snellen lines was achieved by 25% with 12.5% improving to 20/100 or better. Intracranial haemorrhage post IVT occurred in 1/13 (7.6%). The median time from onset of visual loss to IAT was 335 minutes. Improvement by at least two Snellen lines was achieved by 42%. No difference in 3-month VA was noted between patients that received thrombolysis, either alone (n = 8) or combined with other therapies, and those that received conservative therapies. Our results suggest that the management of acute CRAO remains heterogeneous. The lack of obvious benefit of thrombolysis in our small series supports the need for randomizsd clinical trials comparing thrombolysis to placebo to guide hyperacute CRAO management.

OTRE: Where Optimal Transport Guided Unpaired Image-to-Image Translation Meets Regularization by Enhancing.

Non-mydriatic retinal color fundus photography (CFP) is widely available due to the advantage of not requiring pupillary dilation, however, is prone to poor quality due to operators, systemic imperfections, or patient-related causes. Optimal retinal image quality is mandated for accurate medical diagnoses and automated analyses. Herein, we leveraged the Optimal Transport (OT) theory to propose an unpaired image-to-image translation scheme for mapping low-quality retinal CFPs to high-quality counterparts. Furthermore, to improve the flexibility, robustness, and applicability of our image enhancement pipeline in the clinical practice, we generalized a state-of-the-art model-based image reconstruction method, regularization by denoising, by plugging in priors learned by our OT-guided image-to-image translation network. We named it as regularization by enhancing (RE). We validated the integrated framework, OTRE, on three publicly available retinal image datasets by assessing the quality after enhancement and their performance on various downstream tasks, including diabetic retinopathy grading, vessel segmentation, and diabetic lesion segmentation. The experimental results demonstrated the superiority of our proposed framework over some state-of-the-art unsupervised competitors and a state-of-the-art supervised method.