Herein are reported four eyes among three patients with favorable anti-vascular endothelial growth factor crunch syndrome by which contraction of fibrovascular tissue led to relief of vitreoretinal traction without surgical intervention. This phenomenon led to complete or partial retinal reattachment in two patients with diabetic tractional retinal detachments. These cases represent favorable anatomic outcomes of crunch syndrome secondary to anti-vascular endothelial growth factor pharmacotherapy and are unique compared with most cases, which have been associated with negative outcomes. [ Ophthalmic Surg Lasers Imaging Retina 2022;53:455–459.]

Purpose: To present a case of Valsalva retinopathy occurring after yoga in a patient without a clear predisposing condition. Methods: A retrospective chart review was performed. Results: A 36-year-old woman presented with a 2-day history of a “blob,” hazy vision, and floaters in her left eye. She was performing a backbend during yoga but denied being in a headstand position. The visual acuity (VA) was 20/20−2 OS. Ophthalmoscopy showed a retinal hemorrhage inferior to the optic disc in the left eye, which was confirmed on imaging. One month later, ophthalmoscopy and imaging showed almost complete resolution of the hemorrhage with a VA of 20/20+2 OS. Conclusions: This case of Valsalva retinopathy did not involve a predisposing condition, headstand positioning, or breathing exercises. Therefore, when clinicians encounter young, healthy patients with Valsalva retinopathy, they should consider exposures to activities such as yoga as potential risk factors.

In this paper, we propose a novel selection strategy for contrastive learning for medical images. On natural images, contrastive learning uses augmentations to select positive and negative pairs for the contrastive loss. However, in the medical domain, arbitrary augmentations have the potential to distort small localized regions that contain the biomarkers we are interested in detecting. A more intuitive approach is to select samples with similar disease severity characteristics, since these samples are more likely to have similar structures related to the progression of a disease. To enable this, we introduce a method that generates disease severity labels for unlabeled OCT scans on the basis of gradient responses from an anomaly detection algorithm. These labels are used to train a supervised contrastive learning setup to improve biomarker classification accuracy by as much as 6% above self-supervised baselines for key indicators of Diabetic Retinopathy.

There is limited data on the presentation and surgical outcomes of idiopathic macular holes (IMH) for different ethnic and racial groups. Recognition of distinct, clinically-relevant patient subgroups may provide opportunities to identify specific unmet needs including possible barriers to optimal healthcare delivery. Medical records of patients who underwent surgery for IMH (between 2016 and 2022) at a large, urban retina practice were reviewed and self-reported ethnicity (Hispanic and non-Hispanic) and race (Asian, Black, White, and Other) were captured. The primary variables included (1) mean minimum linear diameter (MLD) at presentation and (2) surgical outcome (IMH closure status). Overall, mean MLD for all study eyes (515) was 366.1 μm, and surgical success was achieved in 489 (95.0%) eyes. Hispanic eyes presented with larger mean MLD (p = 0.002) compared to non-Hispanic eyes. Asian, Black, and Other eyes presented with larger mean MLD (p = 0.033, p < 0.001, p < 0.001) when compared to White eyes. The presentation of IMH varied in severity among different ethnic and racial groups. Hispanic patients were found to have worse preoperative visual acuity (VA), longer time to surgery, and larger mean MLD and BD compared to non-Hispanic participants. Black and Other patients were found to have worse VA, time to surgery, and larger mean MLD and BD when compared to White participants.

No abstract