RESUMO
Introduction: Ipilimumab and nivolumab are checkpoint inhibitors that are known to cause a multitude of inflammatory ocular adverse events. Here we report a patient with poliosis and symptomatic depigmentation of the choroid and retinal pigment epithelium (RPE) associated with checkpoint inhibitor therapy for cutaneous melanoma. Case Presentation: The patient presented with floaters in both eyes and concerns for intraocular metastases of metastatic cutaneous melanoma after 1 month of therapy with ipilimumab and nivolumab. External examination revealed poliosis of her eyebrows and eyelashes. Fundus photography demonstrated multiple 1-3 disc-diameter hypopigmented placoid flat areas in the RPE/choroid exposing underlying choroidal vessels in both eyes. At subsequent evaluation 7 months later (after an additional 6 months of checkpoint inhibitor therapy), the lesions appeared more blanched. Evaluation nearly 20 months after the initial presentation showed no significant changes from her prior visit despite cessation of checkpoint inhibitor therapy for 13 months. Conclusion: Checkpoint inhibitor therapy for cutaneous melanoma metastases can cause depigmentation of the choroid and RPE that must be differentiated from progression of intraocular melanoma.
RESUMO
Purpose: To investigate the association between demographic, socioeconomic, and clinical factors and severe vision loss in patients with neovascular glaucoma (NVG). Patients and Methods: A retrospective chart review of patients referred to the University of Virginia (UVA), diagnosed with NVG, and treated for NVG between January 2010 and December 2020 was performed. Patients were grouped according to vision outcomes after 1 year of treatment: mild - moderate vision loss (best corrected visual acuity [BCVA] > light perception [LP]) and severe vision loss (BCVA ≤ LP). The associations between patient characteristics and BCVA were also examined. Results: Of the 89 patients (99 eyes), those with progression to severe vision loss presented with higher intraocular pressure (IOP) (p < 0.001) and lower visual acuity (p = 0.003) on average. However, there was no difference in IOP between the vision loss groups after one year of treatment. Univariate analysis showed a moderate association between a history of type 2 diabetes mellitus (T2DM) and severe vision loss (p = 0.033). Increasing age was associated with an increased likelihood of progression to severe vision loss (odds ratio [OR] 1.074, p = 0.008). Females were more likely to exhibit severe vision loss (OR 3.281, p = 0.036). Patients with Medicare (OR 0.098, p = 0.005) or private insurance (OR 0.110, p = 0.006) were less likely to progress to severe vision loss than those without insurance. Conclusion: Progression of vision loss in patients with NVG may be influenced by the stage of disease at diagnosis, age, sex, T2DM, and insurance status.
RESUMO
Purpose: There is great promise in use of machine learning (ML) for the diagnosis, prognosis, and treatment of various medical conditions in ophthalmology and beyond. Applications of ML for ocular neoplasms are in early development and this review synthesizes the current state of ML in ocular oncology. Methods: We queried PubMed and Web of Science and evaluated 804 publications, excluding nonhuman studies. Metrics on ML algorithm performance were collected and the Prediction model study Risk Of Bias ASsessment Tool was used to evaluate bias. We report the results of 63 unique studies. Results: Research regarding ML applications to intraocular cancers has leveraged multiple algorithms and data sources. Convolutional neural networks (CNNs) were one of the most commonly used ML algorithms and most work has focused on uveal melanoma and retinoblastoma. The majority of ML models discussed here were developed for diagnosis and prognosis. Algorithms for diagnosis primarily leveraged imaging (e.g., optical coherence tomography) as inputs, whereas those for prognosis leveraged combinations of gene expression, tumor characteristics, and patient demographics. Conclusions: ML has the potential to improve the management of intraocular cancers. Published ML models perform well, but were occasionally limited by small sample sizes owing to the low prevalence of intraocular cancers. This could be overcome with synthetic data enhancement and low-shot ML techniques. CNNs can be integrated into existing diagnostic workflows, while non-neural networks perform well in determining prognosis.
Assuntos
Melanoma , Neoplasias da Retina , Humanos , Aprendizado de Máquina , Redes Neurais de Computação , Melanoma/patologia , AlgoritmosRESUMO
PURPOSE: To describe the clinical response and safety profile of the novel HIF-2É inhibitor belzutifan in treating a giant retinal hemangioblastoma (RHB) with extrascleral extension associated with von Hippel-Lindau syndrome (VHL). METHODS: A 71-year-old woman with VHL presented with a giant RHB with extrascleral extension in her only remaining eye. She had no light perception OD and intraocular pressure (IOP) was 48. She requested enucleation due to chronic pain, but, due to concern for significant bleeding given the size of the neoplasm, a trial of belzutifan was initiated. RESULTS: Within three months of treatment initiation, the patient reported an 80% reduction in pain. MRI showed 30% reduction in longest tumor diameter. Dose adjustments were guided by serum hemoglobin levels, allowing the patient to remain on the medication for over a year with continued tumor regression on MRI and avoid enucleation. CONCLUSION: RHB with extrascleral extension is exceedingly rare and its treatment is complex, often requiring enucleation or external beam radiotherapy. This report demonstrates the use of belzutifan to safely and successfully reduce ocular tumor burden of complicated RHB with extrascleral extension, ultimately decreasing the need for enucleation.