Anna M. Stagner

Ophthalmic imaging has advanced to a level at which it can closely approximate key histopathological features of certain ocular tissues, changing the way ocular disease is screened for, diagnosed, and monitored. Modalities such as optical coherence tomography (OCT), anterior segment OCT (AS‐OCT), OCT angiography (OCTA), and in vivo confocal microscopy (IVCM) capture tissue architecture with high‐resolution structural and even microvascular information. In this review, the authors summarize the current evidence on artificial intelligence (AI) based applications that utilize high‐resolution ophthalmic imaging and digital pathology to support near‐histologic interpretation across a range of ocular diseases. Reported diagnostic performance and concordance with histopathologic findings are examined while describing the technical, biological, and regulatory boundaries of AI‐derived inference. While AI supports objective, scalable, and reproducible analyses of ophthalmic imaging data, limitations in resolution, generalizability, and specificity prevent its use as an independent substitute for tissue‐based diagnosis where histopathologic confirmation is required.

Purpose: This study’s purpose was to investigate the outcomes of immune checkpoint inhibitor (ICI) treatment of periocular cutaneous squamous cell carcinoma with orbital invasion. Methods: A retrospective review was performed of 19 patients with biopsy-confirmed, advanced periocular cutaneous squamous cell carcinoma with orbital invasion treated with ICIs at a single institution. Tumors of conjunctival, sinonasal, lacrimal sac, or indeterminate origin were excluded. Demographic and clinical features at presentation, duration (number of cycles) of ICI, and treatment response were analyzed. Results: Nineteen patients with periocular cutaneous squamous cell carcinoma with orbital invasion treated with ICI were identified. The median age at diagnosis was 74 (interquartile range, 67–78) years. Most patients were non-Hispanic White (95%, n=18) and male (68%, n=13). Eight patients (42%) had AJCC T4 disease. Median presenting logMAR visual acuity in the affected eye was 0.3 (0.2–0.8). Eighteen patients (95%) had orbital involvement, and 14 (74%) had perineural involvement. Thirteen (68%) were treated with cemiplimab and 5 (26%) with pembrolizumab, and 1 was transitioned to cemiplimab after progression on pembrolizumab. Patients received a median of 9 (interquartile range, 6–15) cycles. Nine patients (47%) had complete response, 6 (32%) had a partial response, 3 (16%) remained stable, and only 1 (6%) progressed on ICIs. No tumors recurred nor required exenteration by the end of the study period. The median follow-up time was 35 (interquartile range, 19–53) months. Conclusions: Immunotherapy demonstrated excellent, sustained clinical outcomes in periocular cutaneous squamous cell carcinoma with orbital invasion with low morbidity and mortality. A disease control rate of over 90% was achieved and sustained at a median follow-up of almost 3 years.

Uveal melanoma is a rare but aggressive intraocular malignancy with limited therapeutic options and a high risk of metastatic relapse. Although its mutational landscape is well defined, how genetic factors, uveal location, and disease progression shape cell states and the tumor ecosystem remains poorly understood. We integrate single-cell RNA sequencing and spatial transcriptomics across a cohort spanning healthy uveal tissue, primary tumors, and metastases. We uncover a continuous shift in melanoma cell states during disease progression, from differentiated, pigmentation-associated programs toward stress- and epithelial-to-mesenchymal transition-associated states. This trajectory is modulated by uveal tract location, with iris tumors exhibiting a more differentiated phenotype and choroidal tumors enriched for stemness-associated features that localize to melanoma-rich regions correlating with genomic instability. In parallel, genetic background defines distinct melanoma cell states and tumor–immune interactions. Together, these findings define clinically relevant cellular states and provide a framework for understanding metastatic progression and therapeutic vulnerability.

Using a large multi-institutional cohort of patients with thin melanomas, our study identified that while predictive of improved prognosis in later stage disease, the presence of tumour-infiltrating lymphocytes is associated with poorer outcomes in patients with thin melanomas. Increasing mitotic rate, Charlson Comorbidity Index, absence of radial growth phase and self-pay/no insurance are also significantly associated with poorer outcomes, while tumour thickness, historically one of the most important prognostic features, is not independently associated with recurrence or mortality. This study elucidates novel risk factors that could prognosticate recurrence or mortality among thin melanomas and can be used to enable more personalized surveillance and therapeutic strategies.

Purpose: To characterize the frequency and extent of necrosis within granulomas among patients diagnosed with orbital sarcoidosis on biopsy. Methods: A retrospective review was conducted of patients diagnosed with orbital sarcoidosis at a single institution from 2018 to 2024. Histopathology slides were re-reviewed for evidence of any necrosis or infection. Demographic, laboratory, histopathologic, and radiographic data were gathered for these patients. All findings were presented using descriptive statistics. Results: There were 19 total cases of orbital sarcoidosis in the study timeframe. The majority were female (15, 78.9%) with a median age of 49 (range: 11–85) presenting with a unilateral, mass-occupying orbital lesion (n = 16, 84.2%). The lacrimal gland and orbital fibroadipose tissue were the most frequently involved and biopsied. Biopsies from 13 patients (68.4%) had granulomas containing varying amounts of necrosis on histopathology on retrospective review. No fungal or acid-fast microorganisms were detected with special stains; a subset of patients had additional molecular genetic-based microbiologic studies which were also unrevealing. Conclusions: Although the histopathology of sarcoidosis is classically described as a “non-necrotizing (noncaseating) granulomas,” granulomas with varying extents of necrosis are more frequently seen in orbital sarcoidosis than previously recognized, or than reported in biopsies from patients with sarcoidosis at other anatomic sites. The presence of necrosis within sarcoidal granulomas should not exclude a diagnosis of sarcoidosis at this site, given that infection is adequately excluded.