Artificial Intelligence and Machine Learning in Ocular Oncology, Retinoblastoma (ArMOR): Experience with a Multiracial Cohort.

Background: The color variation in fundus images from differences in melanin concentrations across races can affect the accuracy of artificial intelligence and machine learning (AI/ML) models. Hence, we studied the performance of our AI model (with proven efficacy in an Asian-Indian cohort) in a multiracial cohort for detecting and classifying intraocular RB (iRB). Methods: Retrospective observational study. Results: Of 210 eyes, 153 (73%) belonged to White, 37 (18%) to African American, 9 (4%) to Asian, 6 (3%) to Hispanic races, based on the U.S. Office of Management and Budget's Statistical Policy Directive No.15 and 5 (2%) had no reported race. Of the 2473 images in 210 eyes, 427 had no tumor, and 2046 had iRB. After training the AI model based on race, the sensitivity and specificity for detection of RB in 2473 images were 93% and 96%, respectively. The sensitivity and specificity of the AI model were 74% and 100% for group A; 88% and 96% for group B; 88% and 100% for group C; 73% and 98% for group D, and 100% and 92% for group E, respectively. Conclusions: The AI models built on a single race do not work well for other races. When retrained for different races, our model exhibited high sensitivity and specificity in detecting RB and classifying RB.

High-Risk Histopathological Features of Retinoblastoma following Primary Enucleation: A Global Study of 1426 Patients from 5 Continents.

PURPOSE: To evaluate high-risk histopathological features (HRHF) following primary enucleation of eyes with retinoblastoma (RB) and assess the patient outcomes across continents. METHODS: Retrospective study of 1426 primarily enucleated RB eyes from five continents. RESULTS: Of all, 923 (65%) were from Asia (AS), 27 (2%) from Australia (AUS), 120 (8%) from Europe (EUR), 162 (11%) from North America (NA), and 194 (14%) from South America (SA). Based on the continent (AS vs. AUS vs. EUR vs. NA vs. SA), the histopathology features included massive choroidal invasion (31% vs. 7% vs. 13% vs. 19% vs. 27%, p=0.001), post-laminar optic nerve invasion (27% vs. 0% vs. 16% vs. 21% vs. 19%, p=0.0006), scleral infiltration (5% vs. 0% vs. 4% vs. 2% vs. 7%, p=0.13), and microscopic extrascleral infiltration (4% vs. 0% vs. <1% vs. <1% vs. 4%, p=0.68). Adjuvant chemotherapy with/without orbital radiotherapy was given in 761 (53%) patients. Based on Kaplan-Meier estimates in different continents (AS vs. AUS vs. EUR vs. NA vs. SA), the 6-year risk of orbital tumor recurrence was 5% vs. 2% vs. 0% vs. 0% vs. 12% (p<0.001), systemic metastasis was reported in 8% vs. 5% vs. 2% vs. 0% vs. 13% (p=0.001), and death in 10% vs. 3% vs. 2% vs. 0% vs. 11% (p<0.001) patients. CONCLUSION: There is a wide variation in the infiltrative histopathology features of RB across continents, resulting in variable outcomes. SA and AS had a higher risk of orbital tumor recurrence, systemic metastasis, and death compared to AUS, EUR, and NA.

Efficacy of topical 5-Fluorouracil in the management of ocular surface squamous neoplasia: a study of 101 eyes.

OBJECTIVE: To study the efficacy and side-effect profile of topical 5-Fluorouracil (5-FU) in the treatment of ocular surface squamous neoplasia (OSSN). METHODS: Retrospective study of 101 eyes of 100 patients treated with 5-FU with one week on and 3 weeks off regimen. RESULTS: Of the 100 patients (101 eyes), the mean age at diagnosis of OSSN was 49 (median, 52 years; range, 11-87 years). History of prior intervention was noted in 6 (6%) eyes. Tumor epicenter included bulbar conjunctiva (n = 54; 53%), limbus (n = 27; 27%), and cornea (n = 20;20%). Mean number of cycles of topical 5-FU administered was 3 (median, 3; range, 1-8). Complete tumor regression was achieved with topical 5-FU in 89 (88%) eyes with a mean number of 2 cycles (median, 2; range, 1-6) of 5-FU. The remaining 12 (12%) lesions underwent additional treatment including excisional biopsy (n = 7), extended enucleation (n = 3), and topical Interferon alpha 2b (n = 2) for complete tumor control. Over a mean follow-up period of 6 months (median, 5 months; range, 1-36 months) following treatment, tumor recurrence was noted in 2 (2%) patients, and side-effects were noted in 7 (7%) eyes including conjunctival hyperemia (n = 1), punctal stenosis (n = 1), sterile keratitis (n = 4), and limbal stem cell deficiency (n = 1). CONCLUSION: Topical 5-FU is an effective non-invasive therapy for OSSN with a minimal side-effect profile.

Role of MYCN in retinoblastoma: A review of current literature.

Chromosomal abnormalities that involve the MYCN gene are rare; however, it is one of the most commonly mutated genes in retinoblastoma (RB) after the RB1 gene. MYCN is amplified in approximately 1-9 % of all RB tumors. It plays a role in RB oncogenesis via many mechanisms, including synergism with RB1 deletion, positive feedback with MDM2, upregulation of cell cycle regulating genes, upregulation of miRNA, and upregulation of glucose metabolism. MYCN amplifications are not mutually exclusive and can occur even in the presence of RB1 gene mutations. Clinically, RB1+/+MYCNA tumors present as sporadic, unilateral, advanced tumors in very young children and tend to follow an aggressive course. Magnetic resonance imaging features include peripheral tumor location, placoid configuration, retinal folding, tumor-associated hemorrhage, and anterior chamber enhancement. Genetic testing for MYCNA is especially recommended in patients with unilateral RB where genetic blood testing and tumor tissue show a lack of RB1 mutation. MYCN-targeted therapies are evolving and hold promise for the future.

Primary Subretinal Seeding in Retinoblastoma: Clinical Presentation and Treatment Outcomes.

Introduction: The aim of this study was to describe the clinical features and treatment outcomes of primary subretinal seeding (SRS) in patients with intraocular retinoblastoma (RB). Methods: Descriptive analysis of primary SRS in 47 patients (50 eyes) with RB was performed. Results: Mean age was 19 months (range, 2-72 months), and 55% (n = 26) of the subjects were male. At presentation, the SRS involved two or more quadrants in 88% of eyes. Most seeds appeared yellowish gray (66%) and round to oval in shape (48%). Two-thirds of SRS were seen posterior to the equator and within 5 mm from the main tumor. Associated features included subretinal fluid in 50 eyes (100%), total retinal detachment in 28 eyes (56%), and vitreous seeds in 20 eyes (40%). Treatment included intravenous chemotherapy (IVC) (n = 47; 94%), enucleation (n = 2; 4%), and intra-arterial chemotherapy (n = 1; 2%). SRS treatment included adjunct use of focal transpupillary thermotherapy and/or cryotherapy (n = 20; 40%). Retinal tumor control was achieved in 36 eyes (76%) with 32 eyes (78%) showing a type 3 regression pattern, while SRS completely regressed in 24 (48%) eyes, partially in 15 (30%) and worsened in 2 (4%) eyes. Over a mean follow-up of 30 months (range, 3-68 months), SRS recurrence was noted in 12 eyes (29%), globe salvage was achieved in 39 eyes (78%), and 1 (4%) patient died of presumed metastasis. Conclusion: Primary SRS pose a therapeutic challenge during RB treatment. The SRS responds moderately to systemic IVC, with one-third cases showing SRS recurrence and one-fifth ultimately requiring enucleation.