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.

To discuss the clinical presentation, management, and outcome of delayed metastasis in retinoblastoma (RB). Retrospective case series of three patients. Mean age at diagnosis of RB was 29 months (median, 28 months; range, 11–48 months). All were males with non-familial bilateral intraocular RB. Primary treatment for RB included intravenous chemotherapy in all three cases. Secondary treatment included transpupillary thermotherapy/cryotherapy (n = 6 eyes), periocular chemotherapy (n = 2 eyes), intravitreal chemotherapy (n = 1 eye), intra-arterial chemotherapy (n = 1 eye), external beam radiotherapy (EBRT; n = 2 eyes), and enucleation (n = 2 eyes). Primary tumor regression was achieved in all cases and remained status quo at the time of diagnosis of distant metastasis. Two patients developed bone metastasis (ulna; tibia) and one developed soft tissue metastasis (temporal fossa) over a mean follow-up period of 6 years (median, 7 years; range, 5–8 years) from diagnosis of RB. Mean age of detection of metastatic disease was 8 years (median, 8 years; range, 7–9 years). All the lesions were solitary and the diagnosis of metastatic retinoblastoma was confirmed by tissue biopsy. Metastatic disease was treated with surgical excision (n = 1), chemotherapy (n = 2), and EBRT (n = 2). All patients are alive, with two patients free of disease over a mean follow-up period of 23 months (median, 23 months; range, 12–33 months); and 1 in remission 7 months after completion of EBRT. Long-term follow-up of RB cases is mandatory. In spite of intraocular tumor regression, metastasis can still occur many years after treatment of RB.

To compare the outcomes of intravitreal melphalan (IVit-M) versus intravitreal topotecan (IVit-T) for vitreous seeds (VS) in retinoblastoma (RB). Retrospective interventional study. Patients of RB with VS receiving intravitreal chemotherapy between December 2012 and December 2022, at a single quaternary ocular oncology referral center. IVit-M injection of 25mcg/0.1cc in 25 eyes and IVit-T. of 30mcg/0.15cc in 39 eyes. Resolution of VS, globe salvage, intravitreal chemotherapy-related complications RESULTS: The mean age at presentation was 28 months (median, 24 months; range, 4 to 144 months) for the IVit-M group and 25 months (median, 24 months; range, 2 to 60 months) for the IVit-T group. At the time of initiation of intravitreal injection, the VS belonged to type 1 (1 (4%) vs. 1 (3%)), type 2 (9 (36%) vs. 14 (36%)), type 3 (8 (32%) vs.18 (46%)), or a combination of these (7 (28%) vs. 6 (15%)) in IVit-M and IVit-T groups, respectively. Complete resolution of VS following intravitreal chemotherapy was seen in 22 (92%) and 28 (72%) eyes (p=0.069) in IVit-M and IVit-T groups, respectively. At a mean follow-up period of 44 months after the first IVit-C injection in the IVit-M group and 19 months in the IVit-T group, globe salvage was higher in the IVit-T group (77%) than in the IVit-M group (60%, p=0.148), respectively. Posterior segment complications were significantly higher in the IVit-M group than in the IVit-T group (p<0.001). These included retinal pigment epithelial atrophy (p<0.001), optic atrophy (p<0.001), vascular attenuation (p<0.001), and retinal/ subretinal hemorrhages (p=0.004). IVit-T is as efficacious as IVit-M for controlling VS in RB, with a better safety profile in pigmented Asian Indian eyes.

Giant Dacryocele in a Setting of Bilateral Congenital Alacrimia With Punctal and Canalicular Agenesis Anasua Kapoor;Dilip Mishra;Vijitha VS;Mohammad Ali; Ophthalmic Plastic and Reconstructive Surgery