Access to accurate early screening for retinoblastoma (RB) remains challenging despite the fact that later stages can lead to enucleation and blindness. To address this issue, this study develops RetinAI, the first low-cost wearable headset and retinal camera with AI-powered systems for early detection of RB. RetinAI consists of two innovations, an extraocular detection device coupled with a YOLOv11 model to detect the early sign of RB, leukocoria, and an internal retinal imaging system powered by ResNet-50 and YOLOv11 to detect retinal tumors. RetinAI’s clinical tests showed that it can detect both retinoblastoma and normal cases. RetinAI can significantly improve RB early detection and can be used at home, annual check-ups or small clinics without eye specialists.