An Integrated Three-Tier Microservice Architecture for Deploying State-of-the-Art Ocular Cancer Detection Models

This paper describes the design and implementation of a Scalable three-tier microservice system architecture optimized for deployment of deep learning models in real-time ocular cancer screening. The platform decouples the presentation layer, React, from data and routing layer implemented in Node.js, and the specialized machine learning inference service provided by FastAPI, the system supports a robust multi-stage Diagnostic workflow, currently implemented using a ResNet50- A two-phase trained transfer learning model in order to achieve empirically verified perfect classification on the test set. Model, which targets Retinoblastoma (RB), reached An accuracy, Precision, and Recall of 100% in its independent test set. This For instance, microservice architecture has been demonstrated to be critical for the effective and scalable integration of high performance AI tools into practical clinical environments, especially low-resource settings by providing robust data persistence, dedicated user management, native system traceability and smooth routing of diagnostic requests.