ABSTRACT
This chapter explores the paradigm of data centralization in the form of a cancer registry (CR). It describes practical and feasible big data architectures that can be applied to overcome the challenges of poorly connected data repositories in radiation oncology. A CR refers to architectures that are capable of systematically capturing, storing, analyzing, and reporting data on patients with cancer. Two primary types of CR are commonly used worldwide: hospital-based and population-based CRs. There are many running CRs in the world. The chapter describes a small collection of them, which are from three countries: the United States, Italy, and the Netherlands. The Surveillance, Epidemiology, and End Results (SEER) program is a source of information on cancer incidence and survival in the United States. SEER captures and publishes cancer data on incidence and survival from the cancer data sources that cover around 28% of the American population.
