Many current and future clinical research studies rely on medical images for quantitative metrics for diagnosis, prognosis and treatment response. Images are used to quantify disease burden such as tumor volume, inflammation, hemorrhage, and infarction. Serial imaging is used to quantify the outcome of interventions, such as changes in tumor size or loss of brain tissue. Importantly, medical images are providing an ever increasing number of sensitive diagnostic approaches to disease, such as the use of susceptibility weighted and diffusion tensor MR imaging in the evaluation of brain trauma.
Initially developed with the support of an ARRA supplement to the Harvard Catalyst, the Medical Imaging Informatics Bench to Bedside (mi2b2) workbench aims to facilitate searching, acquiring, and previewing the aforementioned material that is stored in multiple PACS (Picture Archiving and Communication System) systems. Obtaining images from a PACS raises the issue of interruption of on-going clinical care as well as the protection of private information and is thus a complex affair. Information can only be retrieved via a specific tool which ensures that only approved patient scans are accessible and also limits the number of simultaneous downloads made by a single user.
This intermediate step is carried out by the mi2b2 platform, consisting of a client component (mi2b2 workbench) and a server component. Mi2b2 is a modular component of the i2b2 (Informatics for Integrating Biology and the Bedside) software project - an NIH-funded National Center for Biomedical Computing based at Partners HealthCare System. It serves as a bridge between a user and the PACS, which may be housed across multiple institutions and departments (e.g. radiology, cardiology, or neurology).