Challenges for data storage in medical imaging research

Abstract

Researchers in medical imaging have multiple challenges for storing, indexing, maintaining viability, and sharing their data. Addressing all these concerns requires a constellation of tools, but not all of them need to be local to the site. In particular, the data storage challenges faced by researchers can begin to require professional information technology skills. With limited human resources and funds, the medical imaging researcher may be better served with an outsourcing strategy for some management aspects. This paper outlines an approach to manage the main objectives faced by medical imaging scientists whose work includes processing and data mining on non-standard file formats, and relating those files to the their DICOM standard descendents. The capacity of the approach scales as the researcher's need grows by leveraging the on-demand provisioning ability of cloud computing.

Fig 1.

A high level view of the key image file components, showing the relationships between the raw files, their DICOM descendent files, and the MIRTH parsing engine creating a database to cross-reference the two data sets for subsequent data mining.

Fig 2.

One potential database schema for relating DICOM image objects to the proprietary “raw” files that created them. The table “known_scanners” forms a knowledge base of scanner and software versions that allow linking a specific DICOM image object to the raw file(s) that created it. The table “DICOM_image” then links to one or more “image_parameter” tables to record values of interest to the researcher (slice thickness, reconstruction kernel, pulse sequence, etc.). If the database encounters an unknown scanner model, an entry is made in the “alerts” table so that the knowledge base can be expanded.