An Architecture to Define Cohorts over Medical Imaging Datasets

The DICOM standard has been widely adopted for the exchange and management of biomedical images. Its hierarchical structure allows representing data and metadata of medical imaging studies. However, other patient data not directly related with the study, such as prescriptions and treatments, are stored in independent Electronic Health Record (EHR) systems. With the increasing production of medical imaging studies, repositories responsible for storing DICOM images started to contain massive amounts of data. Therefore, retrieving a subset of images based on similar criteria as the ones used in EHR systems, is a complex task for a medical researcher. In this paper, we propose an architecture to define cohorts over medical imaging data sets. This proposal uses a DICOM archive to index and to retrieve images, while the studies' selection is performed through a web application, ATLAS, which is normally used on observational studies upon EHR data. The presented architecture was validated using a public data set with synthetic EHR data.