Infrastructure for sharing standardized clinical brain scans across hospitals
DOI: 10.1109/BIBMW.2011.6112547 Conference: 2011 IEEE International Conference on Bioinformatics and Biomedicine Workshops (BIBMW), Atlanta, GA, USA, November 12-15, 2011
Progress in our understanding of brain disorders increasingly relies on costly collection of large standardized brain magnetic resonance imaging (MRI) data sets. Moreover, clinical interpretations of brain scans benefit from compare and contrast analyses of scans from patients with similar, and sometimes rare, demographic, diagnostic, and treatment status. A solution to both needs is to acquire standardized, research-ready clinical brain scans and to build the information technology infrastructure to share such scans, along with other pertinent information, across hospitals. The resulting research-ready brain imaging resource would provide a wealth of accessible standardized brain imaging data relevant to patient care and research. This paper describes a pilot project that develops such a brain resource, including the rationale, the short imaging protocol, the access to patient data, and the system architecture. This pilot project is a joined effort by researchers from the Clinical Translational Science Institutes (CTSIs) at the University of California Irvine (UCI) and University of Southern California (USC) with strong support from the Biomedical Informatics Research Network (BIRN). The pilot system developed enables capture and sharing of standardized, de-identified clinical brain images across institutions via a federated database system.
- [Show abstract] [Hide abstract]
ABSTRACT: With the influx of available multi-modality neuroimaging data, the need to mine large databases for interesting features in a modality neutral way across many brain disorders is of interest. In this paper I present some examples of applying models originating in the computer vision and text mining communities to neuroimaging data which are not tuned for a particular imaging modality and are agnostic to the underlying brain disorder.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.