Format

Send to

Choose Destination
Z Rheumatol. 2018 Apr;77(3):203-208. doi: 10.1007/s00393-018-0422-9.

[Big data in imaging].

[Article in German]

Author information

1
Heinrich-Heine-Universität Düsseldorf (HHU), Poliklinik, Funktionsbereich und Hiller-Forschungszentrum für Rheumatologie, Universitätskliniken Düsseldorf, Moorenstraße 5, 40225, Düsseldorf, Deutschland. philipp.sewerin@med.uni-duesseldorf.de.
2
Heinrich-Heine-Universität Düsseldorf (HHU), Poliklinik, Funktionsbereich und Hiller-Forschungszentrum für Rheumatologie, Universitätskliniken Düsseldorf, Moorenstraße 5, 40225, Düsseldorf, Deutschland.
3
Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Medizinische Klinik 3 - Rheumatologie und Immunologie, Universitätsklinikum Erlangen, Erlangen, Deutschland.

Abstract

Until now, most major medical advancements have been achieved through hypothesis-driven research within the scope of clinical trials. However, due to a multitude of variables, only a certain number of research questions could be addressed during a single study, thus rendering these studies expensive and time consuming. Big data acquisition enables a new data-based approach in which large volumes of data can be used to investigate all variables, thus opening new horizons. Due to universal digitalization of the data as well as ever-improving hard- and software solutions, imaging would appear to be predestined for such analyses. Several small studies have already demonstrated that automated analysis algorithms and artificial intelligence can identify pathologies with high precision. Such automated systems would also seem well suited for rheumatology imaging, since a method for individualized risk stratification has long been sought for these patients. However, despite all the promising options, the heterogeneity of the data and highly complex regulations covering data protection in Germany would still render a big data solution for imaging difficult today. Overcoming these boundaries is challenging, but the enormous potential advances in clinical management and science render pursuit of this goal worthwhile.

KEYWORDS:

Artificial intelligence; Computed tomography; Data analysis; Decision making; Magnetic resonance imaging

PMID:
29411097
DOI:
10.1007/s00393-018-0422-9

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center