Share Email Print
cover

Proceedings Paper

QuantMed: Component-based deep learning platform for translational research
Author(s): Jan Klein; Markus Wenzel; Daniel Romberg; Alexander Köhn; Peter Kohlmann; Florian Link; Annika Hänsch; Volker Dicken; Ruben Stein; Julian Haase; Andreas Schreiber; Rainer Kasan; Horst Hahn; Hans Meine
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

QuantMed is a platform consisting of software components enabling clinical deep learning, together forming the QuantMed infrastructure. It addresses numerous challenges: systematic generation and accumulation of training data; the validation and utilization of quantitative diagnostic software based on deep learning; and thus, providing support for more reliable, accurate, and efficient clinical decisions. QuantMed provides learning and expert correction capabilities on large, heterogeneous datasets. The platform supports collaboration to extract medical knowledge from large amounts of clinical data among multiple partner institutions via a two- stage learning approach: the sensitive patient data remains on premises and is analyzed locally in a first step in so-called QuantMed nodes. Support for GPU clusters accelerates the learning process. The knowledge is then accumulated through the QuantMed hub, and can be re-distributed afterwards. The resulting knowledge modules – algorithmic solution components which contain trained deep learning networks as well as specifications of input data and output parameters - do not contain any personalized data, and thus, are safe to share under data protection law. This way, our modular infrastructure makes it possible to efficiently carry out translational research in the context of deep learning, and deploy results seamlessly into prototypes or third-party software.

Paper Details

Date Published: 2 March 2020
PDF: 8 pages
Proc. SPIE 11318, Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications, 113180U (2 March 2020); doi: 10.1117/12.2549582
Show Author Affiliations
Jan Klein, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Markus Wenzel, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Daniel Romberg, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Alexander Köhn, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Peter Kohlmann, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Florian Link, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Annika Hänsch, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Volker Dicken, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Ruben Stein, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Julian Haase, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Andreas Schreiber, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Rainer Kasan, Digithurst Bildverarbeitungssysteme GmbH & Co. KG (Germany)
Horst Hahn, Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)
Hans Meine, Univ. Bremen (Germany)
Fraunhofer-Institut für Digitale Medizin MEVIS (Germany)


Published in SPIE Proceedings Vol. 11318:
Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications
Po-Hao Chen; Thomas M. Deserno, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray