Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

QuantMed: Component-based deep learning platform for translational research

: Klein, J.; Wenzel, M.; Romberg, D.; Köhn, A.; Kohlmann, P.; Link, F.; Hänsch, A.; Dicken, V.; Stein, R.; Haase, J.; Schreiber, A.; Kasan, R.; Hahn, H.; Meine, H.


Chen, P.-H. ; Society of Photo-Optical Instrumentation Engineers -SPIE-, Bellingham/Wash.:
Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications : 16-17 February 2020, Houston, Texas, United States
Bellingham, WA: SPIE, 2020 (Proceedings of SPIE 11318)
ISBN: 978-1-5106-3403-9
ISBN: 978-1-5106-3404-6
Paper 113180U, 8 pp.
Conference "Medical Imaging - Imaging Informatics for Healthcare, Research, and Applications" <2020, Houston/Tex.>
Conference Paper
Fraunhofer MEVIS ()

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.