KI-RAD: Artificial intelligence for radiological imaging in emergency Artificial intelligence for radiological imaging in emergency and intensive care (BMWi)

KI-RAD is an application project of the north German research alliance for the development of an AI-Space for intelligent health systems (KI-SIGS), a winner of the innovation competition "Artificial Intelligence" of the Federal Ministry of Economics (BMWi). The establishment of the KI-Space includes the development and setup of an AI platform, the definition and implementation of an R&D roadmap and the AI education of the north German healthcare industry. As an application project, KI-RAD will demonstrate the advantages of using the AI-Space and will actively participate in the development.
The aim of the project is the development and provision of AI-supported analysis procedures for the optimization of workflow and reporting quality for medical imaging in emergency and intensive care medicine, especially in the areas of stroke, skeletal trauma and intensive care thorax in cooperation with the University Medical Center Schleswig-Holstein (UKSH), the University Medical Center Hamburg-Eppendorf (UKE) and Philips Research Hamburg.
The Institute of Medical Informatics (IMI) will mainly develop methods for visualization and confidence estimation of deep learning procedures for X-ray thorax images from intensive care medicine in the project KI-RAD. For this purpose, ensemble and iterative pertubation models will be considered, which will be optimised in the course of the project, especially with respect to run-time/inference.

BMWi project funding (2020-2023) 2’080’000€ (UzL: 114’000€ , IMI: 114’000€)

Selected Publications

  1. Heinrich M.P., Oktay O., Bouteldja N.
    OBELISK-Net: Fewer Layers to Solve 3D Multi-Organ Segmentation with Sparse Deformable Convolutions
    Medical Image Analysis (MedIA, 2019)
  2. Schlemper J., Oktay O., Schaap M., Heinrich M.P., Kainz B., Glocker B., Rückert D.
    Attention Gated Networks: Learning to Leverage Salient Regions in Medical Images
    Medical Image Analysis (MedIA, 2019)

Project Team

Prof. Dr. Mattias Heinrich

M. Sc. Lasse Hansen