Junior Research Group Interactive Machine Learning

Dr. Paul Jäger

Human-Machine-Interaction and related topics covered by the research group.
© dkfz.de

Considering human interaction when designing machine learning (ML) systems bears great potential: On the one hand, decision-making in ML systems remains imperfect in practice, thus requiring human interaction for safety-critical applications such as clinical diagnostics. On the other hand, the burden of manual training data annotation can be alleviated by means of human-in-the-loop scenarios.
Taking this human-centered perspective, the Junior Group Interactive Machine Learning (IML) headed by Paul Jäger strives to pioneer ML research directed at real-life applications. Specifically, our research involves probabilistic modeling, explainable AI, user modeling, active learning, and interactive systems with a special focus on image analysis tasks such as object detection or segmentation. A further interest lies in the appropriate and application-oriented evaluation of ML systems.
IML is part of the Helmholtz Imaging Platform, an initiative towards leveraging image processing synergies across all Helmholtz research centers. Thus, next to medical applications driven by the DKFZ environment, the group collaborates with experts across all of Helmholtz to develop human-centered ML systems on diverse and unique imaging tasks.

Contact

Dr. Paul Jäger
Interactive Machine Learning (E290)
Deutsches Krebsforschungszentrum
Im Neuenheimer Feld 223
69120 Heidelberg
Tel: +49 6221 42 3015

Selected Publications

  • Jäger PF, Kohl SAA, Bickelhaupt S, et al. Retina U-Net: Embarrassingly Simple Exploitation of Segmentation Supervision for Medical Object Detection. In: Machine Learning for Health Workshop at Neurips. PMLR; 2020:171-183.
  • Isensee F*, Jäger PF*, Kohl SAA, Petersen J, Maier-Hein KH. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation. Nature Methods. 2021;18(2):203-211.
  • Bickelhaupt S*, Jäger PF*, Laun FB, et al. Radiomics Based on Adapted Diffusion Kurtosis Imaging Helps to Clarify Most Mammographic Findings Suspicious for Cancer. Radiology. 2018;287(3):761-770.
  • Petersen J, Jäger PF, Isensee F, et al. Deep Probabilistic Modeling of Glioma Growth. In: Shen D, Liu T, Peters TM, et al., eds. Medical Image Computing and Computer Assisted Intervention. 2019:806-814
to top
powered by webEdition CMS