The k-Radiomics project

Turning raw k-space into clinical insight

We build AI methods that unlock MRI raw data for interpretable, patient-ready diagnostics.

€ 2.6M Five-year project volume

2023–2028 Funding period

Multi-site University + industry partners

Funded by the Bruno and Helene Jöster Foundation.

The **k-Radiomics** project

Project overview

With the aim of revolutionising the characterisation of tumours and tissues, the team led by Prof. Dr. Dr. Jens Kleesiek, Prof. Dr. Dr. Jan Egger and Dr. Moritz Rempe from the Institute for KI in Medicine (IKIM) at the University Hospital in Essen will use the raw data (k-space) from magnet resonance tomography (MRT) for the k-Radiomics project. The project is being funded by the Bruno and Helene Jöster Foundation with around € 2.6 million over five years.

Why k-Space matters

Until now, MRI raw data have not been used in clinical practice due to a lack of interpretability. The aim of the project is to develop new artificial intelligence (AI) methods to use this data. This will enable improved tissue characterisation in the sense of virtual biopsies and thus improve the diagnosis and treatment of patients in the future.

Project facts

Project Volume: € 2.6 million
Funding Institution: Bruno and Helene Jöster Foundation
Funding Period: 01.09.2023 to 31.08.2028

Project partners

University Hospital Essen

Technical University Dortmund

Fraunhofer Institute for Integrated Circuits, IIS

Publications

Robustness of breast lesion segmentation under MRI undersampling improves with k-space-aware deep learning

Purpose: To assess whether breast lesion segmentation can be learned directly from acquired MRI k-space, and whether doing so improves …

Lukas T. Rotkopf, Marco Schlimbach, Julius C. Holzschuh", Heinz-Peter Schlemmer, Jens Kleesiek, Moritz Rempe

Last updated on May 22, 2026

Robustness of breast lesion segmentation under MRI undersampling improves with k-space-aware deep learning

Generative Modeling of Complex-Valued Brain MRI Data

Standard Magnetic Resonance Imaging (MRI) reconstruction pipelines discard phase information captured during acquisition, despite …

Marco Schlimbach, Moritz Rempe, Jessica Mnischek, Lukas T. Rotkopf, Jens Weingarten, Jens Kleesiek, Kevin Kröninger

Last updated on May 22, 2026

Efficient Complex-Valued Vision Transformers for MRI Classification Directly from k-Space

Deep learning applications in Magnetic Resonance Imaging (MRI) predominantly operate on reconstructed magnitude images, a process that …

Moritz Rempe, Lukas T. Rotkopf, Marco Schlimbach, Helmut Becker, Fabian Hörst, Johannes Haubold, Philipp Dammann, Kevin Kröninger, Jens Kleesiek

Last updated on Apr 22, 2026

Efficient Complex-Valued Vision Transformers for MRI Classification Directly from k-Space

De-Identification of Medical Imaging Data: A Comprehensive Tool for Ensuring Patient Privacy

Medical data employed in research frequently comprises sensitive patient health information (PHI), which is subject to rigorous legal …

Moritz Rempe, Lukas Heine, Constantin Seibold, Fabian Hörst, Jens Kleesiek

Last updated on Apr 22, 2026

De-Identification of Medical Imaging Data: A Comprehensive Tool for Ensuring Patient Privacy

PhaseGen: A Diffusion-Based Approach for Complex-Valued MRI Data Generation

Magnetic resonance imaging (MRI) raw data, or k-Space data, is complex-valued, containing both magnitude and phase information. …

Moritz Rempe, Fabian Hörst, Helmut Becker, Marco Schlimbach, Lukas Rotkopf, Kevin Kröninger, Jens Kleesiek

Last updated on Apr 14, 2025

Recent News

De-Identification tool featured in AuntMinnieEurope

The MRI community website AuntMinnieEurope featured our De-Identification tool as their top story. Our tool is designed to help researchers and clinicians anonymize MRI data, ensuring patient privacy while providing fast and efficient processing.

Maryam Payne

Last updated on Jun 16, 2025

That's a wrap on the k-Radiomics Symposium 2025!

We were honored to host a fantastic group of leading experts for the k-Radiomics Symposium on June 4th & 5th. The symposium featured a series of high-impact talks and collaborative discussions focused on advancing MRI k-Space research and its potential impact on medical innovation. We extend our gratitude to all speakers and attendees for their invaluable contributions. We are inspired by the potential for future work and research opportunities that emerged from our time together.

Moritz Rempe

Last updated on Jun 12, 2025

ISMRM 2025 - Vortrag über "Tumor likelihood estimation on MRI prostate data by utilizing k-Space information"

Moritz Rempe wird auf der ISMRM 2025 die Arbeit ‘Tumor likelihood estimation on MRI prostate data by utilizing k-Space information’ präsentieren. Der Talk wird am 13. Mai 2025 um 8.50 Uhr in der Session ‘AI: Diagnostic Models’ stattfinden.

Moritz Rempe

Last updated on Jun 12, 2025

DPG 2025 - Bester Vortrag im Bereich Medical Physics

Jessica Mnischek hat den Preis für den besten Vortrag im Bereich Medical Physics auf der DPG 2025 gewonnen. Ihre Arbeit mit dem Titel ‘Autoencoder-based Anomaly Detection in MRI Raw Data’ wurde ausgezeichnet.

Jessica Mnischek

Last updated on Apr 7, 2025

k-Radiomics auf der DPG 2024

Marco Schlimbach wird am 20. März 2024 seine Arbeit im Zuge des k-Radiomics Projektes mit dem Titel ‘Enhancing Brain Tumor Characterization through Machine Learning on Raw MRI K-Space Data’ auf der Frühjahrs-Tagung der Deutschen Physiker Gemeinschaft (DPG) 2024 vorstellen.

Marco Schlimbach

Last updated on Apr 7, 2025

Project Team

University Hospital Essen

Prof. Dr. Dr. Jens Kleesiek

Institute for AI in Medicine, University Hospital Essen, Germany

Prof. Dr. Dr. Jan Egger

Institute for AI in Medicine, University Hospital Essen, Germany

Dr. Moritz Rempe

Institute for AI in Medicine, University Hospital Essen, Germany

MD Kelsey Pomykala Herrmann

Institute for AI in Medicine, University Hospital Essen, Germany

PD Dr. Sied Kebir

Department of Clinical Neurooncology, Clinic for Neurology, University Hospital Essen, Germany

Prof. Dr. Christian Reinhardt

Department of Haematology and Stem Cell Transplantation, University Hospital Essen, Germany

Prof. Dr. Katharina Lückerath

Clinic for Nuclear Medicine, University Hospital Essen, Germany

Prof. Dr. Lale Umutlu

Institute for Diagnostic and Interventional Radiology and Neuroradiology, University Hospital Essen, Germany

Prof. Dr. Martin Glas

Department of Clinical Neurooncology, Clinic for Neurology, University Hospital Essen, Germany

Prof. Dr. Philipp Dammann

Clinic for Neurosurgery, University Hospital Essen, Germany

TU Dortmund

Prof. Dr. Kevin Kröninger

Department of Physics, TU Dortmund, Germany

Marco Schlimbach

Department of Physics, TU Dortmund, Germany

Fraunhofer Institute

Dr. Martin Blaimer

University Hospital Erlangen

German Cancer Research Center (DKFZ)

Dr. Lukas Rotkopf

German Cancer Research Center (DKFZ), Germany

Contact

Feel free to reach out via email:

Institute for AI in Medicine, Girardetstraße 2, 45131, Essen, Germany
UME-IKIM