Data Science
Our data science and machine learning research groups aim to develop new ways of handling and analyzing data in radiology. Recent advances in data science, machine learning and computer vision offer radiology numerous opportunities to improve patient care and clinical practice in a variety of areas.
The Institute of Diagnostic and Interventional Radiology has two research groups for data science and machine learning in radiology with different focuses:
Research topics
The aim of our research group is to develop, test and apply artificial intelligence methods in radiology and to perform data curation, pre- and post-processing of the data used.
Our current projects include deep learning methods for a wide range of topics such as radiomics feature extraction, image segmentation and classification. As the field rapidly evolves, we are of course also exploring new and current techniques, including unsupervised learning methods, generative adversarial networks (GANs) and the combination of different data sources. We are always on the lookout for new advances and methods that we can incorporate into our research.
Further information: https://raddatascience.uni-koeln.de/research
Research projects
- Segmentation, classification and characterization of lymph nodes
- Classification and characterization of lung lesions
- Segmentation, classification and characterization of brain tumors
- Characterization of prostate lesions
- Segmentation and characterization of kidney diseases
- Reproducibility of features extracted in radiomics studies
Subsidies
- 2023-2026 Open Medical Inference OMI (BMBF)
- 2023-2026 "DEvelopment and dEployment of a Pipeline for automated LymphoNodal profiling and staging: DEEP-LN", funded by Priority Program 2177 of the DFG [LINK: gepris.dfg.de/gepris/projekt/428219815]
- 2023-2024 "Evaluation of Clinical Translatability of Publicly Available Deep Learning Methods in Chronic Lymphocytic Leukaemia (CLL)", funded by Köln Fortune (Medical Faculty of the University of Cologne)
- 2020-2024 RACOON (LINK: radiologie.uk-koeln.de/forschung/forschung-mit-racoon/)
- 2023-2024 Else Kröner
- 2021-2022 "DeepLesion - Bringing automatic segmentation for brain tumors into clinical practice)", funded by Köln Fortune (Faculty of Medicine, University of Cologne)
- 2020-2021 "RISK - Risk Maps using T2 mapping and Diffusion MR Sequences of the Prostate", ESR Seed Grant Award of the European Society of Radiology (ESR) and the European Institute for Biomedical Imaging Research (EIBIR)
- 2020-2021 "GAIA - Group for Applied Imaging Application of Artificial Intelligence", funded by Köln Fortune (Medical Faculty of the University of Cologne)
- Research Group for Experimental Imaging and Image-guided Therapy, Institute for Diagnostic and Interventional Radiology, University Hospital Cologne
- Cardiovascular Imaging Research Group, Institute of Diagnostic and Interventional Radiology, University Hospital Cologne
- Machine Learning and Data Science Group, Institute of Diagnostic and Interventional Radiology, University Hospital Cologne
- Research Group for Oncological Imaging, Institute for Diagnostic and Interventional Radiology, University Hospital Cologne
- Clinic for Stereotaxy and Functional Neurosurgery, University Hospital Cologne
- Clinic and Polyclinic for Internal Medicine I - Oncology, Haematology, Clinical Neurosurgery, University Hospital Cologne
- Center for Data and Simulation Science (CDS), University of Cologne
- Multiparametric imaging and radiomics - PD Dr. B. Baeßler
- Center for Integrated Oncology (CIO)
- Philips Research Aachen
- Philips Research Hamburg
- Jülich Supercomputing Center
- Regional Computing Center of the University of Cologne (RRZK)
- German Cancer Research Center (DKFZ)