Dickscheid group

Artificial intelligence for decoding human brain organisation

Timo Dickscheid

  • Group leader “Big Data Analytics”, Institute of Neuroscience and Medicine, Structural and functional organisation of the brain (INM-1), Forschungszentrum Jülich
  • Professor, “Big Data Analytics for Microscopic Images”, Institute of Computer Science , Heinrich Heine Universität Düsseldorf




Facing the challenges of brain complexity and big data analytics, research at INM-1 addresses human brain organization on its different scales, hand in hand with brain simulation and the investigation of learning in artificial and biological neural networks to advance our understanding of cognition, which opens perspectives to discover novel mechanisms for AI.

The research group is embedded into the  Big Data Analytics group headed by Timo Dickscheid, which develops methods for high throughput analysis and 3D reconstruction of microscopic image data, and neuroinformatics solutions for high-resolution brain atlases. The focus of this Helmholtz AI research group is on deep learning methods for microstructural object detection and mulimodal texture analysis in high throughput imaging settings with limited training data, supported by shape and topological constraints. Driven by continuously increasing image resolutions and data volumes, methods are designed for distributed operation on HPC systems.



Research lines

  • Machine Learning and Computer Vision for biomedical image analysis
  • High throughput imaging and HPC environments for microscopy
  • Neuroinformatics


Master students:

  • Philip Bröhl, HHU Düsseldorf
  • Cornelius Crijnen, HHU Düsseldorf

Selected publications

  • Vaca E, Menzel M, Amunts K, Axer M, Dickscheid T, “GORDA: Graph-Based Orientation Distribution Analysis of SLI Scatterometry Patterns of Nerve Fibres”, 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), 2022, doi: 10.1109/ISBI52829.2022.9761492
  • Schiffer C, Spitzer H, Kiwitz K, Unger N, Wagstyl K, Evans AC, et al. Convolutional neural networks for cytoarchitectonic brain mapping at large scale. Neuroimage. 2021; 240(118327):118327. DOI: 10.1016/j.neuroimage.2021.118327
  • Schiffer C, Harmeling S, Amunts K, Dickscheid T. 2D histology meets 3D topology: Cytoarchitectonic brain mapping with graph neural networks. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2021.2021. p. 395–404. DOI: 10.1007/978-3-030-87237-3_38
  • Upschulte E, Harmeling S, Amunts K, Dickscheid T. Contour Proposal Networks for Biomedical Instance Segmentation. Medical Image Analysis. 2022; 102371. https://doi.org/10.1016/j.media.2022.102371
  • Kiwitz K, Schiffer C, Spitzer H, Dickscheid T, Amunts K. Deep learning networks reflect cytoarchitectonic features used in brain mapping. Sci Rep. 2020;10(1):22039. DOI: 10.1038/s41598-020-78638-y
  • Dickscheid T, Haas S, Bludau S, Glock P, Huysegoms M, Amunts K. Towards 3D Reconstruction of Neuronal Cell Distributions from Histological Human Brain Sections. Advances in Parallel Computing. 2019;34 (Future Trends of HPC in a Disruptive Scenario):223–239. DOI: 10.3233/APC190016
  • Spitzer H, Kiwitz K, Amunts K, Harmeling S, Dickscheid T. Improving Cytoarchitectonic Segmentation of Human Brain Areas with Self-supervised Siamese Networks. Medical Image Computing and Computer Assisted Intervention – MICCAI 2018. Springer International Publishing; 2018:663–671.
  • Dickscheid T, Förstner W. A Trainable Markov Random Field for Low-Level Image Feature Matching with Spatial Relationships. Photogrammetrie - Fernerkundung - Geoinformation. 2013;2013(4):269–283. DOI: 10.1127/1432-8364/2013/0176
  • Amunts K, Lepage C, Borgeat L, et al. BigBrain: An Ultrahigh-Resolution 3D Human Brain Model. Science. 2013;340(6139):1472-1475. DOI: 10.1126/science.1235381
  • Dickscheid T, Schindler F, Förstner W. Coding Images with Local Features. International Journal of Computer Vision. 2011;94(2):154–174. DOI: 10.1007/s11263-010-0340-z

Main projects

  • Development of an online accessible multimodal human brain atlas with cellular resolution
  • AI-driven image registration for micrometer resolution biomedical images
  • Deep Learning methods for brain mapping and instance segmentation of microstructural objects

Main Contributions

  • EBRAINS Knowledge Graph
    Find and access multimodal data, models and connect data to the software that will help you analyse the data
  • siibra-explorer - the EBRAINS interactive atlas viewer
    a browser based viewer of brain atlases. Tight integration with the Human Brain Project Knowledge Graph allows seamless querying of semantically and spatially anchored datasets.
  • Siibrasoftware interfaces for interacting with brain atlases
    A dynamic toolsuite for interacting with the EBRAINS brain atlases, a tightly integrated toolsuite which includes siibra-explorer, an interactive 3D atlas viewer, as well as a dedicated programmatic Python client called siibra-python. The aim of siibra is to provide both programmatic and interactive access to the EBRAINS brain atlases, which include the BigBrain and MNI Colin reference spaces, for example, without duplicating software code.