Division of Medical Image Computing

PD Dr. Klaus Maier-Hein

Magnetic resonance imaging produces a wealth of information which we combine in personally adapted computational models of living organs. This image shows a graph theory-based model of the human brain that helps us learn, detect, and predict disease patterns.
© dkfz.de

Medical images uniquely represent the anatomical and functional progress of diseases in 3D space and time. The Division of Medical Image Computing strives to utilize the vast and unexploited potential in these images through computational image understanding and information processing.

“Radiomics” denotes the emerging endeavor of systematic extraction, mining and leveraging of this rich information towards personalized medicine. We aim to comprehensively summarize imaging information from multiple time-points and modalities in condensed, quantitative signatures and link them with clinical and biological parameters (e.g. genomics or proteomics). We develop our methods for various clinical applications, with a particular emphasis on prostate cancer, breast cancer and brain tumors.

Another focus of our research lies in processing, analysis and visualization of neurological datasets, especially from diffusion-weighted MRI. We develop techniques for white matter fiber tractography and segmentation, as well as for brain connectivity analysis (connectomics). Main fields of application comprise Alzheimer’s disease, autism spectrum disorder and borderline personality disorder, as well as surgery planning and navigation in the context of tumor treatment.

FUTURE OUTLOOK

The applications mentioned above require cutting edge developments at the core of computer science. We have a profound track record in the methodology of machine learning, especially in the context of big data applications where large-scale heterogeneous data sources are analyzed. Transparent deep learning techniques that are interpretable and that explicitly deal with uncertainty in the data are of particular interest to us. We further pursue novel image computing concepts that combine mathematical modelling approaches with current machine learning technology. They can enable the simultaneous optimization of all required components in end-to-end training scenarios.

We put a strong focus on the successful validation and translation of the developed techniques into clinical practice. To this end, a dedicated group for scientific software engineering was established, which coordinates and implements IT strategies of the research program “Imaging and Radiooncology” at DKFZ and contributes to several consortia such as the German Cancer Consortium (DKTK) or the National Center for Tumor Diseases (NCT). Our versatile and open technological portfolio builds a foundation for national and international projects and is constantly advanced to fulfill the needs of current medical imaging research.

Contact

PD Dr. Klaus Maier-Hein
Medical Image Computing (E230)
Deutsches Krebsforschungszentrum
Im Neuenheimer Feld 223
69120 Heidelberg
Tel: +49 6221 42 3545
Fax: +49 6221 42 2345

Selected Publications

  • Kickingereder P, Isensee F, Tursunova I, Petersen J, Neuberger U, Bonekamp D, Brugnara G, Schell M, Kessler T, Foltyn M, Harting I, Sahm F, Prager M, Nowosielski M, Wick A, Nolden M, Radbruch A, Debus J, Schlemmer HP, Heiland S, Platten M, von Deimling A, van den Bent MJ, Gorlia T, Wick W, Bendszus M, Maier-Hein KH. Automated quantitative tumour response assessment of MRI in neuro-oncology with artificial neural networks: a multicentre, retrospective study. Lancet Oncol. 2019 May;20(5):728-740. doi: 10.1016/S1470-2045(19)30098-1. Epub 2019 Apr 2.
  • Bickelhaupt S, Jaeger PF, Laun FB, Lederer W, Daniel H, Kuder TA, Wuesthof L, Paech D, Bonekamp D, Radbruch A, Delorme S, Schlemmer H-P, Steudle FH, Maier-Hein KH: Radiomics Based on Adapted Diffusion Kurtosis Imaging Helps to Clarify Most Mammographic Findings Suspicious for Cancer. Radiology 287 (3), 761-770, 2018.
  • Wasserthal J, Neher P, Maier-Hein KH: TractSeg - Fast and accurate white matter tract segmentation. Neuroimage 183, 239-253, 2018.
  • Maier-Hein KH, Neher PF, Houde JC, Cote MA, Garyfallidis E, Zhong J, Chamberland M, Yeh FC, Lin YC, Ji Q, Reddick WE, Glass JO, Chen DQ, Feng Y, Gao C, Wu Y, Ma J, Renjie H, Li Q, Westin CF, Deslauriers-Gauthier S, Gonzalez JOO, Paquette M, St-Jean S, Girard G, Rheault F, Sidhu J, Tax CMW, Guo F, Mesri HY, David S, Froeling M, Heemskerk AM, Leemans A, Bore A, Pinsard B, Bedetti C, Desrosiers M, Brambati S, Doyon J, Sarica A, Vasta R, Cerasa A, Quattrone A, Yeatman J, Khan AR, Hodges W, Alexander S, Romascano D, Barakovic M, Auria A, Esteban O, Lemkaddem A, Thiran JP, Cetingul HE, Odry BL, Mailhe B, Nadar MS, Pizzagalli F, Prasad G, Villalon-Reina JE, Galvis J, Thompson PM, Requejo FS, Laguna PL, Lacerda LM, Barrett R, Dell`Acqua F, Catani M, Petit L, Caruyer E, Daducci A, Dyrby TB, Holland-Letz T, Hilgetag CC, Stieltjes B, Descoteaux M: The challenge of mapping the human connectome based on diffusion tractography. Nature Communications 8 (1), 1349, 2017.
to top