Brief profile:
Klaus Maier-Hein heads the Medical Image Processing Division at the German Cancer Research Center (DKFZ). He is also head of the Section for Automated Image Analysis at Heidelberg University Hospital and spokesman for the Helmholtz Information & Data Science School for Health (HIDSS4Health) of the Karlsruhe Institute of Technology, the German Cancer Research Center and Heidelberg University.
Honors /Awards:
- Winner of Brain Tumor Segmentation (BraTS) Challenge (last author, MICCAI 2020)
- Winner of Kidney Tumor Segmentation Challenge (last author, kits19.grand-challenge.org)
- Winner of Liver Tumor Segmentation Challenge (last author, www.lits-challenge.com)
- Winner of Medical Segmentation Decathlon (last author, MICCAI 2018, Granada, Spain)
- Winner of Automated Cardiac Diagnosis Challenge (last author, MICCAI 2017, Canada)
Memberships:
Since 2019 Coordinator of Helmholtz Imaging Platform
Since 2019 Spokesman of Helmholtz Information & Data Science School for Health
2019 Program committee Visual Computing for Biology and Medicine 2019, Brno
Since 2018 Steering committee Medical Data Donors e.V.
The Division of Medical Image Computing (MIC) pioneers research in machine learning and information processing, with the particular aim of improving cancer patient care by systematic image data analytics.
Lung cancer, COPD, COVID-19
- Isensee, F. et al. (2024). nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation. In: Linguraru, M.G., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. MICCAI 2024. Lecture Notes in Computer Science, vol 15009. Springer, Cham. https://doi.org/10.1007/978-3-031-72114-4_47
- Neher, P., Hirjak, D. & Maier-Hein, K. Radiomic tractometry reveals tract-specific imaging biomarkers in white matter. Nat Commun 15, 303 (2024). https://doi.org/10.1038/s41467-023-44591-3
- Brugnara, G., Baumgartner, M., Scholze, E.D. et al. Deep-learning based detection of vessel occlusions on CT-angiography in patients with suspected acute ischemic stroke. Nat Commun 14, 4938 (2023). https://doi.org/10.1038/s41467-023-40564-8
- Bohn, J.R. et al. (2023). RPTK: The Role of Feature Computation on Prediction Performance. In: Woo, J., et al. Medical Image Computing and Computer Assisted Intervention – MICCAI 2023 Workshops. MICCAI 2023. Lecture Notes in Computer Science, vol 14394. Springer, Cham. https://doi.org/10.1007/978-3-031-47425-5_11
- Almeida, S.D., Norajitra, T., Lüth, C.T. et al. Prediction of disease severity in COPD: a deep learning approach for anomaly-based quantitative assessment of chest CT. Eur Radiol 34, 4379–4392 (2024). https://doi.org/10.1007/s00330-023-10540-3
Silvia Dias Almeida | PhD student | ||
Jonas Bohn | PhD student | ||
Tobias Norajitra | Postdoc, Group Lead |
Lung Research - Projects
- Characterization and prediction of COPD as a comorbidity from computed tomography imaging
For COPD, different patterns ("phenotypes") of lung damage are observed with different consequences for individual therapy, e.g. the destruction of the alveolar sac (emphysema) or bronchial wall thickening and obstruction with mucus (airway disease). Medical air-flow lung function tests typically fail to detect subtle changes within the lungs or even subregions of the lung. Beyond visual inspection of computed tomography (CT), we aim to further analyze CT image data by exploring unseen patterns and clusters using Deep Learning, in order to find new methods for the classification and monitoring of COPD.
2. Predicting Immunotherapy Outcome of Lung Cancer Patients by Composite Radiomics Signatures in CT Scans
About 50 % of advanced lung cancer patients which are assigned to receive immunotherapy do not respond to this treatment and succumb to disease progression. The aim of this project is to promote a more precise prediction of potential treatment outcome in lung cancer patients at an early stage of therapy by means of Radiomics and Deep Learning. We aim at robustly classifying patients as probable responders or nonresponders, thus increasing potential survival by opening the possibility to select other treatments with better prognosis for the individual patient.
