Dr. Markus Wenzel

My core interest is the use of interpretable deep learning in health care. My goal is to integrate learning and computer aided prediction into clinically useful applications that collaborate with users. 

Selected publications - for a full list check out Markus Wenzel on Google Scholar

• Geissler, K., Wenzel, M., …, Meine, H.: Improving Uncertainty Quantification for Active Learning for Breast Segmentation in MRI. Under review, MIDL 2023
• Wenzel, M. (2022): Generative Adversarial Networks and other Generative Models. arXiv preprint arXiv:2207.03887; Book chapter to appear in Colliot, O: “Deep Learning for Brain Disorders.” Springer
• Mensing D, Hirsch J, Wenzel M, Günther M (2022): 3D (c)GAN for whole body MR synthesis. MICCAI DGM 2022
• Shabanian M, Wenzel M, DeVincenzo JP (2022): Infant brain age classification: 2D CNN outperforms 3D CNN in small dataset. Medical Imaging 2022: Image Processing 12032, 626-633
• Schreiber A, Hahn H, Wenzel M, Loch T (2020): Artificial intelligence: What do urologists need to know? Der Urologe. Ausg. A 59 (9), 1026-1034
• Klein J, Wenzel M, Romberg D, Köhn A, Kohlmann P, Link F, Hänsch A, Dicken V, Stein R, Haase J, Schreiber A, Hahn H, Meine H (2020) QuantMed: Component-based DL platform for translational research. Proceedings of SPIE Medical Imaging: Imaging Informatics for Healthcare, Research, and Applications 
• Wenzel M, Milletari F, Krüger J, Lange C, Schenk M, Apostolova I, Klutmann S, Ehrenburg M, Buchert R (2019) Automatic classification of dopamine transporter SPECT: deep convolutional neural networks can be trained to be robust with respect to variable image characteristics. EUR J NUCL MED MOL I Online first
• Wenzel, M. (2017): Deep Learning in der Medizin. Journal Onkologie; 6:184-188
• Harz, M. (2017): Cancer, Computers, and Complexity: Decision-Making for the Patient. European Review; 25(1):96–106
• Harz, M.T., Georgii, J., Wang, L., Schilling, K., Peitgen, H.-O. (2012): Efficient Breast Deformation Simulation. VRIPHYS 2012
• Harz, M.T., Ritter, F., Benten, S., Schilling, K., Peitgen, H.-O.: A Novel Workflow-centric Breast MRI Reading Prototype Utilizing Multi-touch Gestures. Proc IWDM 2012

• Certified Scientific Trainer Foundation Level/BDTV geprüfter Scientific Trainer Foundation Level (12/2022)
• PhD Thesis: “Complexity Reduction in Image-Based Breast Care”. 2014 (University Bremen; “magna cum laude”)
• Distance Learning University, Hagen, Germany; 2001-2005 (BSc Computer Science; “With Distinction”)
• Georg-August University, Goettingen, Germany; 1991-2000 (Political Science, Sinology)
• Scholarship awarded by the Studienstiftung des Deutschen Volkes (German Academic
• Scholarship Foundation), Germany’s most prestigious scholarship foundation.
• Abitur, Goethe-Gymnasium Kassel (Average grade 1,1, equals an “A”) 

• Key Scientist Cognitive Computing, Key Scientist Computational Breast Care at Fraunhofer MEVIS (since Oct 2021)
• Research Scientist at Fraunhofer MEVIS (Oct 2005 - Nov 2021)
• Senior Scientist Cognitive Medical Computing at Fraunhofer MEVIS (Oct 2005 - Nov 2021)
• Application Developer at W&W Informatik (Apr 1999 - Sep 2005)