Christoph Berger

Profile Picture

About

Biomedical Computing Master's student at the Technical University of Munich with a B.Sc. in Engineering Science from the Munich School of Engineering at TUM. 

Additionally, I am a student at the Center for Digital Technology and Management in the class of Spring 2020, pursuing an honours degree in Technology Management. 

Areas of interest include machine learning for medical applications, safe and interpretable deep learning and applications of AI.

During and inbetween my studies I worked at the Computational Imaging and Bioinformatics Lab (CIBL) at Harvard Medical School and Dana-Farber Cancer Institute under Prof. Aerts (2019), at the Image-Based Biomedical Modeling (IBBM) group under Prof. Menze at TUM (2017-2018) and the Computational Imaging (CompImg) group at the Neuroradiology Department at the Rechts der Isar Clinic/TUM in Munich under Dr. Wiestler (2019-2020). 

I am also passionate about teaching and have been a TA for Engineering Informatics I, an undergraduate introductory programming course in C, for four years in a row as well as a TA for the courses Heat Transfer and Fluid and Structural Mechanics during my undergraduate studies.

Notable Events

"The BraTS Algorithmic Repository", Invited Talk on October 3, 2019, CBICA Seminar Series; Perelman School of Medicine, University of Pennsylvania

"Fusion of Brain Tumor Segmentations", Invited Talk on January 22, 2019, Neuroradiology Research Colloquium; Klinikum rechts der Isar, Munich

Projects

Most of my current projects can be found on Github or in the list below.

Publications

Kofler, F., Berger, C., Waldmannstetter, D., Lipkopva, J., Ezhov, I., Tetteh, G., Kirschke, J.S., Zimmer, C., Wiestler, B. and Menze, B., 2020. BraTS Toolkit: Translating BraTS brain tumor segmentation algorithms into clinical and scientific practice. Frontiers in Neuroscience14, p.125.

MICCAI 2020 Challenge: Bjoern Menze, Leo Joskowicz, Spyridon Bakas, Andras Jakab, Ender Konukoglu, Anton Becker, & Christoph Berger. (2020, March 20). Quantification of Uncertainties in Biomedical Image Quantification. Zenodo. http://doi.org/10.5281/zenodo.3718912

McKinley, R., Wepfer, R., Grunder, L., Aschwanden, F., Fischer, T., Friedli, C., Muri, R., Rummel, C., Verma, R., Weisstanner, C., Wiestler, B., Berger, C., Eichinger, P., Muhlau, M., Reyes, M., Salmen, A., Chan, A., Wiest, R., and Wagner, F. 2020. Automatic detection of lesion load change in Multiple Sclerosis using convolutional neural networks with segmentation confidence. NeuroImage: Clinical25, p.102104.

Hosny, A., Schwier, M., Berger, C., Örnek, E.P., Turan, M., Tran, P.V., Weninger, L., Isensee, F., Maier-Hein, K.H., McKinley, R. and Lu, M.T., 2019. ModelHub. AI: Dissemination Platform for Deep Learning Models. arXiv preprint arXiv:1911.13218.

Bakas, S., Reyes, M., Jakab, A., Bauer, S., Rempfler, M., Crimi, A., Shinohara, R.T., Berger, C., Ha, S.M., Rozycki, M. and Prastawa, M., 2018. Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the BRATS challenge. arXiv preprint arXiv:1811.02629.

Other Interests

  • TEDxTUM, Team Lead Operations (2019), Member (2018, 2020) - we're a team of volunteers organizing TEDx-style events at the TU Munich with up to 600 guests to give local and novel ideas a stage
  • Volunteering for different organizations, for example the Karate World Championship in Austria (2016) or at the Bits & Pretzels Startup Festival in Munich (2018)

Toolkit

Fluent in C and Python, Basics in C++ and Java

I have built and trained models with Keras and Tensorflow, utilized Docker to deploy models for medical image segmentation and use Git to keep everything under version control. I'm used to working in fast paced environments and get things done efficiently. I use my interdisciplinary background in engineering, natural sciences and computer science to see solutions others wouldn't see. All while being able to communicate state-of-the-art research in simple and accessible terms as it is key for efficient collaboration in multidisciplinary teams.