Michael Goetz
German Cancer Research Center
5 Papers
26 Citations
Michael Goetz is an academic researcher from German Cancer Research Center. The author has contributed to research in topics: Image segmentation & Adaptive learning. The author has an hindex of 3, co-authored 5 publications.
Chat about Author
Papers
MiMSeg - an algorithm for automated detection of tumor tissue on NMR apparent diffusion coefficient maps.
Franciszek Binczyk,Bram Stjelties,Christian Weber,Michael Goetz,Klaus Meier-Hein,Hans Peter Meinzer,Barbara Bobek-Billewicz,Rafal Tarnawski,Joanna Polanska +8 more
TL;DR: The proposed methodology is a combination of classical decomposition of ADC distribution into a Gaussian mixture model (GMM) with k-means clustering subsequently performed on the parameters of mixture model components, leading to the identification of ADC distributions for every tissue type.
25
Machine-learning based comparison of CT-perfusion maps and dual energy CT for pancreatic tumor detection
Michael Goetz,Stephan Skornitzke,Christian Weber,Franziska Fritz,Philipp Mayer,Marco Koell,Wolfram Stiller,Klaus H. Maier-Hein +7 more
TL;DR: The use of a machine learning algorithm for assessing the amount of information that becomes available by the combination of multiple images is proposed, and Dual Energy Iodine maps might be used for diagnosis of pancreatic tumors instead of Perfusion CT, although the detection rate is lower.
7
A learning-based, fully automatic liver tumor segmentation pipeline based on sparsely annotated training data
Michael Goetz,Eric Heim,Keno Maerz,Tobias Norajitra,Mohammadreza Hafezi,Nassim Fard,Arianeb Mehrabi,Max Knoll,Christian Weber,Lena Maier-Hein,Klaus H. Maier-Hein +10 more
TL;DR: A new algorithm for liver tumor segmentation that allows incorporating different CT scans and requires no manual interaction is presented and derives a liver segmentation with state-of-the-art shape models which are robust to initialization.
6
Input Data Adaptive Learning (IDAL) for Sub-acute Ischemic Stroke Lesion Segmentation
Michael Goetz,Christian Weber,Christoph Kolb,Klaus H. Maier-Hein +3 more
- 05 Oct 2015
TL;DR: A method for learning from a large training base by adaptively selecting optimal training samples for given input data and leading to a significant improvement of the classification accuracy is presented.
3
DALSA: Domain Adaptation for Supervised Learning From Sparsely Annotated MR Images
Michael Goetz,Christian Weber,Franciszek Binczyk,Joanna Polanska,Rafal Tarnawski,Barbara Bobek-Billewicz,Ullrich Koethe,Jens Kleesiek,Bram Stieltjes,Klaus H. Maier-Hein +9 more
TL;DR: A new method is proposed that employs transfer learning techniques to effectively correct sampling selection errors introduced by sparse annotations during supervised learning for automated tumor segmentation and dramatically eases the establishment and constant extension of large annotated databases in various scenarios and imaging setups.