Erik Gösche
Professorship for Computational Imaging
Research associates
Contact
- Email: erik.goesche@fau.de
Office hours
by appointment
Research field
I am specializing in the development of deep learning algorithms for MRI reconstruction. My research focuses on creating advanced techniques to improve the quality and usability of dynamic contrast-enhanced MRI (DCE-MRI) for breast imaging.
I am happy to supervise motivated students for a project or thesis who have already gained first experience in the field of MRI reconstruction. Feel free to contact me!
- Since 02/2024
Ph.D. Candidate at Computational Imaging Lab, Friedrich-Alexander-Universität Erlangen-Nürnberg - 10/2021 – 11/2023
M.Sc. in Data Science at Friedrich-Alexander-Universität Erlangen-Nürnberg
Thesis: “Attention-based networks for brain segmentation in k-space”, written at University of California, San Francisco - 10/2018 – 09/2021
B.Sc. in Applied Computer Science at University of Applied Sciences Mittweida
Thesis: “Object detection as a pre-processing step for segmentation of people”, written at Volkswagen Sachsen GmbH, Zwickau
- Computational Complexity Exercise (WiSe)
- Medizintechnik II Tafelübung (SoSe)
- Seminar: Machine Learning in MRI (WiSe/SoSe)
| Student | Title | Type |
|---|---|---|
| Alen Jose Anto | RadRecon: A Self-Supervised Framework for Radial MRI Reconstruction Using ESPIRiT-Based Sensitivity Maps | Master’s Thesis |
| Christopher Brückner | Self-supervised VarNet with ROVir-Based Focused Loss for MRI Reconstruction | Master’s Thesis |
| Nguyen Anh Mai | Comparative Literature Review of DCE MRI Analysis Frameworks and Tracer Kinetic Modeling Approaches | Project |
| Ximeng Zhang | Comparative Literature Review of DCE MRI Analysis Frameworks and Tracer Kinetic Modeling Approaches | Master’s Thesis |
| Alen Jose Anto | Comparison of non-uniform Fast Fourier Transform implementations using DCE MRI data | Project |