Timo Löhr, M.Sc.
Image-Based Biomedical Modeling Group (Prof. Dr. Bjoern Menze)PhD candidate
Office
Center for Translational Cancer Research (TranslaTUM)
Klinikum rechts der Isar, Trogerstr 1, 81675 Munich
[my firstname].loehr@tum.de
Research Focus
My research interest is motivated by the unexploited potential of MR image analysis based on Deep Learning methodologies. Especially the extraction of information relevant to the diagnosis and prognosis of Multiple Sclerosis and the longitudinal prediction of the disease course is at the core of my studies. This includes the development of Deep Learning techniques in order to not only detect, localize and segment lesions in human brain scans, but also model and predict the future progression. Simultaneously, I'm interested in novel Deep Learning methods, such as Graph Learning/Geometric Deep Learning, tackling state-of-the-art challenges in biomedical imaging.
Center for Translational Cancer Research (TranslaTUM)
Klinikum rechts der Isar, Trogerstr 1, 81675 Munich
[my firstname].loehr@tum.de
Research Focus
My research interest is motivated by the unexploited potential of MR image analysis based on Deep Learning methodologies. Especially the extraction of information relevant to the diagnosis and prognosis of Multiple Sclerosis and the longitudinal prediction of the disease course is at the core of my studies. This includes the development of Deep Learning techniques in order to not only detect, localize and segment lesions in human brain scans, but also model and predict the future progression. Simultaneously, I'm interested in novel Deep Learning methods, such as Graph Learning/Geometric Deep Learning, tackling state-of-the-art challenges in biomedical imaging.
Projects for students
We are inviting applications for several exciting research opportunities for students with our group. Please also feel free to reach out if you are interested in a Bachelor thesis, research project, etc. The projects are intended for students in Informatics, Electrical Engineering, or related fields. Please refer to the project descriptions below for more detailed information.We expect all students to have:
- Prior theoretical knowledge on deep learning
- Some practical experience with deep learning (PyTorch or TensorFlow)
- Good Python coding skills
- Ideally experience in computer vision / medical image analysis
Deep supervision loss for MS lesion segmentation in MRI brain images
Improving lesion segmentation by adapting novel centerline dice loss
Detection and Segmentation of MS lesions in longitudinal MRI data
Longitudinal analysis of MS lesions based on radiomic image features
Background
- since 2020: Ph.D. candidate at IBBM group (TU Munich) with Prof. Dr. Bjoern Menze and TUM Neuroradiology (Klinikum rechts der Isar)
- 2020: M.Sc. in Computer Science from TU Munich
- 2016: B.Sc. in Computer Science from TU Dortmund
Publications
- Li, H., Loehr, T., Sekuboyina, A., Zhang, J., Wiestler, B., & Menze, B. e-UDA: Efficient Unsupervised Domain Adaptation for Cross-Site Medical Image Segmentation. 2020
- Löhr, T., Li, H. & Menze, B. A Multi-View Approach for Automatic Segmentation of Intracranial Aneurysms from Time of Flight MRAs. 2020
Google Scholar profile
| UsersForm | |
|---|---|
| Title: | M.Sc. |
| Circumference of your head (in cm): | |
| Firstname: | Timo |
| Middlename: | |
| Lastname: | Löhr |
| Picture: | |
| Birthday: | |
| Nationality: | Germany |
| Languages: | English, German, French |
| Groups: | Image-Based Biomedical Modeling |
| Expertise: | Segmentation, Medical Imaging, Computer Vision |
| Position: | Scientific Staff |
| Status: | Active |
| Emailbefore: | timo.loehr |
| Emailafter: | tum.de |
| Room: | |
| Telephone: | |
| Alumniactivity: | |
| Defensedate: | |
| Thesistitle: | |
| Alumnihomepage: | |
| Personalvideo01: | |
| Personalvideotext01: | |
| Personalvideopreview01: | |
| Personalvideo02: | |
| Personalvideotext02: | |
| Personalvideopreview02: | |
