Research Assistant
+49 (0)40 42878 3547
E.3087
Lennart Bargsten
Curriculum Vitae
| 2018 - today | MTEC Institute / TUHH |
| 2017 - 2018 | Helmut Schmidt University |
| 2014 - 2017 | University of Hamburg (Physics, M.Sc.) |
| 2011 - 2014 | TUHH (Mechanical Engineering, B.Sc.) |
Interests
Deep learning for medical image analysis
- Focus on ultrasound and computed tomography data (2D, 3D)
- Particularly interested in methods for performance improvement of deep learning models with limited data
- Generative adversarial networks for domain adaption and style transfer
- Ultrasound simulations for data augmentation
Roles
- Research assistant
- PhD student
Publications
2020
-
L. Bargsten, K. A. Riedl, T. Wissel, F. J. Brunner, K. Schaefers, J. Sprenger, M. Grass, S. Blankenberg, M. Seiffert, A. Schlaefer
(2020).
Tailored Methods for Segmentation of Intravascular Ultrasound Images via Convolutional Neural Networks.
SPIE Medical Imaging Conference
accepted.
[BibTex]
-
M. Seemann, L. Bargsten, A. Schlaefer
(2020).
Data augmentation for computed tomography angiography via synthetic image generation and neural domain adaptation.
Current Directions in Biomedical Engineering.
6
(1),
20200015.
[Abstract] [doi] [www] [BibTex]
-
L. Bargsten, A. Schlaefer
(2020).
SpeckleGAN: a generative adversarial network with an adaptive speckle layer to augment limited training data for ultrasound image processing.
International Journal of Computer Assisted Radiology and Surgery.
15
(9),
1427-1436.
[Abstract] [doi] [www] [BibTex]
2019
-
F. Sommer, L. Bargsten, A. Schlaefer
(2019).
IVUS-Simulation for Improving Segmentation Performance of Neural Networks via Data Augmentation.
CURAC 2019 Tagungsband Reutlingen
47-51.
[Abstract] [www] [BibTex]
-
L. Bargsten, M. Wendebourg, A. Schlaefer
(2019).
Data Representations for Segmentation of Vascular Structures Using Convolutional Neural Networks with U-Net Architecture.
In Proc. 2019 41st IEEE Engineering in Medicine and Biology Society (EMBC'19) Berlin, Germany
989-992.
[Abstract] [doi] [www] [BibTex]