SKM 2023 – wissenschaftliches Programm

Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

BP: Fachverband Biologische Physik

BP 11: Poster Session I

BP 11.19: Poster

Dienstag, 28. März 2023, 12:30–15:30, P1

Semantic Segmentation for Single Particle Tracking in Noisy Data — •Mattias Luber, Mohammad Amin Eskandari, and Timo Betz — Third Institute of Physics - University of Göttingen

The quantitative analysis of particle motion critically depends on the quality of particle trajectory detection. Especially the position detection of particles in fluorescence microscopy images is an important task faced in biophysics. Trajectories are used to study processes like intra-cellular transport, protein diffusion within and through membranes and the reconstruction of force fields driving the particle motion. In such settings, high spatial and temporal resolution are desired. However, in practice those factors have contradictory measurement requirements. High temporal resolution requires short exposure times, which limits the photon budget and thus lead to low signal to noise ratios. This work proposes an approach to reconstruct the particle position from noisy images by applying U-NET based deep learning models to fluorescence microscopy images. Further it is shown that this method can successfully track particles with shorter exposure times, compared to traditional approaches.