The primary objectives of this thesis are to become familiar with three recent methods for tracking cells in time-lapse microsocopy image data [1-3] and to investigate their behavior with respect to the quality of cell instance segmentation masks over a dataset repository of diverse microscopy imaging modalities and spatiotemporal cell characteristics. The textual part of the thesis must include a concise description of the evaluated cell tracking pipelines and of the evaluation protocol followed. The behavior of the evaluated cell tracking pipelines must be documented in a quantitative as well as qualitative fashion using performance scores and practical visual examples.

Literature:

• [1] T. Ben-Haim, T. R. Raviv. Graph neural network for cell tracking in microscopy videos. In Proceedings of the 17th European Conference on Computer Vision, 610-626 (2022).
• [2] B. Gallusser, M. Weigert. Trackastra: Transformer-based cell tracking for live-cell microscopy. In Proceedings of the 18th European Conference on Computer Vision, 467-484 (2024)
• [3] R. Reme et al. Particle tracking in biological images with optical-flow enhanced Kalman filtering. In Proceedings of the 21st IEEE International Symposium on Biomedical Imaging, 1-5 (2024).