Authors:
Nabeel Khalid
1
;
2
;
Mohammadmahdi Koochali
2
;
Khola Naseem
1
;
2
;
Maria Caroprese
3
;
Gillian Lovell
4
;
Daniel A. Porto
5
;
Johan Trygg
6
;
7
;
Andreas Dengel
1
;
2
and
Sheraz Ahmed
2
Affiliations:
1
RPTU Kaiserslautern–Landau, 67663 Kaiserslautern, Germany
;
2
German Research Center for Artificial Intelligence (DFKI) GmbH, 67663 Kaiserslautern, Germany
;
3
Sartorius Digital Solutions, Royston, U.K.
;
4
Sartorius BioAnalytics, Royston, U.K.
;
5
Sartorius BioAnalytics, Ann Arbor, U.S.A
;
6
Sartorius Corporate Research, Umeå, Sweden
;
7
Computational Life Science Cluster (CLiC), Umeå University, Umeå, Sweden
Keyword(s):
Biomedical, Healthcare, Deep Learning, Cell Segmentation, Cell Tracking, Segment Anything, Track Anything, Microscopy.
Abstract:
Integrating cell segmentation with tracking is critical for achieving a detailed and dynamic understanding of cellular behavior. This integration facilitates the study and quantification of cell morphology, movement, and interactions, offering valuable insights into a wide range of biological processes and diseases. However, traditional methods rely on labor-intensive and costly annotations, such as full segmentation masks or bounding boxes for each cell. To address this limitation, we present SAT: Segment and Track Anything for Microscopy, a novel pipeline that leverages point annotations in the first frame to automate cell segmentation and tracking across all subsequent frames. By significantly reducing annotation time and effort, SAT enables efficient and scalable analysis, making it well-suited for large-scale studies. The pipeline was evaluated on two diverse datasets, achieving over 80% Multiple Object Tracking Accuracy (MOTA), demonstrating its robustness and effectiveness acr
oss various imaging modalities and cell types. These results highlight SAT’s potential to streamline biomedical research and enable deeper exploration of cellular behavior.
(More)