Deep probabilistic tracking of particles in fluorescence microscopy images |
| |
| Affiliation: | 1. Biomedical Computer Vision Group, Heidelberg University, BioQuant, IPMB, and DKFZ Heidelberg, Heidelberg 69120, Germany;2. Department of Infectious Diseases, Molecular Virology, Heidelberg University, Heidelberg 69120, Germany;3. German Center for Infection Research, Heidelberg Partner Site;4. Cell Biology and Epigenetics, Department of Biology, Technische Universität Darmstadt, Darmstadt 64287, Germany;5. Institute of Cytology, Russian Academy of Sciences, St. Petersburg, Russia;6. Micron Advanced Bioimaging Unit, Department of Biochemistry, University of Oxford, Oxford OX1 3QU, United Kingdom;1. Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA;2. Applied Physics Laboratory, Johns Hopkins University, Laurel, MD, USA;3. Department of Orthopedic Surgery, Johns Hopkins Hospital, Baltimore, USA;4. Laboratory for Computer Aided Medical Procedures, Technical University of Munich, Munich, Germany;1. Department of Advanced Information Technology, Kyushu University, Fukuoka, Japan;2. Research Center for Medical Bigdata, National Institute of Informatics, Tokyo, Japan;3. Department of Gastroenterology, Kyoto Second Red Cross Hospital, Kyoto, Japan;1. School of Computer Science and Engineering, The Hebrew University of Jerusalem, Israel;2. Department of Ophthalmology, Hadassah Medical Center, Jerusalem, Israel |
| |
| Abstract: | Tracking of particles in temporal fluorescence microscopy image sequences is of fundamental importance to quantify dynamic processes of intracellular structures as well as virus structures. We introduce a probabilistic deep learning approach for fluorescent particle tracking, which is based on a recurrent neural network that mimics classical Bayesian filtering. Compared to previous deep learning methods for particle tracking, our approach takes into account uncertainty, both aleatoric and epistemic uncertainty. Thus, information about the reliability of the computed trajectories is determined. Manual tuning of tracking parameters is not necessary and prior knowledge about the noise statistics is not required. Short and long-term temporal dependencies of individual object dynamics are exploited for state prediction, and assigned detections are used to update the predicted states. For correspondence finding, we introduce a neural network which computes assignment probabilities jointly across multiple detections as well as determines the probabilities of missing detections. Training requires only simulated data and therefore tedious manual annotation of ground truth is not needed. We performed a quantitative performance evaluation based on synthetic and real 2D as well as 3D fluorescence microscopy images. We used image data of the Particle Tracking Challenge as well as real time-lapse fluorescence microscopy images displaying virus structures and chromatin structures. It turned out that our approach yields state-of-the-art results or improves the tracking results compared to previous methods. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
