Instance-Level Microtubule Tracking

  title={Instance-Level Microtubule Tracking},
  author={Samira Masoudi and Afsaneh Razi and Cameron H. G. Wright and Jay C. Gatlin and Ulas Bagci},
  journal={IEEE Transactions on Medical Imaging},
We propose a new method of instance-level microtubule (MT) tracking in time-lapse image series using recurrent attention. Our novel deep learning algorithm segments individual MTs at each frame. Segmentation results from successive frames are used to assign correspondences among MTs. This ultimately generates a distinct path trajectory for each MT through the frames. Based on these trajectories, we estimate MT velocities. To validate our proposed technique, we conduct experiments using real and… Expand
A survey on applications of deep learning in microscopy image analysis
The applications of deep learning algorithms in microscopy image analysis, which include image classification, region segmentation, object tracking and super-resolution reconstruction, are introduced. Expand
Automated and semi-automated enhancement, segmentation and tracing of cytoskeletal networks in microscopic images: A review
A short summary of the research on the (semi-)automated enhancement, segmentation and tracing methods that are particularly designed and developed for microscopic images of cytoskeletal networks, and covers the recently introduced, deep-learning-assisted methods alongside the advantages they offer over classical methods. Expand


Deep neural networks for data association in particle tracking
A novel approach to data association for particle tracking applications based on deep neural networks that learns particle behavior from the data, and based on this it determines how to best extend trajectories from one frame to the next. Expand
Microtubule Dynamics Analysis Using Kymographs and Variable-Rate Particle Filters
A new probabilistic method is proposed to segment the traces of the moving objects in kymograph representations of the image data based on variable-rate particle filtering and uses multiscale trend analysis of the extracted traces to estimate the relevant kinematic parameters. Expand
plusTipTracker: Quantitative image analysis software for the measurement of microtubule dynamics.
The algorithm underlying the reconstruction of full MT trajectories relies on the spatially and temporally global tracking framework described in Jaqaman et al. (2008) and the numerical methods and analytical functionality incorporated in plusTipTracker substantially advance this previous work in terms of flexibility and robustness. Expand
Recurrent Instance Segmentation
This work proposes a new instance segmentation paradigm consisting in an end-to-end method that learns how to segment instances sequentially, based on a recurrent neural network that sequentially finds objects and their segmentations one at a time. Expand
Particle Filtering for Multiple Object Tracking in Dynamic Fluorescence Microscopy Images: Application to Microtubule Growth Analysis
This work proposes an improved, completely automatic tracker, built within a Bayesian probabilistic framework, that better exploits spatiotemporal information and prior knowledge than common approaches, yielding more robust tracking also in cases of photobleaching and object interaction. Expand
Aggregation of patch-based estimations for illumination-invariant optical flow in live cell imaging
This work presents a novel optical flow estimation method based on a two-stage aggregation framework and demonstrates its ability to outperform state-of-the-art methods in challenging cases frequently arising in live cell imaging. Expand
Multiple Microtubule Tracking in Microscopy Time-Lapse Images Using Piecewise-stationary Multiple Motion Model Kalman Smoother
This work describes a new application of piecewise-stationary multiple motion model Kalman smoother (PMMS) for modeling individual microtubules motility trends and provides a quantitative description of microtubule velocity which, in turn, enumerates the occurrence of micro Tubule-microtubule interactions per frame. Expand
Tracking Multiple Particles in Fluorescence Time-Lapse Microscopy Images via Probabilistic Data Association
This work has developed an approach for tracking multiple fluorescent particles based on probabilistic data association that combines a localization scheme that uses a bottom-up strategy based on the spot-enhancing filter as well as a top-down strategy that uses the Gaussian probability distributions computed by a Kalman filter. Expand
Multiple Hypothesis Tracking for Cluttered Biological Image Sequences
The proposed method for simultaneously tracking thousands of targets in biological image sequences, which is of major importance in modern biology, is presented and the benefits of advanced Bayesian tracking techniques for the accurate computational modeling of dynamical biological processes are demonstrated. Expand
Multiple-target tracking of 3D fluorescent objects based on simulated annealing
This paper presents a framework for tracking fluorescent objects imaged with 3D+time video-microscopy and uses the simulated annealing algorithm for its flexibility for feature correspondence and its ability to give results in a very short time. Expand