Context aware spatio-temporal cell tracking in densely packed multilayer tissues

Chakraborty, Anirban; Roy-Chowdhury, Amit K.

doi:10.1016/j.media.2014.09.008

Cited by 25 publications

(13 citation statements)

References 27 publications

(39 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, the proposed G-snake is combined with other existing forces and applied to a very challenging problem of tracking dense biological cell populations. It is confirmed that [41] Confocal laser scan Low Dense 83.9% 83.9% [12] Phase-contrast Low Dense 97.4% 81.8% [11] Bright-field Medium Sparse n.a n.a [42] Phase-contrast Low Sparse 87.3% 84.4% [15] Confocal laser scan Low Dense 97.0% 96.8% [43] Phase-contrast Low Sparse n.a n.a Proposed Phase-contrast Low Dense 97.7% 94.5%…”

Section: Discussionmentioning

confidence: 60%

“…Also noting that, the celltracking accuracies in our work are returned by uniformly fixing the guiding-force weight κ = 1. [12], [15], [41] share a similar level of cell density and spatial resolution to us. However, we achieved higher accuracies than [12] and [41], in spite of our datasets containing more complex cell dynamics, particularly in the MDCK1 and the WH-PEC-d5 datasets.…”

Section: Comparison With Existing Cell-tracking Workmentioning

confidence: 65%

“…[12], [15], [41] share a similar level of cell density and spatial resolution to us. However, we achieved higher accuracies than [12] and [41], in spite of our datasets containing more complex cell dynamics, particularly in the MDCK1 and the WH-PEC-d5 datasets. Although a comparable accuracy is reported by [15], it is worth noting postprocessing steps as employed for reconnecting broken or early-terminated trajectories.…”

Section: Comparison With Existing Cell-tracking Workmentioning

confidence: 65%

“…Comparing with [12], [15], [41], [42], the developed system has achieved higher or comparable accuracies. To facilitate fair comparison, the statistics are precision values, i.e., the number of correct (automatically) tracked cells divided by the total number of cells as automatically identified by the corresponding system or approach.…”

Section: Comparison With Existing Cell-tracking Workmentioning

confidence: 90%

See 3 more Smart Citations

A Dynamic-Shape-Prior Guided Snake Model With Application in Visually Tracking Dense Cell Populations

Molloy

2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

This work proposes a dynamic-shape-prior guided snake model (DSP G-snake) that is designed to improve the overall stability of the point-based snake model. The dynamic shape prior is first proposed for snakes, that efficiently unifies different types of high-level priors into a new force term. To be specific, a global-topology regularity is first introduced that settles the inherent self-intersection problem with snakes. The problem that a snake's snaxels tend to unevenly distribute along the contour is also handled, leading to good parameterization. Unlike existing methods that employ learning templates or commonly enforce hard priors, the dynamic-template scheme strongly respects the deformation flexibility of the model, while retaining a decent global topology for the snake. It is verified by experiments that the proposed algorithm can effectively prevent snakes from self-crossing, or automatically untie an already selfintersected contour. In addition, the proposed model is combined with existing forces and applied to the very challenging task of tracking dense biological cell populations. The DSP G-snake model has enabled an improvement of up to 30% in tracking accuracy with respect to regular model-based approaches. Through experiments on real cellular datasets, with highly dense populations and relatively large displacements, it is confirmed that the proposed approach has enabled superior performance, in comparison to modern active-contour competitors as well as state-of-the-art cell tracking frameworks.

show abstract

Section: Discussionmentioning

confidence: 60%

Section: Comparison With Existing Cell-tracking Workmentioning

confidence: 65%

Section: Comparison With Existing Cell-tracking Workmentioning

confidence: 65%

Section: Comparison With Existing Cell-tracking Workmentioning

confidence: 90%

See 2 more Smart Citations

A Dynamic-Shape-Prior Guided Snake Model With Application in Visually Tracking Dense Cell Populations

Molloy

2019

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

show abstract

“…Then, affine transformations calculated from the supporter triplet help determine abnormal positions, where the precise position is estimated from the features of the target itself. In [9], cells were tracked in spatiotemporal optical images from densely packed multilayer tissues. The tight spatial topology of neighboring cells were exploited as contextual information by applying spatio-temporal graph labeling.…”

Section: Introductionmentioning

confidence: 99%

Robust motion tracking in liver from 2D ultrasound images using supporters

Özkan¹,

Tanner²,

Kastelic³

et al. 2017

Int J CARS

View full text Add to dashboard Cite

Purpose: Effectiveness of image-guided radiation therapy with precise dose delivery depends highly on accurate target localization, which may involve motion during treatment due to, e.g., breathing and drift. Therefore, it is important to track the motion and adjust the radiation delivery accordingly. Tracking generally requires reliable target appearance and image features, whereas in ultrasound imaging acoustic shadowing and other artifacts may degrade the visibility of a target, leading to substantial tracking errors. To minimize such errors, we propose a method based on so-called supporters, a computer vision tracking technique. This allows us to leverage information from surrounding motion for improving robustness of motion tracking on 2D ultrasound image sequences of the liver. Methods: Image features, potentially useful for predicting the target positions, are individually tracked and a supporter model capturing the coupling of motion between these features and the target is learned on-line. This model is then applied to predict the target position, when the target cannot be otherwise tracked reliably. Results: The proposed method was evaluated using the Challenge on Liver Ultrasound Tracking (CLUST)-2015 dataset. Leave-one-out cross validation was performed on the training set of 24 2D image sequences of each 1-5 minutes. The method was then applied on the test set (24 2D sequences), where the results were evaluated by the challenge organizers, yielding 1.04 mm mean and 2.26 mm 95%ile tracking error for all targets. We also devised a simulation framework to emulate acoustic shadowing artifacts from the ribs, which showed effective tracking despite the shadows. Conclusions: Results support the feasibility and demonstrate the advantages of using supporters. The proposed method improves its baseline tracker, which uses optic-flow and elliptic vessel models, and yields the state-of-the-art real-time tracking solution for the CLUST challenge.

show abstract