Fast Segmentation From Blurred Data in 3D Fluorescence Microscopy

Storath, Martin; Rickert, Dennis; Unser, Michaël; Weinmann, Andreas

doi:10.1109/tip.2017.2716843

Cited by 12 publications

(5 citation statements)

References 69 publications

(108 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Staircase artifacts (Knoll et al 2011) have been observed in the reconstruction results of TSD-FISTA. Previous research has shown that incorporating operation directions and utilizing isotropic discretization can lead to improved reconstruction quality in 3D fluorescence microscopy (Storath et al 2017). However, our analysis in appendix E suggests that implementing TSD-FISTA with 13 isotropic-discretization operation directions does not yield significant improvements in MPI reconstruction quality compared to TSD-FISTA with 3 operation directions.…”

Section: Discussionmentioning

confidence: 60%

See 1 more Smart Citation

A fused LASSO operator for fast 3D magnetic particle imaging reconstruction

He,

Li,

Zhang

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. Magnetic particle imaging (MPI) is a promising imaging modality that leverages the nonlinear magnetization behavior of superparamagnetic iron oxide nanoparticles to determine their concentration distribution. Previous optimization models with multiple regularization terms have been proposed to achieve high-quality MPI reconstruction, but these models often result in increased computational burden, particularly for dense gridding 3D fields of view. In order to achieve faster reconstruction speeds without compromising reconstruction quality, we have developed a novel fused LASSO operator, total sum-difference (TSD), which effectively captures the sparse and smooth priors of MPI images. Methods. Through an analysissynthesis equivalence strategy and a constraint smoothing strategy, the TSD regularized model was solved using the fast iterative soft-thresholding algorithm (FISTA). The resulting reconstruction method, TSD-FISTA, boasts low computational complexity and quadratic convergence rate over iterations. Results. Experimental results demonstrated that TSD-FISTA required only 10% and 37% of the time to achieve comparable or superior reconstruction quality compared to commonly used fused LASSO-based ADMM and Tikhonov-based algebraic reconstruction techniques, respectively. Significance. TSD-FISTA shows promise for enabling real-time 3D MPI reconstruction at high frame rates for large fields of view.

show abstract

Section: Discussionmentioning

confidence: 60%

“…The 3 operation directions in ( 21) can be extended to 13 operation directions for almost isotropic discretization (Storath et al 2016(Storath et al , 2017)…”

Section: Data Availability Statementmentioning

confidence: 99%

A fused LASSO operator for fast 3D magnetic particle imaging reconstruction

He,

Li,

Zhang

et al. 2024

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

“…The piecewise-constant assumption holds in many CT imaging problems such as industrial inspection [33], [34] or assessment of bone microstructure in medicine [35], [36]. Many different priors are possible for such volumes, such as minimum L 0norm [13], [37], sparse Haar transform [16], or Gauss-Markov-Potts prior [14].…”

Section: Combination With Gauss-markov-potts Prior Model On the Vmentioning

confidence: 99%

“…Moreover, Gauss-Markov-Potts prior allows variability in the classes thanks to the introduction of variances v. Another Potts model, which promotes minimum L 0 -norm for the gradient of the volume, is used in [13] for CT. The reconstruction algorithm in [13] is an instance of ADMM [42], and performs a variable-splitting in each direction used to compute the gradient : as a result, it requires more memory than the reconstruction algorithm proposed in [14], and has been only applied to small volumes in 3D [37].…”

Section: Combination With Gauss-markov-potts Prior Model On the Vmentioning

confidence: 99%

Error-Splitting Forward Model for Iterative Reconstruction in X-Ray Computed Tomography and Application With Gauss–Markov–Potts Prior

Chapdelaine

Mohammad-Djafari

Gac

et al. 2019

IEEE Trans. Comput. Imaging

View full text Add to dashboard Cite

In order to enhance image quality for controlling the interior of a volume in industry, model-based iterative reconstruction (MBIR) methods in 3D X-ray Computed Tomography (CT) have shown their efficiency compared to analytical reconstruction methods. MBIR methods enforce a prior model on the volume to reconstruct and make fusion of the information contained in the prior model and the projection data. The projections have many uncertainties which have very different origins in 3D CT. They are taken into account in MBIR methods but, despite of their different origins, they are in general gathered in only one term in the forward model. In this paper, we propose to derive a new forward model by adding a further error term in the Poisson statistics of photon-count, corresponding to the deviation of the monochromatic model with respect to the actual polychromacy of the rays. A Taylor expansion of the Poisson log-likelihood leads us to a new algebraic forward model accounting for two terms of uncertainties : we call it the errorsplitting forward model. Different prior models are assigned to each of distinguished uncertainties : measurement uncertainties are modeled as Gaussian, while linear model uncertainties are modeled as heavy-tailed to bring robustness to the reconstruction process. We give strategies to fix the parameters of the errorsplitting forward model. Next, we use it in a full MBIR method with Gauss-Markov-Potts prior model on the volume, in order to reconstruct piecewise-constant objects for non-destructive testing in industry. Compared to the conventional forward model, we show in our experiments that the use of the error-splitting forward model with Gauss-Markov-Potts prior combines better robustness and accuracy.

show abstract

“…Finding u given g as in ( 1) is an ill-posed (under-determined) inverse problem whose solution requires the use of suitable regularization. In a variety of works [12,13,11,4], Storath et al considered the inverse Potts regularization model for joint image restoration and segmentation. Heuristically, such approach is based on the use of a penalized regularization functional defined in terms of an 0type gradient smoothing prior reducing noise and preserving distinctive details (such as image edges).…”

Section: Introductionmentioning

confidence: 99%

Constrained and Unconstrained Inverse Potts Modelling for Joint Image Super-Resolution and Segmentation

Mylonopoulos¹,

Cascarano²,

Calatroni³

et al. 2022

Image Processing on Line

View full text Add to dashboard Cite

In this work we consider two methods for joint single-image super-resolution and image partitioning. The proposed approaches rely on a constrained and on an unconstrained version of the inverse Potts model where an 0 regularization prior on the image gradient is used for promoting piecewise constant solutions. For the numerical solution of both models, we provide a unified implementation based on the Alternating Direction Method of Multipliers (ADMM). Upon suitable assumptions on both model operators and on the algorithmic parameters involved, we show that all the ADMM subproblems admit closed-form solutions, thus making the resulting algorithms computationally very cheap even when high-dimensional data are considered. Numerical details of the implementation of both models are given and several experiments are carried out on both synthetic and natural images to underline the accuracy and the computational efficiency of the models. Source CodeThe Matlab source code, the code online documentation and the online demo are available from the web page of this article 1 . Compilation and usage instruction are included in the README.txt file of the archive.

show abstract

Fast Segmentation From Blurred Data in 3D Fluorescence Microscopy

Cited by 12 publications

References 69 publications

A fused LASSO operator for fast 3D magnetic particle imaging reconstruction

A fused LASSO operator for fast 3D magnetic particle imaging reconstruction

Error-Splitting Forward Model for Iterative Reconstruction in X-Ray Computed Tomography and Application With Gauss–Markov–Potts Prior

Constrained and Unconstrained Inverse Potts Modelling for Joint Image Super-Resolution and Segmentation

Contact Info

Product

Resources

About