Sparse representation and dictionary learning penalized image reconstruction for positron emission tomography

Chen, Shuhang; Liu, Huafeng; Shi, Peng; Chen, Yunmei

doi:10.1088/0031-9155/60/2/807

Cited by 46 publications

(34 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, authors in [12] proposed an adaptive dictionary learning approach for PET image deblurring while suppressing Poisson noise effects. In [13], a reconstruction framework integrating SR and DL into a maximum likelihood estimator has been proposed for accurate and robust PET image reconstruction. Besides, dual dictionary learning has been successfully applied to biomedical imaging as well [14–16].…”

Section: Introductionmentioning

confidence: 99%

Semisupervised Tripled Dictionary Learning for Standard-Dose PET Image Prediction Using Low-Dose PET and Multimodal MRI

Wang

et al. 2017

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Objective To obtain high-quality positron emission tomography (PET) image with low-dose tracer injection, this study attempts to predict the standard-dose PET (S-PET) image from both its low-dose PET (L-PET) counterpart and corresponding magnetic resonance imaging (MRI). Methods It was achieved by patch-based sparse representation (SR), using the training samples with a complete set of MRI, L-PET and S-PET modalities for dictionary construction. However, the number of training samples with complete modalities is often limited. In practice, many samples generally have incomplete modalities (i.e., with one or two missing modalities) that thus cannot be used in the prediction process. In light of this, we develop a semi-supervised tripled dictionary learning (SSTDL) method for S-PET image prediction, which can utilize not only the samples with complete modalities (called complete samples) but also the samples with incomplete modalities (called incomplete samples), to take advantage of the large number of available training samples and thus further improve the prediction performance. Results Validation was done on a real human brain dataset consisting of 18 subjects, and the results show that our method is superior to the SR and other baseline methods. Conclusion This work proposed a new S-PET prediction method, which can significantly improve the PET image quality with low-dose injection. Significance The proposed method is favorable in clinical application since it can decrease the potential radiation risk for patients.

show abstract

Section: Introductionmentioning

confidence: 99%

Semisupervised Tripled Dictionary Learning for Standard-Dose PET Image Prediction Using Low-Dose PET and Multimodal MRI

Wang

et al. 2017

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…3) Other Applications and Variations: Later works applied dictionary learning to dynamic MRI [28], [115], [116], parallel MRI [117], and PET reconstruction [118]. An alternative Bayesian nonparametric dictionary learning approach was used for MRI reconstruction in [119].…”

Section: B Synthesis Dictionary Learning-based Approaches For Reconsmentioning

confidence: 99%

Image Reconstruction: From Sparsity to Data-Adaptive Methods and Machine Learning

2020

View full text Add to dashboard Cite

The field of medical image reconstruction has seen roughly four types of methods. The first type tended to be analytical methods, such as filtered back-projection (FBP) for X-ray computed tomography (CT) and the inverse Fourier transform for magnetic resonance imaging (MRI), based on simple mathematical models for the imaging systems. These methods are typically fast, but have suboptimal properties such as poor resolution-noise trade-off for CT. A second type is iterative reconstruction methods based on more complete models for the imaging system physics and, where appropriate, models for the sensor statistics. These iterative methods improved image quality by reducing noise and artifacts. The FDA-approved methods among these have been based on relatively simple regularization models. A third type of methods has been designed to accommodate modified data acquisition methods, such as reduced sampling in MRI and CT to reduce scan time or radiation dose. These methods typically involve mathematical image models involving assumptions such as sparsity or lowrank. A fourth type of methods replaces mathematically designed models of signals and systems with data-driven or adaptive models inspired by the field of machine learning. This paper focuses on the two most recent trends in medical image reconstruction: methods based on sparsity or low-rank models, and data-driven methods based on machine learning techniques.

show abstract

“…We conclude that our dictionary-based reconstruction method appears to have an edge over the other three methods. Our formulation in (8) enforces that the solution is an exact representation in the dictionary, and searching for solutions in the cone spanned by the dictionary elements is a strong assumption in the reconstruction formulation. In [33] we investigated this requirement experimentally and showed that relaxing the equality Πx = (I ⊗ D) does not give an advantage, i.e., approximating a solution by Πx ≈ (I ⊗ D)α and minimizing Πx − (I ⊗ D)α 2 does not improve the reconstruction quality, and one can compute a good reconstruction as a conic combination of the dictionary elements.…”

Section: Studies Of the Reconstruction Stagementioning

confidence: 99%

“…Imposing both non-negativity and a 1-norm constraint on the representation vector α are strong assumptions in the reconstruction formulation. If we drop the non-negativity constraint in the image reconstruction problem, then (8) takes the form of a constrained least squares problem:…”

Section: Simplifying the Computational Problemmentioning

confidence: 99%

Tomographic image reconstruction using training images

Soltani¹,

Andersen

Hansen

2017

Journal of Computational and Applied Mathematics

View full text Add to dashboard Cite

We describe and examine an algorithm for tomographic image reconstruction where prior knowledge about the solution is available in the form of training images. We first construct a nonnegative dictionary based on prototype elements from the training images; this problem is formulated as a regularized non-negative matrix factorization. Incorporating the dictionary as a prior in a convex reconstruction problem, we then find an approximate solution with a sparse representation in the dictionary. The dictionary is applied to non-overlapping patches of the image, which reduces the computational complexity compared to other algorithms. Computational experiments clarify the choice and interplay of the model parameters and the regularization parameters, and we show that in few-projection low-dose settings our algorithm is competitive with total variation regularization and tends to include more texture and more correct edges. * ssol@dtu.dk † mskan@dtu.dk ‡ pcha@dtu.dk

show abstract

Sparse representation and dictionary learning penalized image reconstruction for positron emission tomography

Cited by 46 publications

References 20 publications

Semisupervised Tripled Dictionary Learning for Standard-Dose PET Image Prediction Using Low-Dose PET and Multimodal MRI

Semisupervised Tripled Dictionary Learning for Standard-Dose PET Image Prediction Using Low-Dose PET and Multimodal MRI

Image Reconstruction: From Sparsity to Data-Adaptive Methods and Machine Learning

Tomographic image reconstruction using training images

Contact Info

Product

Resources

About