Sparse-view tomography via displacement function interpolation

Zeng, G.L.

doi:10.1186/s42492-019-0024-7

Cited by 6 publications

(4 citation statements)

References 26 publications

(33 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These numbers are chosen for ease in viewing artifacts. According to Zeng [20], for a scan using 896 detectors, measurements from 1200 views over 360° are considered as a full sinogram, and measurements from 400 views over 360° are considered as an under-sampled sinogram.…”

Section: Sinograms and Ct Image Reconstructionmentioning

confidence: 99%

See 1 more Smart Citation

Sinogram Interpolation Inspired by Single-Image Super Resolution

Christiansen,

Zeng

2023

J Biotechnology App

View full text Add to dashboard Cite

Computed tomography is a medical imaging procedure used to estimate the interior of a patient or an object. Radiation scans are taken at regularly spaced angles around the object, forming a sinogram. This sinogram is then reconstructed into an image representing the contents of the object. This results in a fair amount of radiation exposure for the patient, which increases the risk of cancer. Less radiation and fewer views, however, leads to inferior image reconstruction. To solve this sparse-view problem, a deep-learning model is created that takes as input a sparse sinogram and outputs a sinogram with interpolated data for additional views. The architecture of this model is based on the super-resolution convolutional neural network. The reconstruction of modelinterpolated sinograms has less mean-squared error than the reconstruction of the sparse sinogram. It also has less mean-squared error than a reconstruction of a sinogram interpolated using the popular bilinear image-resizing algorithm. This model can be easily adapted to different image sizes, and its simplicity translates into efficiency in both time and memory requirements.

show abstract

Section: Sinograms and Ct Image Reconstructionmentioning

confidence: 99%

“…A few of the current models are the Super-Resolution Convolutional Neural Network (SRCNN) [11], residual models including MSRN [12,13] and EDSR [14], and the inception model [15]. There are other ways to extend the sparse data such analytic extension [22,23], deformation [24], nonlinear filtering [25], and so on.…”

Section: Introductionmentioning

confidence: 99%

Sinogram Interpolation Inspired by Single-Image Super Resolution

Christiansen,

Zeng

2023

J Biotechnology App

View full text Add to dashboard Cite

show abstract

“…Constraints are vital in shrinking the solution space [4]. Iterative algorithms are better than analytical algorithms when the imaging system is under-determined [5][6][7][8][9]. The total-variation (TV) norm of the gradient of an image is a good indicator for the piecewise-constant feature of the image.…”

Section: Introductionmentioning

confidence: 99%

Extreme Few-View Tomography without Training Data

L Zeng

2024

BJSTR

View full text Add to dashboard Cite

There are fewer than 10 projection views in extreme few-view tomography. The state-of-the-art methods to reconstruct images with few-view data are compressed sensing based. Compressed sensing relies on a sparsification transformation and total variation (TV) norm minimization. However, for the extreme fewview tomography, the compressed sensing methods are not powerful enough. This paper seeks additional information as extra constraints so that extreme few-view tomography becomes possible. In transmission tomography, we roughly know the linear attenuation coefficients of the objects to be imaged. We can use these values as extra constraints. Computer simulations show that these extra constraints are helpful and improve the reconstruction quality.

show abstract

“…When a limited number of X-ray projections are available, simple sinogram interpolation algorithms (e.g. linear view interpolation) are not able to generate meaningful projections and introduce rotational artefacts in the reconstruction domain [6]. To mitigate this, Lee et al proposed a deep learning sinogram synthesis algorithm to improve the sinogram after applying a linear view interpolation [7].…”

Section: Introductionmentioning

confidence: 99%

A machine learning supported sinogram interpolation method for X-ray computed tomography

Bellens¹,

Janssens²,

Vandewalle³

et al. 2023

eJNDT

View full text Add to dashboard Cite

The time of an X-ray Computed Tomography (XCT) measurement is directly affected by the number of acquired X-ray projections. In general, a large number of X-ray projections, hence a large acquisition time is required to obtain a qualitative reconstruction and successive feature analysis. To expand the applicability of XCT towards low-end parts we propose a novel sinogram interpolation method that incorporates the object rotation. The method combines a forward projection model of the XCT system and a deep learning regression model to generate intermediate X-ray projections for XCT scans with a reduced number of projections. Thereby, the accompanying reconstruction artefacts can be reduced while preserving a lower acquisition time. The method is validated on simulated projections of the 3D Shepp-Logan phantom and simulated projections of real 3D printed components using the ASTRA-toolbox. Within the reconstructions, less streaking artefacts are observed and an increased contrast between different features is obtained without introducing rotational artefacts.

show abstract

Sparse-view tomography via displacement function interpolation

Cited by 6 publications

References 26 publications

Sinogram Interpolation Inspired by Single-Image Super Resolution

Sinogram Interpolation Inspired by Single-Image Super Resolution

Extreme Few-View Tomography without Training Data

A machine learning supported sinogram interpolation method for X-ray computed tomography

Contact Info

Product

Resources

About