Few-Views Image Reconstruction with SMART and an Allowance for Contrast Structure Shadows

Vlasov, Vitaly V.; Konovalov, Alexander; Uglov, Alexander S.

doi:10.1007/978-3-319-23192-1_56

Cited by 7 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where μ and Δ μ are the mean and the root-mean-square deviation calculated over all R cells of the image, and the indices "src" and "tom" refer to the initial phantom and the reconstructed image, respectively. Our experience (see, eg, 60,74,76 ) reveals that these characteristics are suitable and effective for use in cases where the initial phantom is known. If k cor is close to unity, then the initial phantom and the reconstructed image are in strong correlation pointing to high reconstruction accuracy.…”

Section: Results and Their Discussionmentioning

confidence: 96%

“…As quantitative characteristics which can be used to evaluate initial phantom reconstruction accuracy, we took the correlation coefficient k cor and the deviation factor k dev :

k_{cor} = \frac{\sum_{r = 1}^{R} ((), μ_{j}^{tom} - {\overset{false¯}{μ}}^{tom}) ((), μ_{j}^{src} - {\overset{false¯}{μ}}^{src})}{((), R - 1) normalΔ μ^{tom} normalΔ μ^{src}}

k_{dev} = \frac{\sqrt{\frac{1}{R} {false\sum}_{r = 1}^{R} {((), μ_{j}^{tom} - μ_{j}^{src})}^{2}}}{normalΔ μ^{src}},

where

\overset{μ}{true}

and Δ μ are the mean and the root‐mean‐square deviation calculated over all R cells of the image, and the indices “ src ” and “ tom ” refer to the initial phantom and the reconstructed image, respectively. Our experience (see, eg, 60,74,76 ) reveals that these characteristics are suitable and effective for use in cases where the initial phantom is known. If k cor is close to unity, then the initial phantom and the reconstructed image are in strong correlation pointing to high reconstruction accuracy.…”

Section: Numerical Experiments On Fluorescent Image Reconstructionmentioning

confidence: 95%

“…However, in the last years the CS‐like algorithms 10,22,25‐34 have begun to seriously compete with it. We have gained rich experience of successful ART application both in DOT 52,53,64‐66 and in limited‐data X‐ray computed tomography 73,74 . Our attempts to use ART in combination with L p regularization (0 ≤ p ≤ 1) also refer to the same tomography applications 60,75,76 .…”

Section: Numerical Experiments On Fluorescent Image Reconstructionmentioning

confidence: 99%

“…We have gained rich experience of successful ART application both in DOT 52,53,[64][65][66] and in limited-data X-ray computed tomography. 73,74 Our attempts to use ART in combination with L p regularization (0 ≤ p ≤ 1) also refer to the same tomography applications. 60,75,76 In this paper we try to apply our experience to EP-FMT and consider two ART-based CS-like algorithms: ART with TV regularization, ART-TV 59,60 and ART with fast iterative shrinkage-thresholding, ART-FIST that is a modification of the well-known fast iterative shrinkagethresholding algorithm FISTA.…”

Section: Reconstruction Algorithmsmentioning

confidence: 99%

See 3 more Smart Citations

Early‐photon reflectance fluorescence molecular tomography for small animal imaging: Mathematical model and numerical experiment

Konovalov

Vlasov

Uglov

2020

Numer Methods Biomed Eng

Self Cite

View full text Add to dashboard Cite

The paper presents an original approach to time‐domain reflectance fluorescence molecular tomography (FMT) of small animals. It is based on the use of early arriving photons and state‐of‐the‐art compressed‐sensing‐like reconstruction algorithms and aims to improve the spatial resolution of fluorescent images. We deduce the fundamental equation that models the imaging operator and derive analytical representations for the sensitivity functions which are responsible for the reconstruction of the fluorophore absorption coefficient. The idea of fluorescence lifetime tomography with our approach is also discussed. We conduct a numerical experiment on 3D reconstruction of box phantoms with spherical fluorescent inclusions of small diameters. For modeling measurement data and constructing the sensitivity matrix we assume a virtual fluorescence tomograph with a scanning fiber probe that illuminates and collects light in reflectance geometry. It provides for large source‐receiver separations which correspond to the macroscopic regime. Two compressed‐sensing‐like reconstruction algorithms are used to solve the inverse problem. These are the algebraic reconstruction technique with total variation regularization and our modification of the fast iterative shrinkage‐thresholding algorithm. Results of our numerical experiment show that our approach is capable of achieving as good spatial resolution as 0.2 mm and even better at depths to 9 mm inclusive.

show abstract

Section: Results and Their Discussionmentioning

confidence: 96%

“…As quantitative characteristics which can be used to evaluate initial phantom reconstruction accuracy, we took the correlation coefficient k cor and the deviation factor k dev :

k_{cor} = \frac{\sum_{r = 1}^{R} ((), μ_{j}^{tom} - {\overset{false¯}{μ}}^{tom}) ((), μ_{j}^{src} - {\overset{false¯}{μ}}^{src})}{((), R - 1) normalΔ μ^{tom} normalΔ μ^{src}}

k_{dev} = \frac{\sqrt{\frac{1}{R} {false\sum}_{r = 1}^{R} {((), μ_{j}^{tom} - μ_{j}^{src})}^{2}}}{normalΔ μ^{src}},

where

\overset{μ}{true}

Section: Numerical Experiments On Fluorescent Image Reconstructionmentioning

confidence: 95%

Section: Numerical Experiments On Fluorescent Image Reconstructionmentioning

confidence: 99%

Section: Reconstruction Algorithmsmentioning

confidence: 99%

See 2 more Smart Citations

Early‐photon reflectance fluorescence molecular tomography for small animal imaging: Mathematical model and numerical experiment

Konovalov

Vlasov

Uglov

2020

Numer Methods Biomed Eng

Self Cite

View full text Add to dashboard Cite

show abstract

“…In the tomographic reconstruction community, numerous studies have focused on algebraic approaches to inverse problems, in particular utilizing Algebraic Reconstruction Techniques (ART) and its variants such as Multiplicative ART (MART). Examples include the work on MART-AP [20] and simultaneous MART [31]. Further, Chen et al proposed an adaptive Non-Local Means (NLM) based reconstruction method to compensate for over-smoothed image edges in few-view reconstructions [6].…”

Section: Other Related Workmentioning

confidence: 99%

Lose the Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion

Anirudh

Kim

Thiagarajan

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Computed Tomography (CT) reconstruction is a fundamental component to a wide variety of applications ranging from security, to healthcare. The classical techniques require measuring projections, called sinograms, from a full 180°view of the object. However, obtaining a full-view is not always feasible, such as when scanning irregular objects that limit flexibility of scanner rotation. The resulting limited angle sinograms are known to produce highly artifact-laden reconstructions with existing techniques. In this paper, we propose to address this problem using CTNet -a system of 1D and 2D convolutional neural networks, that operates directly on a limited angle sinogram to predict the reconstruction. We use the x-ray transform on this prediction to obtain a "completed" sinogram, as if it came from a full 180°view. We feed this to standard analytical and iterative reconstruction techniques to obtain the final reconstruction. We show with extensive experimentation on a challenging real world dataset that this combined strategy outperforms many competitive baselines. We also propose a measure of confidence for the reconstruction that enables a practitioner to gauge the reliability of a prediction made by CTNet. We show that this measure is a strong indicator of quality as measured by the PSNR, while not requiring ground truth at test time. Finally, using a segmentation experiment, we show that our reconstruction also preserves the 3D structure of objects better than existing solutions.

show abstract

Minimizing the Number of Views in Few-View Computed Tomography: a Deep Learning Approach

Vlasov

Konovalov

2022

2022 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)

View full text Add to dashboard Cite

Few-Views Image Reconstruction with SMART and an Allowance for Contrast Structure Shadows

Cited by 7 publications

References 17 publications

Early‐photon reflectance fluorescence molecular tomography for small animal imaging: Mathematical model and numerical experiment

Early‐photon reflectance fluorescence molecular tomography for small animal imaging: Mathematical model and numerical experiment

Lose the Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion

Minimizing the Number of Views in Few-View Computed Tomography: a Deep Learning Approach

Contact Info

Product

Resources

About