Development of a chest digital tomosynthesis R/F system and implementation of low‐dose <scp>GPU</scp>‐accelerated compressed sensing (<scp>CS</scp>) image reconstruction

Choi, Sunghoon; Lee, Haenghwa; Lee, Dong‐Hoon; Choi, Seung-Yeon; Lee, Chang-Lae; Kwon, Woocheol; Shin, Jungwook; Seo, Changwoo; Kim, Hee-Joung

doi:10.1002/mp.12843

Cited by 6 publications

(3 citation statements)

References 46 publications

(53 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although filtered backprojection (FBP) [13] has excellent high-frequency detection sensitivity, the enhanced noise and ripple artifacts are concerning. In contrast, a simultaneous algebraic reconstruction technique (SART) [24] is expected to be effective at suppressing noise in iterative reconstruction (IR) and has been useful in various fields [25][26][27][28]. The usefulness of combining the first-iterative shrinkage-thresholding algorithm (FISTA) and IR-total variation (TV) was recently reported [29,30].…”

Section: Introductionmentioning

confidence: 99%

Improved digital chest tomosynthesis image quality by use of a projection-based dual-energy virtual monochromatic convolutional neural network with super resolution

et al. 2020

View full text Add to dashboard Cite

We developed a novel dual-energy (DE) virtual monochromatic (VM) very-deep super-resolution (VDSR) method with an unsharp masking reconstruction algorithm (DE–VM–VDSR) that uses projection data to improve the nodule contrast and reduce ripple artifacts during chest digital tomosynthesis (DT). For estimating the residual errors from high-resolution and multiscale VM images from the projection space, the DE–VM–VDSR algorithm employs a training network (mini-batch stochastic gradient-descent algorithm with momentum) and a hybrid super-resolution (SR) image [simultaneous algebraic reconstruction technique (SART) total-variation (TV) first-iterative shrinkage–thresholding algorithm (FISTA); SART–TV–FISTA] that involves subjective reconstruction with bilateral filtering (BF) [DE–VM–VDSR with BF]. DE-DT imaging was accomplished by pulsed X-ray exposures rapidly switched between low (60 kV, 37 projection) and high (120 kV, 37 projection) tube-potential kVp by employing a 40° swing angle. This was followed by comparison of images obtained employing the conventional polychromatic filtered backprojection (FBP), SART, SART–TV–FISTA, and DE–VM–SART–TV–FISTA algorithms. The improvements in contrast, ripple artifacts, and resolution were compared using the signal-difference-to-noise ratio (SDNR), Gumbel distribution of the largest variations, radial modulation transfer function (radial MTF) for a chest phantom with simulated ground-glass opacity (GGO) nodules, and noise power spectrum (NPS) for uniform water phantom. The novel DE–VM–VDSR with BF improved the overall performance in terms of SDNR (DE–VM–VDSR with BF: 0.1603, without BF: 0.1517; FBP: 0.0521; SART: 0.0645; SART–TV–FISTA: 0.0984; and DE–VM–SART–TV–FISTA: 0.1004), obtained a Gumbel distribution that yielded good images showing the type of simulated GGO nodules used in the chest phantom, and reduced the ripple artifacts. The NPS of DE–VM–VDSR with BF showed the lowest noise characteristics in the high-frequency region (~0.8 cycles/mm). The DE–VM–VDSR without BF yielded an improved resolution relative to that of the conventional reconstruction algorithms for radial MTF analysis (0.2–0.3 cycles/mm). Finally, based on the overall image quality, DE–VM–VDSR with BF improved the contrast and reduced the high-frequency ripple artifacts and noise.

show abstract

Section: Introductionmentioning

confidence: 99%

Improved digital chest tomosynthesis image quality by use of a projection-based dual-energy virtual monochromatic convolutional neural network with super resolution

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Therefore, radiation dose safety becomes more important, [2–5] and reduction of CT radiation dose is thus important in terms of maintenance of good image quality. [6]…”

Section: Introductionmentioning

confidence: 99%

Automatic current selection with iterative reconstruction reduces effective dose to less than 1 mSv in low-dose chest computed tomography in persons with normal BMI

Chen

Wu²,

Sheu³

et al. 2019

Medicine

View full text Add to dashboard Cite

Most of the recent studies have used fixed tube current while few investigators use automatic current selection (ACS) with iterative reconstruction (IR) techniques to reduce effective dose (ED) to < 1 mSv in low-dose chest computed tomography (LDCCT). We investigated whether image quality of lungs as produced by a fixed tube current (FTC) of 35 mAs can be maintained with ED < 1 mSv produced by ACS with IR techniques in LDCCT. A total of 32 participants were included. The LDCCT was performed by a FTC 35 mAs (with a kilovoltage peak of 120 kVp) in 16 participants (Group A), and by a DoseRight ACS in 16 participants (Group B). Their images were improved by IR technique. The ED was estimated by multiplying the individual dose length product (DLP) by the dose conversion factor. The image quality was assessed by the CT number, noise levels, signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) of the regions of interest in the apex, upper lobe, and lower lobe of lung regions in the CT images. A t-test was used to evaluate the LDCCT image quality between the groups. The ED was significantly 49.2% lower in Group B than in Group A (0.71 ± 0.05 mSv vs 1.40 ± 0.02 mSv, P < .001). However, noise level, SNR, and CNR were not significantly different between Groups A and B, indicating the image quality was similar between two groups, or our setting parameters for DoseRight ACS with IR technique can achieve the image quality as good as obtained on the FTC 35 mAs with IR techniques. Our results suggest that the DoseRight ACS with IR technique reduces ED to lower than 1 mSv (averagely 0.71 mSv) yet maintains an image quality as good as produced by FTC 35 mAs with IR technique in normal BMI persons. The ACS setup thus is more preferable than the FTC to achieve the ALARA (as low as reasonably achievable) principle.

show abstract

“…As in previous chest DT studies, the FBP (kernel: Ramachandran-Laksminarayanan) and SART (polychromatic 120kV acquisition) were used [27]. The number of iterations must be optimized because the characteristics of the IR image are dependent on the number of iterations.…”

Section: Optimization Parameters Of Vm Energy Initial Learning Ratementioning

confidence: 99%

Untitled

View full text Add to dashboard Cite

Development of a chest digital tomosynthesis R/F system and implementation of low‐dose GPU‐accelerated compressed sensing (CS) image reconstruction

Abstract: The current work describes the development and performance assessment of both hardware and software for tomosynthesis applications. The authors observed reasonable outcomes by showing a potential for low-dose application in CDT imaging using GPU acceleration.

Cited by 6 publications

References 46 publications

Improved digital chest tomosynthesis image quality by use of a projection-based dual-energy virtual monochromatic convolutional neural network with super resolution

Improved digital chest tomosynthesis image quality by use of a projection-based dual-energy virtual monochromatic convolutional neural network with super resolution

Automatic current selection with iterative reconstruction reduces effective dose to less than 1 mSv in low-dose chest computed tomography in persons with normal BMI

Untitled

Contact Info

Product

Resources

About