Reduced anatomical clutter in digital breast tomosynthesis with statistical iterative reconstruction

Garrett, John W.; Li, Yinsheng; Li, Ké; Chen, Guang-Hong

doi:10.1002/mp.12864

Cited by 15 publications

(14 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, artifacts in both planes could be well mitigated at the same time. For verification, we also tested the 2D convolution kernels which operated merely within the

italicxy

plane (i.e., slice‐wise regularization 4,10 ). Results indicate that the network performance was degraded, where the out‐of‐plane artifacts and the inconsistent intensity distributions along the

z

direction became much more dramatic.…”

Section: Discussionmentioning

confidence: 99%

“…However, due to the incompleteness of the projection data, the reconstructed DBT images may suffer severe in-plane and out-of-plane artifacts. [2][3][4] To reduce such image artifacts, various reconstruction strategies have been investigated. For example, the filtered backprojection (FBP) algorithm with modified ramp filter could be used to improve the mass detectability.…”

Section: Introductionmentioning

confidence: 99%

“…Therefore, DBT is able to mitigate the tissue‐overlapping problem 1 in the conventional digital mammography (DM) imaging. However, due to the incompleteness of the projection data, the reconstructed DBT images may suffer severe in‐plane and out‐of‐plane artifacts 2–4 …”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

DIR‐DBTnet: Deep iterative reconstruction network for three‐dimensional digital breast tomosynthesis imaging

Deng

Yang

et al. 2021

Medical Physics

View full text Add to dashboard Cite

The goal of this study is to develop a three-dimensional (3D) iterative reconstruction framework based on the deep learning (DL) technique to improve the digital breast tomosynthesis (DBT) imaging performance. Methods: In this work, the DIR-DBTnet is developed for DBT image reconstruction by mapping the conventional iterative reconstruction (IR) algorithm to the deep neural network. By design, the DIR-DBTnet learns and optimizes the regularizer and the iteration parameters automatically during the network training with a large amount of simulated DBT data. Numerical, experimental, and clinical data are used to evaluate its performance. Quantitative metrics such as the artifact spread function (ASF), breast density, and the signal difference to noise ratio (SDNR) are measured to assess the image quality. Results: Results show that the proposed DIR-DBTnet is able to reduce the in-plane shadow artifacts and the out-of-plane signal leaking artifacts compared to the filtered backprojection (FBP) and the total variation (TV)-based IR methods. Quantitatively, the full width half maximum (FWHM) of the measured ASF from the clinical data is 27.1% and 23.0% smaller than those obtained with the FBP and TV methods, while the SDNR is increased by 194.5% and 21.8%, respectively. In addition, the breast density obtained from the DIR-DBTnet network is more accurate and consistent with the ground truth. Conclusions: In conclusion, a deep iterative reconstruction network, DIR-DBTnet, has been proposed for 3D DBT image reconstruction. Both qualitative and quantitative analyses of the numerical, experimental, and clinical results demonstrate that the DIR-DBTnet has superior DBT imaging performance than the conventional algorithms.

show abstract

“…Thus, artifacts in both planes could be well mitigated at the same time. For verification, we also tested the 2D convolution kernels which operated merely within the

italicxy

z

direction became much more dramatic.…”

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

DIR‐DBTnet: Deep iterative reconstruction network for three‐dimensional digital breast tomosynthesis imaging

Deng

Yang

et al. 2021

Medical Physics

View full text Add to dashboard Cite

show abstract

“…(1). This implementation was inspired by the forward-backward splitting algorithm [26]- [28] with the modified proximal operator shown in Eq. 7.…”

Section: Proposed Esmart-recon: Algorithm and Numerical Implementamentioning

confidence: 99%

“…Optimal reconstruction parameters for ST-TV-SIR are μ spatial = 2 × 10 −5 , μ temporal = 1 × 10 −5 , λ = 0.1, s = 0.2, N Iter = 15, and N denoising = 100. The implementation of both PICCS and ST-TV-SIR was based on a generalization of the algorithm for total-variation-based statistical image reconstruction presented in[28]. Reconstruction parameters for SMART-RECON and eSMART-RECON were optimized in section IV-A1.…”

mentioning

confidence: 99%

An Enhanced SMART-RECON Algorithm for Time-Resolved C-Arm Cone-Beam CT Imaging

Garrett

et al. 2020

IEEE Trans. Med. Imaging

Self Cite

View full text Add to dashboard Cite

Temporal resolution in time-resolved cone-beam CT (TR-CBCT) imaging is often limited by the time needed to acquire a complete data set for image reconstruction. With the recent developments of performing nearly limited-view artifact-free reconstruction from data in a limited-view angle range and a prior image, temporal resolution of TR-CBCT imaging can be improved. One such an example is the use of Simultaneous Multiple Artifacts Reduction in Tomographic RECONstruction (SMARTR-ECON) [1] technique. However, with SMART-RECON, one can only improve temporal resolution up to 1 frame per second (fps) which is an improvement of 4.5 times over that of the conventional FBP reconstruction. In this paper, a new technique referred to as enhanced SMART-RECON (eSMART-RECON) was introduced to enhance the temporal performance of SMART-RECON in a multi-sweep CBCT data acquisition protocol. Both numerical simulation studies with ground truth and in vivo human subject studies using C-arm CBCT acquisition systems were conducted to demonstrate the following key results: for a multisweep CBCT acquisition protocol, eSMART-RECON enables 4-7.5 fps temporal resolution for TR-CBCT which is 4-7.5 times better than that offered by the original SMART-RECON, and 18-34 times better than that offered by the conventional FBP reconstruction.

show abstract

Accurate and robust sparse‐view angle CT image reconstruction using deep learning and prior image constrained compressed sensing (DL‐PICCS)

Zhang

Chen

2021

Medical Physics

Self Cite

View full text Add to dashboard Cite

Background: Sparse-view CT image reconstruction problems encountered in dynamic CT acquisitions are technically challenging. Recently, many deep learning strategies have been proposed to reconstruct CT images from sparse-view angle acquisitions showing promising results. However, two fundamental problems with these deep learning reconstruction methods remain to be addressed:(1) limited reconstruction accuracy for individual patients and (2) limited generalizability for patient statistical cohorts. Purpose: The purpose of this work is to address the previously mentioned challenges in current deep learning methods. Methods: A method that combines a deep learning strategy with prior image constrained compressed sensing (PICCS) was developed to address these two problems. In this method, the sparse-view CT data were reconstructed by the conventional filtered backprojection (FBP) method first, and then processed by the trained deep neural network to eliminate streaking artifacts. The outputs of the deep learning architecture were then used as the needed prior image in PICCS to reconstruct the image. If the noise level from the PICCS reconstruction is not satisfactory, another light duty deep neural network can then be used to reduce noise level. Both extensive numerical simulation data and human subject data have been used to quantitatively and qualitatively assess the performance of the proposed DL-PICCS method in terms of reconstruction accuracy and generalizability. Results: Extensive evaluation studies have demonstrated that: (1) quantitative reconstruction accuracy of DL-PICCS for individual patient is improved when it is compared with the deep learning methods and CS-based methods; (2) the false-positive lesion-like structures and false negative missing anatomical structures in the deep learning approaches can be effectively eliminated in the DL-PICCS reconstructed images; and (3) DL-PICCS enables a deep learning scheme to relax its working conditions to enhance its generalizability. Conclusions: DL-PICCS offers a promising opportunity to achieve personalized reconstruction with improved reconstruction accuracy and enhanced generalizability.

show abstract

Reduced anatomical clutter in digital breast tomosynthesis with statistical iterative reconstruction

Cited by 15 publications

References 65 publications

DIR‐DBTnet: Deep iterative reconstruction network for three‐dimensional digital breast tomosynthesis imaging

DIR‐DBTnet: Deep iterative reconstruction network for three‐dimensional digital breast tomosynthesis imaging

An Enhanced SMART-RECON Algorithm for Time-Resolved C-Arm Cone-Beam CT Imaging

Accurate and robust sparse‐view angle CT image reconstruction using deep learning and prior image constrained compressed sensing (DL‐PICCS)

Contact Info

Product

Resources

About