Deep learning framework for digital breast tomosynthesis reconstruction

Moriakov, Nikita; Michielsen, Koen; Adler, Jonas; Mann, Ritse M.; Sechopoulos, Ioannis; Teuwen, Jonas

doi:10.1117/12.2512912

Cited by 13 publications

(14 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Robustness against model uncertainty, however, is not readily obtained. An application of a learned primal dual scheme to breast tomosynthesis is given by Moriakov et al (2018). To outperform existing reconstruction methods, one needs to encode the information about breast thickness into the learned updates for both primal and dual variables.…”

Section: Learned Iterative Schemesmentioning

confidence: 99%

Solving inverse problems using data-driven models

et al. 2019

View full text Add to dashboard Cite

Recent research in inverse problems seeks to develop a mathematically coherent foundation for combining data-driven models, and in particular those based on deep learning, with domain-specific knowledge contained in physical–analytical models. The focus is on solving ill-posed inverse problems that are at the core of many challenging applications in the natural sciences, medicine and life sciences, as well as in engineering and industrial applications. This survey paper aims to give an account of some of the main contributions in data-driven inverse problems.

show abstract

Section: Learned Iterative Schemesmentioning

confidence: 99%

Solving inverse problems using data-driven models

et al. 2019

View full text Add to dashboard Cite

show abstract

“…For the application of DBT image reconstruction, Moriakov et al . have demonstrated the feasibility of using the DL‐based primal‐dual type IR algorithm 21 for 2D DBT images reconstruction 22 . Results show that DBT images with high breast density accuracy and reduced image artifact can be obtained.…”

Section: Introductionmentioning

confidence: 93%

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

“…The algorithm used to compute the low resolution 3D DBT reconstructions, referred to as DBToR-X for now, is a modified, memory-optimized version of the DBToR algorithm that was originally developed for 2D slice-wise DBT reconstruction [2], and was adapted for the purpose of 3D reconstruction with the realistic projection geometry described in section II-A.…”

Section: B Deep Learning Reconstructionmentioning

confidence: 99%

“…Recently, we developed a deep learning-based reconstruction for a simplified 2D version of the DBT limited angle problem [2]. With it, we were able to reconstruct the distribution of the glandular tissue in the breast to an accuracy that allowed for the estimation of the individual patient dose to within 20% and of the total glandular tissue to within 3%.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning-based Initialization of Iterative Reconstruction for Breast Tomosynthesis

Michielsen¹,

Moriakov²,

Teuwen³

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Reconstruction of digital breast tomosynthesis is a challenging problem due to the limited angle data available in such systems. Due to memory limitations, deep learningbased methods can help improve these reconstructions, but can not (yet) attain sufficiently high resolution. In addition to this practical issue, questions remain on the possibility of such models introducing 'ghost' information from the training data that is not compatible with the projection data. To take advantage of some of the benefits of deep learning-based reconstructions while avoiding these limitations, we propose to use the low resolution deep learning-based reconstruction as an initialization of a regular high resolution iterative method.The network was trained using digital phantoms, some based on a mathematical model and some derived from patient dedicated breast CT scans. The output of this network was then used as initialization for 10 000 iterations of MLTR for nine patient based phantoms that were not included in the training. The same nine cases were also reconstructed without any initialization for comparison.The reconstructions including initialization were found to reach a lower mean squared error than those without, and visual inspection found much improved retrieval of the breast outline and depiction of the skin, confirming that adding the deep learning-based initialization adds valuable information to the reconstruction.

show abstract

Deep learning framework for digital breast tomosynthesis reconstruction

Cited by 13 publications

References 6 publications

Solving inverse problems using data-driven models

Solving inverse problems using data-driven models

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

Deep Learning-based Initialization of Iterative Reconstruction for Breast Tomosynthesis

Contact Info

Product

Resources

About