New reconstruction algorithm for digital breast tomosynthesis: better image quality for humans and computers

@article{RodrguezRuiz2018NewRA,
  title={New reconstruction algorithm for digital breast tomosynthesis: better image quality for humans and computers},
  author={Alejandro Rodr{\'i}guez-Ruiz and Jonas Teuwen and Suzan Vreemann and Ramona W. Bouwman and Ruben E. van Engen and Nico Karssemeijer and Ritse M. Mann and Albert Gubern-M{\'e}rida and Ioannis Sechopoulos},
  journal={Acta Radiologica (Stockholm, Sweden : 1987)},
  year={2018},
  volume={59},
  pages={1051 - 1059}
}
Background The image quality of digital breast tomosynthesis (DBT) volumes depends greatly on the reconstruction algorithm. [] Key Method In parallel, a three-dimensional deep-learning convolutional neural network (3D-CNN) was trained (n = 259 patients, 51 positives with BI-RADS 3, 4, or 5 calcifications) and tested (n = 46 patients, nine positives), separately with FBP and EMPIRE volumes, to discriminate between samples with and without calcifications.

Figures and Tables from this paper

Deep learning framework for digital breast tomosynthesis reconstruction
TLDR
Results indicate that the proposed algorithm outperforms the baseline iterative reconstruction algorithm in terms of reconstruction quality for both breast edges and internal structures and is robust to noise.
Artificial Intelligence for Mammography and Digital Breast Tomosynthesis: Current Concepts and Future Perspectives.
TLDR
This review explains how deep learning works in the context of mammography and DBT and defines the important technical challenges, and discusses the current status and future perspectives of artificial intelligence-based clinical applications for mammography, DBT, and radiomics.
Digital breast tomosynthesis: a state-of-the-art review
TLDR
This review aims at describing current DBT technique, analyzing D BT in clinical practice and providing an overview of published studies on clinical experience with DBT in the screening and diagnostic settings.
How does wide-angle breast tomosynthesis depict calcifications in comparison to digital mammography? A retrospective observer study
TLDR
The results show the current limitations of DBT and its derived SM to depict calcifications in comparison to DM.
Synthetic 2-Dimensional Mammography Can Replace Digital Mammography as an Adjunct to Wide-Angle Digital Breast Tomosynthesis
TLDR
Wide-angle DBT combined with DM or SM increases sensitivity and accuracy without reducing specificity compared with DM alone; therefore, SM should replace DM for combined readings with WA-DBT.
Impact of artificial intelligence support on accuracy and reading time in breast tomosynthesis image interpretation: a multi-reader multi-case study
TLDR
Radiologists improved their cancer detection accuracy in digital breast tomosynthesis (DBT) when using an AI system for support, while simultaneously reducing reading time, in a study of breast radiologists reading wide-angle DBT exams with and without AI support.
...
...

References

SHOWING 1-10 OF 37 REFERENCES
Optimizing High Resolution Reconstruction in Digital Breast Tomosynthesis Using Filtered Back Projection
TLDR
The results from the quantitative evaluation and clinical reading by experienced radiologists indicate that the proposed methods can significantly improve contrast and sharpness of micro-calcifications and reduce noise compared to a baseline FBP method with standard filter settings.
Digital breast tomosynthesis: Dose and image quality assessment.
  • A. Maldera, P. De Marco, P. Colombo, D. Origgi, A. Torresin
  • Medicine, Physics
    Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics
  • 2017
Tomosynthesis reconstruction using the simultaneous algebraic reconstruction technique (SART) on breast phantom data
TLDR
Results show that acceptable reconstruction can be achieved by SART after only one iteration, and preliminary results show that both BP and SART can separate superimposed phantom structures along the Z direction, but SART is more effective in improving the conspicuity of tissue-mimicking details and suppressing interplane blurring.
Enhanced imaging of microcalcifications in digital breast tomosynthesis through improved image-reconstruction algorithms.
TLDR
A practical, iterative algorithm for image-reconstruction in undersampled tomographic systems, such as digital breast tomosynthesis (DBT), indicates that there may be a substantial advantage in using the present image- reconstruction algorithm for microcalcification imaging.
Optimizing filtered backprojection reconstruction for a breast tomosynthesis prototype device
TLDR
A general theory of filtered backprojection reconstruction for linear tomosynthesis is formulated and the impact of the filter functions with simulated projections and with clinical data acquired with a research breast tomosynthetic system is demonstrated.
Evaluation and optimization of the maximum-likelihood approach for image reconstruction in digital breast tomosynthesis
TLDR
The state-of-art iterative maximum likelihood (ML) statistical reconstruction algorithms for DBT are investigated and the iFBP algorithm provides the benefits of statistical iterative reconstruction techniques and requires much shorter computation time.
A Novel Approach for Filtered Backprojection in Tomosynthesis Based on Filter Kernels Determined by Iterative Reconstruction Techniques
TLDR
A set of filter kernels for FBP is experimentally developed, determined by iterative reconstruction providing similar image characteristics and quality as an algebraic reconstruction.
A review of breast tomosynthesis. Part II. Image reconstruction, processing and analysis, and advanced applications.
TLDR
A review of breast tomosynthesis research is performed, with an emphasis on its medical physics aspects, including reconstruction, image processing, and analysis, as well as the advanced applications being investigated for breasttomosynthesis.
Out-of-Plane Artifact Reduction in Tomosynthesis Based on Regression Modeling and Outlier Detection
TLDR
The experiments show that the resulting reconstructed images are de-blurred and streak-like artifacts are reduced, visibility of clinical features, contrast and sharpness are improved and thick-slice reconstruction is possible without the loss of contrast andsharpness.
...
...