Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Deep learning reconstruction of digital breast tomosynthesis images for accurate breast density and patient-specific radiation dose estimation

Teuwen, Jonas ; Moriakov, Nikita ; Fedon, Christian ; Caballo, Marco ; Reiser, Ingrid ; Bakic, Pedrag LU ; García, Eloy ; Diaz, Oliver ; Michielsen, Koen and Sechopoulos, Ioannis (2021) In Medical Image Analysis 71.
Abstract

The two-dimensional nature of mammography makes estimation of the overall breast density challenging, and estimation of the true patient-specific radiation dose impossible. Digital breast tomosynthesis (DBT), a pseudo-3D technique, is now commonly used in breast cancer screening and diagnostics. Still, the severely limited 3rd dimension information in DBT has not been used, until now, to estimate the true breast density or the patient-specific dose. This study proposes a reconstruction algorithm for DBT based on deep learning specifically optimized for these tasks. The algorithm, which we name DBToR, is based on unrolling a proximal-dual optimization method. The proximal operators are replaced with convolutional neural networks and... (More)

The two-dimensional nature of mammography makes estimation of the overall breast density challenging, and estimation of the true patient-specific radiation dose impossible. Digital breast tomosynthesis (DBT), a pseudo-3D technique, is now commonly used in breast cancer screening and diagnostics. Still, the severely limited 3rd dimension information in DBT has not been used, until now, to estimate the true breast density or the patient-specific dose. This study proposes a reconstruction algorithm for DBT based on deep learning specifically optimized for these tasks. The algorithm, which we name DBToR, is based on unrolling a proximal-dual optimization method. The proximal operators are replaced with convolutional neural networks and prior knowledge is included in the model. This extends previous work on a deep learning-based reconstruction model by providing both the primal and the dual blocks with breast thickness information, which is available in DBT. Training and testing of the model were performed using virtual patient phantoms from two different sources. Reconstruction performance, and accuracy in estimation of breast density and radiation dose, were estimated, showing high accuracy (density <±3%; dose <±20%) without bias, significantly improving on the current state-of-the-art. This work also lays the groundwork for developing a deep learning-based reconstruction algorithm for the task of image interpretation by radiologists.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Deep learning, Digital breast tomosynthesis, Reconstruction
in
Medical Image Analysis
volume
71
article number
102061
publisher
Elsevier
external identifiers
  • pmid:33910108
  • scopus:85105552060
ISSN
1361-8415
DOI
10.1016/j.media.2021.102061
language
English
LU publication?
yes
id
49df2db2-4e85-438a-ad52-d1bd505f56be
date added to LUP
2021-12-23 08:04:40
date last changed
2024-06-15 23:07:48
@article{49df2db2-4e85-438a-ad52-d1bd505f56be,
  abstract     = {{<p>The two-dimensional nature of mammography makes estimation of the overall breast density challenging, and estimation of the true patient-specific radiation dose impossible. Digital breast tomosynthesis (DBT), a pseudo-3D technique, is now commonly used in breast cancer screening and diagnostics. Still, the severely limited 3rd dimension information in DBT has not been used, until now, to estimate the true breast density or the patient-specific dose. This study proposes a reconstruction algorithm for DBT based on deep learning specifically optimized for these tasks. The algorithm, which we name DBToR, is based on unrolling a proximal-dual optimization method. The proximal operators are replaced with convolutional neural networks and prior knowledge is included in the model. This extends previous work on a deep learning-based reconstruction model by providing both the primal and the dual blocks with breast thickness information, which is available in DBT. Training and testing of the model were performed using virtual patient phantoms from two different sources. Reconstruction performance, and accuracy in estimation of breast density and radiation dose, were estimated, showing high accuracy (density &lt;±3%; dose &lt;±20%) without bias, significantly improving on the current state-of-the-art. This work also lays the groundwork for developing a deep learning-based reconstruction algorithm for the task of image interpretation by radiologists.</p>}},
  author       = {{Teuwen, Jonas and Moriakov, Nikita and Fedon, Christian and Caballo, Marco and Reiser, Ingrid and Bakic, Pedrag and García, Eloy and Diaz, Oliver and Michielsen, Koen and Sechopoulos, Ioannis}},
  issn         = {{1361-8415}},
  keywords     = {{Deep learning; Digital breast tomosynthesis; Reconstruction}},
  language     = {{eng}},
  publisher    = {{Elsevier}},
  series       = {{Medical Image Analysis}},
  title        = {{Deep learning reconstruction of digital breast tomosynthesis images for accurate breast density and patient-specific radiation dose estimation}},
  url          = {{http://dx.doi.org/10.1016/j.media.2021.102061}},
  doi          = {{10.1016/j.media.2021.102061}},
  volume       = {{71}},
  year         = {{2021}},
}