Estimating the compressed breast-shape using deep learning

Koen Michielsen; Alejandro Rodriguez-Ruiz; Ioannis Sechopoulos

doi:10.1117/12.2563635

22 May 2020 Estimating the compressed breast-shape using deep learning

Koen Michielsen, Alejandro Rodriguez-Ruiz, Ioannis Sechopoulos

Proceedings Volume 11513, 15th International Workshop on Breast Imaging (IWBI2020); 115131W (2020) https://doi.org/10.1117/12.2563635
Event: Fifteenth International Workshop on Breast Imaging, 2020, Leuven, Belgium

Abstract

Knowledge of the compressed breast shape can be valuable information to improve tomosynthesis reconstructions. The goal of this work was to use a convolutional neural network to refine the shape as estimated from tomosynthesis projection data. Training data was created by generating random three-dimensional breast shapes and simulating the limited angle projections. A rough approximation of the breast shape was made by segmenting and then back-projecting the projection data. Following this, a 3-layer u-net was trained on 900 pairs of simulated breast shapes and the corresponding shape estimates. The resulting network was applied to 100 test cases, where it significantly reduced the average distance between the surfaces of the true and estimated breast shapes from 2.3 mm to 0.5 mm (p < 0.001). If these results can be confirmed using patient data, it is likely that advanced image processing techniques that rely on precise knowledge of the compressed breast shape will become feasible since our work now provides a method to obtain such an accurate estimate of the breast shape without the need for any additional imaging hardware.

Citation Download Citation

Koen Michielsen, Alejandro Rodriguez-Ruiz, and Ioannis Sechopoulos "Estimating the compressed breast-shape using deep learning", Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 115131W (22 May 2020); https://doi.org/10.1117/12.2563635

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Breast

Digital breast tomosynthesis

3D modeling

Convolutional neural networks

RELATED CONTENT

Integration of spatio temporal contrast sensitivity with a multi slice...
Proceedings of SPIE (March 28 2013)

Effect of denoising on the quality of reconstructed images in...
Proceedings of SPIE (March 19 2013)

Second generation anthropomorphic physical phantom for mammography and DBT ...
Proceedings of SPIE (March 22 2016)

Pectoral muscle segmentation in breast tomosynthesis with deep learning
Proceedings of SPIE (February 27 2018)

Detection of soft tissue densities from digital breast tomosynthesis ...
Proceedings of SPIE (March 24 2016)

Transfer learning with convolutional neural networks for lesion classification on...
Proceedings of SPIE (February 27 2018)

First results with a deep learning (feed forward CNN) approach...
Proceedings of SPIE (July 06 2018)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years