Automatic Segmentation of Mammary Tissue using Computer Simulations of Breast Phantoms and Deep-learning Techniques

Lucca R. Peregrino, Jordy V. Gomes, Thaís G. do Rêgo, Yuri de A. M. Barbosa, Telmo de M. e Silva Filho, Andrew D. A. Maidment, Bruno Barufaldi

2021

Abstract

Digital breast tomosynthesis (DBT) has rapidly emerged for screening mammography to improve cancer detection. Segmentation of dense tissue plays an important role in breast imaging applications to estimate cancer risk. However, the current segmentation methods do not guarantee an ideal ground-truth in clinical practice. Computer simulations provide ground-truth that enables the development of convolutional neural network (CNN) applications designed for image segmentation. This study aims to train a CNN model to segment dense tissue in DBT images simulated using anthropomorphic phantoms. The phantom images were simulated based on clinical settings of a DBT system. A U-Net, a CNN model, was trained with 2,880 images using a slice-wise approach. The U-Net performance was evaluated in terms of percent of density in the central slice and volumetric breast density in the medio-lateral slices. Our results show that the U-Net can segment dense tissue from DBT images with overall loss, accuracy, and intersection over union of 0.27, 0.93, and 0.62 in the central slices, and 0.32, 0.92, and 0.54 in the medio-lateral slices, respectively. These preliminary results allow us to explore the use of CNN architectures to segment dense tissue in clinical images, which is a highly complex task in screening with DBT.

Paper Citation

in Harvard Style

Peregrino L., Gomes J., G. do Rêgo T., Barbosa Y., Filho T., Maidment A. and Barufaldi B. (2021). Automatic Segmentation of Mammary Tissue using Computer Simulations of Breast Phantoms and Deep-learning Techniques. In Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 4: BIOSIGNALS; ISBN 978-989-758-490-9, SciTePress, pages 252-259. DOI: 10.5220/0010310400002865

in Bibtex Style

@conference{biosignals21,
author={Lucca R. Peregrino and Jordy V. Gomes and Thaís G. do Rêgo and Yuri de A. M. Barbosa and Telmo de M. e Silva Filho and Andrew D. A. Maidment and Bruno Barufaldi},
title={Automatic Segmentation of Mammary Tissue using Computer Simulations of Breast Phantoms and Deep-learning Techniques},
booktitle={Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 4: BIOSIGNALS},
year={2021},
pages={252-259},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010310400002865},
isbn={978-989-758-490-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2021) - Volume 4: BIOSIGNALS
TI - Automatic Segmentation of Mammary Tissue using Computer Simulations of Breast Phantoms and Deep-learning Techniques
SN - 978-989-758-490-9
AU - Peregrino L.
AU - Gomes J.
AU - G. do Rêgo T.
AU - Barbosa Y.
AU - Filho T.
AU - Maidment A.
AU - Barufaldi B.
PY - 2021
SP - 252
EP - 259
DO - 10.5220/0010310400002865
PB - SciTePress