Automatic breast segmentation in digital mammography using a convolutional neural network

Omid Haji Maghsoudi, Aimilia Gastounioti, Lauren Pantalone, Emily Conant, Despina Kontos

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Digital mammography (DM) has been considered as the primary modality for breast cancer screening. The relative amount of breast fibroglandular tissue, referred to as percent breast density (PD), has been considered as an important factor associated with breast cancer. We have developed and tested a robust method to accurately segment the pectoral muscle and the breast area using a deep learning approach. We use a U-Net architecture with a ResNet decoder to increase the depth of features. The architecture is trained using 555 DM images and tested and validated on an independent set of 555 images. The results show that our network achieves an average and standard deviation dice coefficient of 94.86% ± 1.93%, respectively, and sensitivity of 96.31% ± 1.87%. The method present here can be considered as the first step toward the automatic estimation of PD.

Original languageEnglish
Title of host publication15th International Workshop on Breast Imaging, IWBI 2020
EditorsHilde Bosmans, Nicholas Marshall, Chantal Van Ongeval
PublisherSPIE
ISBN (Electronic)9781510638310
DOIs
StatePublished - 2020
Event15th International Workshop on Breast Imaging, IWBI 2020 - Leuven, Belgium
Duration: May 25 2020May 27 2020

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11513
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

Conference15th International Workshop on Breast Imaging, IWBI 2020
Country/TerritoryBelgium
CityLeuven
Period05/25/2005/27/20

Keywords

  • Breast Cancer
  • Deep Learning
  • Digital Mammography
  • Segmentation

Fingerprint

Dive into the research topics of 'Automatic breast segmentation in digital mammography using a convolutional neural network'. Together they form a unique fingerprint.

Cite this