Convolutional neural network for automated mass segmentation in mammography.

Journal: BMC bioinformatics
Published Date: Dec 9, 2020

Abstract

BACKGROUND: Automatic segmentation and localization of lesions in mammogram (MG) images are challenging even with employing advanced methods such as deep learning (DL) methods. We developed a new model based on the architecture of the semantic segmentation U-Net model to precisely segment mass lesions in MG images. The proposed end-to-end convolutional neural network (CNN) based model extracts contextual information by combining low-level and high-level features. We trained the proposed model using huge publicly available databases, (CBIS-DDSM, BCDR-01, and INbreast), and a private database from the University of Connecticut Health Center (UCHC).

Authors

  • Dina Abdelhafiz
    Department of Computer Science and Engineering, University of Connecticut, Storrs, 06269, CT, USA. dina.abdelhafiz@uconn.edu.
  • Jinbo Bi
    Computer Science & Engineering Department at the University of Connecticut.
  • Reda Ammar
    Department of Computer Science and Engineering, University of Connecticut, Storrs, 06269, CT, USA.
  • Clifford Yang
    Department of Diagnostic Imaging, University of Connecticut Health Center, Farmington, 06030, CT, USA.
  • Sheida Nabavi
    Department of Computer Science and Engineering, University of Connecticut, Storrs, 06269, CT, USA.

Keywords

External Resources

Popular Topics
Recent Journals