Model-based deep CNN-regularized reconstruction for digital breast tomosynthesis with a task-based CNN image

Mingjie Gao1,2, Jeffrey A Fessler1,2, Heang-Ping Chan1

  • 1Department of Radiology, University of Michigan, Ann Arbor, MI 48109, United States of America.

PubMed
Summary

This study introduces a new deep learning method to improve digital breast tomosynthesis (DBT) image quality. The model reduces noise and enhances microcalcification visibility, aiding breast cancer detection.