A deep learning approach to estimate x-ray scatter in digital breast tomosynthesis: From phantom models to clinical applications.

Journal: Medical physics
PMID: 37394837

Abstract

BACKGROUND: Digital breast tomosynthesis (DBT) has gained popularity as breast imaging modality due to its pseudo-3D reconstruction and improved accuracy compared to digital mammography. However, DBT faces challenges in image quality and quantitative accuracy due to scatter radiation. Recent advancements in deep learning (DL) have shown promise in using fast convolutional neural networks for scatter correction, achieving comparable results to Monte Carlo (MC) simulations.

Authors

  • Marta C Pinto
    From the Department of Medical Imaging, Radboud University Medical Center, Geert Grooteplein 10, 6525 GA, Post 766, Nijmegen, the Netherlands (M.C.P., R.M.M., I.S.); ScreenPoint Medical, Nijmegen, the Netherlands (A.R.R.); Cancer Registry of Norway, Oslo, Norway (K.P., S.H.); Siemens Healthcare, Forchheim, Germany (J.W., S.K.); Department of Radiology, the Netherlands Cancer Institute, Amsterdam, the Netherlands (R.M.M.); and the Dutch Expert Centre for Screening, Nijmegen, the Netherlands (I.S.).
  • Franziska Mauter
    Dept. of Medical Imaging, Radboud University Medical Center, Nijmegen, The Netherlands.
  • Koen Michielsen
    Department of Medical Imaging, Radboud University Medical Center, the Netherlands.
  • Ramyar Biniazan
    Siemens Healthcare GmbH, Forchheim, Germany.
  • Steffen Kappler
    From the Department of Medical Imaging, Radboud University Medical Center, Geert Grooteplein 10, 6525 GA, Post 766, Nijmegen, the Netherlands (M.C.P., R.M.M., I.S.); ScreenPoint Medical, Nijmegen, the Netherlands (A.R.R.); Cancer Registry of Norway, Oslo, Norway (K.P., S.H.); Siemens Healthcare, Forchheim, Germany (J.W., S.K.); Department of Radiology, the Netherlands Cancer Institute, Amsterdam, the Netherlands (R.M.M.); and the Dutch Expert Centre for Screening, Nijmegen, the Netherlands (I.S.).
  • Ioannis Sechopoulos
    Department of Radiology and Nuclear Medicine, Radboud University Medical Center, PO Box 9101, 6500 HB, Nijmegen, The Netherlands.

Keywords

External Resources

Popular Topics
Recent Journals