Training of a deep learning based digital subtraction angiography method using synthetic data.

Journal: Medical physics
PMID:

Abstract

BACKGROUND: Digital subtraction angiography (DSA) is a fluoroscopy method primarily used for the diagnosis of cardiovascular diseases (CVDs). Deep learning-based DSA (DDSA) is developed to extract DSA-like images directly from fluoroscopic images, which helps in saving dose while improving image quality. It can also be applied where C-arm or patient motion is present and conventional DSA cannot be applied. However, due to the lack of clinical training data and unavoidable artifacts in DSA targets, current DDSA models still cannot satisfactorily display specific structures, nor can they predict noise-free images.

Authors

  • Lizhen Duan
    Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ), Heidelberg, Germany.
  • Elias Eulig
    German Cancer Research Center (DKFZ), Heidelberg, Germany.
  • Michael Knaup
    Division of X-Ray Imaging and Computed Tomography, German Cancer Research Center (DKFZ), Heidelberg, Germany.
  • Ralf Adamus
    Department of Radiology, Neuroradiology and Nuclear Medicine, Klinikum Nürnberg, Paracelsus Medical University, Nürnberg, Germany.
  • Michael Lell
    University Hospital Nürnberg, Nürnberg, 90419, Germany.
  • Marc Kachelrieß
    German Cancer Research Center, Heidelberg, 69120, Germany.