Deep Learning Reconstruction

Deep Learning Reconstruction is a computational image formation method that employs deep neural networks to transform raw medical imaging data into high-quality coronary artery images by learning complex noise and artifact suppression patterns from training datasets, distinguishing it from conventional reconstruction techniques through its data-driven, nonlinear mapping capabilities.

664

Publications

36.2K

Citations

3.2K

Authors

957

Institutions

Publications per year

2017–2026

660

Authors

3.2K

  1. DN
    Dominik Nickel

    Siemens Healthineers (Germany), Germany

    10 publications · 579 citations

    10

    h-index

  2. AE
    Ahmed E. Othman

    Johannes Gutenberg University Mainz, Germany

    10 publications · 550 citations

    10

    h-index

  3. SG
    Sebastian Gassenmaier

    University of Tübingen, Germany

    9 publications · 550 citations

    9

    h-index

  4. FK
    Florian Knöll

    New York University, United States

    8 publications · 593 citations

    8

    h-index

  5. OA
    Osamu Abe

    The University of Tokyo, Japan

    8 publications · 327 citations

    8

    h-index

1–5 of 3.2K

Venues

  1. European Radiology

    41 publications · 2.2K citations

    27

    h-index

  2. Optics Express

    24 publications · 1.5K citations

    21

    h-index

  3. European Journal of Radiology

    EJR · 20 publications · 536 citations

    17

    h-index

  4. Magnetic Resonance in Medicine

    MRM · 18 publications · 1.1K citations

    16

    h-index

  5. arXiv (Cornell University)

    Repository · 28 publications · 889 citations

    15

    h-index

1–5