A Dual-Channel Deep Learning Approach for Lung Cavity Estimation From Hyperpolarized Gas and Proton MRI.

Journal: Journal of magnetic resonance imaging : JMRI
Published Date:

Abstract

BACKGROUND: Hyperpolarized gas MRI can quantify regional lung ventilation via biomarkers, including the ventilation defect percentage (VDP). VDP is computed from segmentations derived from spatially co-registered functional hyperpolarized gas and structural proton ( H)-MRI. Although acquired at similar lung inflation levels, they are frequently misaligned, requiring a lung cavity estimation (LCE). Recently, single-channel, mono-modal deep learning (DL)-based methods have shown promise for pulmonary image segmentation problems. Multichannel, multimodal approaches may outperform single-channel alternatives.

Authors

  • Joshua R Astley
    POLARIS, Department of Infection, Immunity & Cardiovascular Disease, The University of Sheffield, Sheffield, United Kingdom.
  • Alberto M Biancardi
    POLARIS, Department of Infection, Immunity and Cardiovascular Disease, The University of Sheffield, Sheffield, UK.
  • Helen Marshall
    POLARIS, Department of Infection, Immunity and Cardiovascular Disease, The University of Sheffield, Sheffield, UK.
  • Paul J C Hughes
    POLARIS, Department of Infection, Immunity and Cardiovascular Disease, The University of Sheffield, Sheffield, UK.
  • Guilhem J Collier
    POLARIS, Department of Infection, Immunity and Cardiovascular Disease, The University of Sheffield, Sheffield, UK.
  • Laurie J Smith
    POLARIS, Department of Infection, Immunity and Cardiovascular Disease, The University of Sheffield, Sheffield, UK.
  • James A Eaden
    POLARIS, Department of Infection, Immunity and Cardiovascular Disease, The University of Sheffield, Sheffield, UK.
  • Rod Hughes
    Early Development Respiratory, AstraZeneca, Cambridge, UK.
  • Jim M Wild
    Department of Oncology and Metabolism, The University of Sheffield, Sheffield, United Kingdom.
  • Bilal A Tahir
    POLARIS, Department of Infection, Immunity & Cardiovascular Disease, The University of Sheffield, Sheffield, United Kingdom.