DeepValve: The first automatic detection pipeline for the mitral valve in Cardiac Magnetic Resonance imaging.

Journal: Computers in biology and medicine
Published Date: Apr 30, 2025

Abstract

Mitral valve (MV) assessment is key to diagnosing valvular disease and to addressing its serious downstream complications. Cardiac magnetic resonance (CMR) has become an essential diagnostic tool in MV disease, offering detailed views of the valve structure and function, and overcoming the limitations of other imaging modalities. Automated detection of the MV leaflets in CMR could enable rapid and precise assessments that enhance diagnostic accuracy. To address this gap, we introduce DeepValve, the first deep learning (DL) pipeline for MV detection using CMR. Within DeepValve, we tested three valve detection models: a keypoint-regression model (UNET-REG), a segmentation model (UNET-SEG) and a hybrid model based on keypoint detection (DSNT-REG). We also propose metrics for evaluating the quality of MV detection, including Procrustes-based metrics (UNET-REG, DSNT-REG) and customized Dice-based metrics (UNET-SEG). We developed and tested our models on a clinical dataset comprising 120 CMR images from patients with confirmed MV disease (mitral valve prolapse and mitral annular disjunction). Our results show that DSNT-REG delivered the best regression performance, accurately locating landmark locations. UNET-SEG achieved satisfactory Dice and customized Dice scores, also accurately predicting valve location and topology. Overall, our work represents a critical first step towards automated MV assessment using DL in CMR and paving the way for improved clinical assessment in MV disease.

Authors

  • Giulia Monopoli
    Department of Computational Physiology, Simula Research Laboratory, Kristian Augusts gate 23, Oslo, 0164, Oslo, Norway. Electronic address: giulia@simula.no.
  • Daniel Haas
    Department of Computational Physiology, Simula Research Laboratory, Kristian Augusts gate 23, Oslo, 0164, Oslo, Norway.
  • Ashay Singh
    Department of Computational Physiology, Simula Research Laboratory, Kristian Augusts gate 23, Oslo, 0164, Oslo, Norway.
  • Eivind Westrum Aabel
    ProCardio Center for Innovation, Department of Cardiology, Oslo University Hospital, PO Box 4950 Nydalen, Oslo, 0424, Oslo, Norway; Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, PO Box 1171 Blindern, Oslo, 0318, Oslo, Norway.
  • Margareth Ribe
    Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, PO Box 1171 Blindern, Oslo, 0318, Oslo, Norway.
  • Anna Isotta Castrini
    ProCardio Center for Innovation, Department of Cardiology, Oslo University Hospital, PO Box 4950 Nydalen, Oslo, 0424, Oslo, Norway; Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, PO Box 1171 Blindern, Oslo, 0318, Oslo, Norway.
  • Nina Eide Hasselberg
    ProCardio Center for Innovation, Department of Cardiology, Oslo University Hospital, PO Box 4950 Nydalen, Oslo, 0424, Oslo, Norway; Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, PO Box 1171 Blindern, Oslo, 0318, Oslo, Norway.
  • Cecilie Bugge
    ProCardio Center for Innovation, Department of Cardiology, Oslo University Hospital, PO Box 4950 Nydalen, Oslo, 0424, Oslo, Norway; Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, PO Box 1171 Blindern, Oslo, 0318, Oslo, Norway.
  • Christian Five
    ProCardio Center for Innovation, Department of Cardiology, Oslo University Hospital, PO Box 4950 Nydalen, Oslo, 0424, Oslo, Norway; Institute of Clinical Medicine, Faculty of Medicine, University of Oslo, PO Box 1171 Blindern, Oslo, 0318, Oslo, Norway.
  • Kristina Haugaa
  • Nickolas Forsch
    Department of Computational Physiology, Simula Research Laboratory, Kristian Augusts gate 23, Oslo, 0164, Oslo, Norway.
  • Vajira Thambawita
    SimulaMet, Oslo, Norway.
  • Gabriel Balaban
    School of Economics Innovation and Technology, Kristiania University College, Kirkegata 24-26, Oslo, 0153, Oslo, Norway.
  • Mary M Maleckar
    Simula Research Laboratory, 1364, Fornebu, Norway.

Keywords

External Resources

Popular Topics
Recent Journals