Mean pulmonary artery pressure prediction with explainable multi-view cardiovascular magnetic resonance cine series deep learning model

Journal of Cardiovascular Magnetic Resonance, vol. 27, pp. 101133

Abstract

BACKGROUND: Pulmonary hypertension (PH) is a heterogeneous condition and regardless of etiology impacts negatively on survival. Diagnosis of PH is based on hemodynamic parameters measured invasively at right heart catheterization (RHC); however, a non-invasive alternative would be clinically valuable. Our aim was to estimate RHC parameters non-invasively from cardiac magnetic resonance (MR) data using deep learning models and to identify key contributing imaging features. METHODS: We constructed an explainable convolutional neural network (CNN) taking cardiac MR cine series from four different views as input to predict mean pulmonary artery pressure (mPAP). The model was trained and evaluated on 1646 examinations. The model's attention weight and predictive performance associated with each frame, view, or phase were used to judge its importance. Additionally, the importance of each cardiac chamber was inferred by perturbing part of the input pixels. RESULTS: of 0.64 in predicting mPAP and identified the right ventricle region on short-axis view to be especially informative. CONCLUSION: Hemodynamic parameters can be estimated non-invasively with a CNN, using MR cine series from four views, revealing key contributing features at the same time.

Authors 10

1. Li‐Hsin Cheng Aachen Division of Image Processing Department of Radiology, Leiden University Medical Centre

   Leiden University · Leiden University Medical Center

   Affiliation as printed

   Division of Image Processing (LKEB), Department of Radiology, Leiden University Medical, Center, the Netherlands

2. Xiaowu Sun Aachen Division of Image Processing Department of Radiology, Leiden University Medical Centre

   Leiden University · Leiden University Medical Center

   Affiliation as printed

   Division of Image Processing (LKEB), Department of Radiology, Leiden University Medical, Center, the Netherlands

3. Charlie Elliot

   Sheffield Teaching Hospitals NHS Foundation Trust

   Affiliation as printed

   Sheffield Pulmonary Vascular Disease Unit, Sheffield Teaching Hospitals NHS Foundation, Trust, UK

4. Robin Condliffe

   Sheffield Teaching Hospitals NHS Foundation Trust

   Affiliation as printed

   Sheffield Pulmonary Vascular Disease Unit, Sheffield Teaching Hospitals NHS Foundation, Trust, UK

5. David Gerard Kiely

   National Institute for Health and Care Research · Sheffield Teaching Hospitals NHS Foundation Trust · NIHR Sheffield Biomedical Research Centre

   Affiliation as printed

   Sheffield Pulmonary Vascular Disease Unit, Sheffield Teaching Hospitals NHS Foundation, Trust, UK; National Institute for Health and Care Research (NIHR) Sheffield Biomedical Research Centre, Sheffield, UK

6. Samer Alabed

   University of Sheffield

   Affiliation as printed

   Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, UK

7. Andrew J. Swift

   University of Sheffield

   Affiliation as printed

   Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, UK

8. Rob J. van der Geest Aachen Division of Image Processing Department of Radiology, Leiden University Medical Centre

   Leiden University · Leiden University Medical Center

   Affiliation as printed

   Division of Image Processing (LKEB), Department of Radiology, Leiden University Medical, Center, the Netherlands. Electronic address: r.j.van_der_geest@lumc.nl

9. Iain J. Armstrong
10. Alexander M.K. Rothman