Journal of Cardiovascular Magnetic Resonance (Apr 2022)

Training and clinical testing of artificial intelligence derived right atrial cardiovascular magnetic resonance measurements

  • Faisal Alandejani,
  • Samer Alabed,
  • Pankaj Garg,
  • Ze Ming Goh,
  • Kavita Karunasaagarar,
  • Michael Sharkey,
  • Mahan Salehi,
  • Ziad Aldabbagh,
  • Krit Dwivedi,
  • Michail Mamalakis,
  • Pete Metherall,
  • Johanna Uthoff,
  • Chris Johns,
  • Alexander Rothman,
  • Robin Condliffe,
  • Abdul Hameed,
  • Athanasios Charalampoplous,
  • Haiping Lu,
  • Sven Plein,
  • John P. Greenwood,
  • Allan Lawrie,
  • Jim M. Wild,
  • Patrick J. H. de Koning,
  • David G. Kiely,
  • Rob Van Der Geest,
  • Andrew J. Swift

DOI
https://doi.org/10.1186/s12968-022-00855-3
Journal volume & issue
Vol. 24, no. 1
pp. 1 – 11

Abstract

Read online

Abstract Background Right atrial (RA) area predicts mortality in patients with pulmonary hypertension, and is recommended by the European Society of Cardiology/European Respiratory Society pulmonary hypertension guidelines. The advent of deep learning may allow more reliable measurement of RA areas to improve clinical assessments. The aim of this study was to automate cardiovascular magnetic resonance (CMR) RA area measurements and evaluate the clinical utility by assessing repeatability, correlation with invasive haemodynamics and prognostic value. Methods A deep learning RA area CMR contouring model was trained in a multicentre cohort of 365 patients with pulmonary hypertension, left ventricular pathology and healthy subjects. Inter-study repeatability (intraclass correlation coefficient (ICC)) and agreement of contours (DICE similarity coefficient (DSC)) were assessed in a prospective cohort (n = 36). Clinical testing and mortality prediction was performed in n = 400 patients that were not used in the training nor prospective cohort, and the correlation of automatic and manual RA measurements with invasive haemodynamics assessed in n = 212/400. Radiologist quality control (QC) was performed in the ASPIRE registry, n = 3795 patients. The primary QC observer evaluated all the segmentations and recorded them as satisfactory, suboptimal or failure. A second QC observer analysed a random subcohort to assess QC agreement (n = 1018). Results All deep learning RA measurements showed higher interstudy repeatability (ICC 0.91 to 0.95) compared to manual RA measurements (1st observer ICC 0.82 to 0.88, 2nd observer ICC 0.88 to 0.91). DSC showed high agreement comparing automatic artificial intelligence and manual CMR readers. Maximal RA area mean and standard deviation (SD) DSC metric for observer 1 vs observer 2, automatic measurements vs observer 1 and automatic measurements vs observer 2 is 92.4 ± 3.5 cm2, 91.2 ± 4.5 cm2 and 93.2 ± 3.2 cm2, respectively. Minimal RA area mean and SD DSC metric for observer 1 vs observer 2, automatic measurements vs observer 1 and automatic measurements vs observer 2 was 89.8 ± 3.9 cm2, 87.0 ± 5.8 cm2 and 91.8 ± 4.8 cm2. Automatic RA area measurements all showed moderate correlation with invasive parameters (r = 0.45 to 0.66), manual (r = 0.36 to 0.57). Maximal RA area could accurately predict elevated mean RA pressure low and high-risk thresholds (area under the receiver operating characteristic curve artificial intelligence = 0.82/0.87 vs manual = 0.78/0.83), and predicted mortality similar to manual measurements, both p < 0.01. In the QC evaluation, artificial intelligence segmentations were suboptimal at 108/3795 and a low failure rate of 16/3795. In a subcohort (n = 1018), agreement by two QC observers was excellent, kappa 0.84. Conclusion Automatic artificial intelligence CMR derived RA size and function are accurate, have excellent repeatability, moderate associations with invasive haemodynamics and predict mortality.

Keywords