Machine-learning tool for classifying pulmonary hypertension via expert reader-provided CT features: An educational resource for non-dedicated radiologists.

Journal: European journal of radiology
PMID:

Abstract

PURPOSE: Pulmonary hypertension (PH) is a complex disease classified into five groups (I-V) by the European Society of Cardiology/European Respiratory Society (ESC/ERS) guidelines. Chest contrast-enhanced computed tomography (CECT) is crucial in the non-invasive PH assessment. This study aimed to develop a machine learning (ML)-based educational resource for classifying PH cases via CECT according to ESC/ERS groups.

Authors

  • L Cereser
    Institute of Radiology, Department of Medicine (DMED), University of Udine, Italy; Institute of Radiology, University Hospital S. Maria della Misericordia, Azienda Sanitaria Universitaria Friuli Centrale (ASUFC), Udine, Italy. Electronic address: lorenzo.cereser@uniud.it.
  • A Borghesi
    Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia, Italy. Electronic address: andrea.borghesi@unibs.it.
  • M De Martino
    Division of Medical Statistics, Department of Medicine (DMED), University of Udine, Italy. Electronic address: maria.demartino@uniud.it.
  • T Nadarevic
    Department of Diagnostic and Interventional Radiology, Clinical Hospital Center Rijeka, University of Rijeka, Croatia. Electronic address: tin.nadarevic@medri.uniri.hr.
  • C Cicciò
    Department of Diagnostic Imaging and Interventional Radiology, IRCCS Sacro Cuore Don Calabria Hospital, Negrar di Valpolicella (VR), Italy. Electronic address: carmelo.ciccio@sacrocuore.it.
  • G Agati
    Institute of Radiology, Department of Medicine (DMED), University of Udine, Italy. Electronic address: agati.giorgio@spes.uniud.it.
  • P Ciolli
    Department of Medical and Surgical Specialties, Radiological Sciences, and Public Health, University of Brescia, Italy. Electronic address: p.ciolli@unibs.it.
  • V Collini
    Cardiology, Cardiothoracic Department, University Hospital S. Maria della Misericordia, Azienda Sanitaria Universitaria Friuli Centrale (ASUFC), Udine, Italy. Electronic address: valentino.collini@asufc.sanita.fvg.it.
  • V Patruno
    Pulmonology Department, University Hospital S. Maria della Misericordia, Azienda Sanitaria Universitaria Friuli Centrale (ASUFC), Udine, Italy. Electronic address: vincenzo.patruno@asufc.sanita.fvg.it.
  • M Isola
    Division of Medical Statistics, Department of Medicine (DMED), University of Udine, Italy. Electronic address: miriam.isola@uniud.it.
  • M Imazio
    Cardiology, Cardiothoracic Department, University Hospital S. Maria della Misericordia, Azienda Sanitaria Universitaria Friuli Centrale (ASUFC), Udine, Italy. Electronic address: massimo.imazio@uniud.it.
  • C Zuiani
    Institute of Radiology, Department of Medicine (DMED), University of Udine, Italy; Institute of Radiology, University Hospital S. Maria della Misericordia, Azienda Sanitaria Universitaria Friuli Centrale (ASUFC), Udine, Italy. Electronic address: chiara.zuiani@uniud.it.
  • V Della Mea
    Department of Mathematics, Computer Science, and Physics, University of Udine, Italy. Electronic address: vincenzo.dellamea@uniud.it.
  • R Girometti
    Institute of Radiology, Department of Medicine (DMED), University of Udine, Italy; Institute of Radiology, University Hospital S. Maria della Misericordia, Azienda Sanitaria Universitaria Friuli Centrale (ASUFC), Udine, Italy. Electronic address: rossano.girometti@uniud.it.