Non-invasive derivation of instantaneous free-wave ratio from invasive coronary angiography using a new deep learning artificial intelligence model and comparison with human operators' performance.

Journal: The international journal of cardiovascular imaging
PMID:

Abstract

Invasive coronary physiology is underused and carries risks/costs. Artificial Intelligence (AI) might enable non-invasive physiology from invasive coronary angiography (CAG), possibly outperforming humans, but has seldom been explored, especially for instantaneous wave-free Ratio (iFR). We aimed to develop binary iFR lesion classification AI models and compare them with human performance. single-center retrospective study of patients undergoing CAG and iFR. A validated encoder-decoder convolutional neural network (CNN) performed segmentation. Manual annotation of target vessel and pressure sensor location on a segmented telediastolic frame followed. Three AI models classified lesions as positive (≤ 0.89) or negative (> 0.89). Model 1 uses preprocessed vessel diameters with a transformer. Models 2/3 are EfficientNet-B5 CNNs using concatenated angiography and segmentation - Model 3 employs class-frequency-weighted Cross-Entropy Loss. Previous findings demonstrated Model 3's superiority for left anterior descending (LAD) and Model 1's for circumflex (Cx)/right coronary artery (RCA) - they were therefore unified into a vessel-based model. Ten-fold patient-level cross-validation enabled full sample training/testing. Three experienced operators performed binary iFR classification using single frames of raw/segmented images. Comparison metrics were accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Across 250 measurements, AI accuracy was 72%, PPV 48%, NPV 90%, sensitivity 77%, and specificity 71%. Human accuracy ranged from 54 to 74%. NPV was high for the Cx/RCA (AI: 96/98%; operators: 94/97%), but AI significantly outperformed humans in the LAD (78% vs. 60-64%). An AI model capable of binary iFR lesions classification mildly outperformed interventional cardiologists, supporting further validation studies.

Authors

  • Catarina Oliveira
    Structural and Coronary Heart Disease Unit, Cardiovascular Center of the University of Lisbon (CCUL@RISE), Faculdade de Medicina, Universidade de Lisboa, Serviço de Cardiologia, Avenida Professor Egas Moniz, Lisboa, 1649-028, Portugal. catarinasdeoliveira@gmail.com.
  • Marta Vilela
    Structural and Coronary Heart Disease Unit, Cardiovascular Center of the University of Lisbon (CCUL@RISE), Faculdade de Medicina, Universidade de Lisboa, Serviço de Cardiologia, Avenida Professor Egas Moniz, Lisboa, 1649-028, Portugal.
  • João Silva Marques
    Structural and Coronary Heart Disease Unit, Cardiovascular Center of the University of Lisbon (CCUL@RISE), Faculdade de Medicina, Universidade de Lisboa, Serviço de Cardiologia, Avenida Professor Egas Moniz, Lisboa, 1649-028, Portugal.
  • Cláudia Jorge
    Structural and Coronary Heart Disease Unit, Cardiovascular Center of the University of Lisbon (CCUL@RISE), Faculdade de Medicina, Universidade de Lisboa, Serviço de Cardiologia, Avenida Professor Egas Moniz, Lisboa, 1649-028, Portugal.
  • Tiago Rodrigues
    BioMachines Lab, Lisbon, Portugal.
  • Ana Rita Francisco
    Structural and Coronary Heart Disease Unit, Cardiovascular Center of the University of Lisbon (CCUL@RISE), Faculdade de Medicina, Universidade de Lisboa, Serviço de Cardiologia, Avenida Professor Egas Moniz, Lisboa, 1649-028, Portugal.
  • Rita Marante de Oliveira
    Faculdade de Medicina, Universidade de Lisboa, Av Prof. Egas Moniz, Lisboa, 1649-028, Portugal.
  • Beatriz Silva
    Structural and Coronary Heart Disease Unit, Cardiovascular Center of the University of Lisbon, Faculdade de Medicina, Universidade de Lisboa, Lisboa, Portugal; Serviço de Cardiologia, Departamento de Coração e Vasos, CHULN Hospital de Santa Maria, Lisboa, Portugal.
  • João Lourenço Silva
    INESC-ID / Instituto Superior Técnico, University of Lisbon, Lisbon, Portugal.
  • Arlindo L Oliveira
  • Fausto J Pinto
    Faculty of Medicine, University of Lisbon, Lisbon, Portugal.
  • Miguel Nobre Menezes
    Structural and Coronary Heart Disease Unit, Cardiovascular Center of the University of Lisbon, Faculdade de Medicina, Universidade de Lisboa, Lisboa, Portugal; Serviço de Cardiologia, Departamento de Coração e Vasos, CHULN Hospital de Santa Maria, Lisboa, Portugal. Electronic address: mnmenezes.gm@gmail.com.