ABSTRACT
The quantification of stenosis severity from X-ray catheter angiography is a challenging task. Indeed, this requires to fully understand the lesion's geometry by analyzing dynamics of the contrast material, only relying on visual observation by clinicians. To support decision making for cardiac intervention, we propose a hybrid CNN-Transformer model for the assessment of angiography-based non-invasive fractional flow-reserve (FFR) and instantaneous wave-free ratio (iFR) of intermediate coronary stenosis. Our approach predicts whether a coronary artery stenosis is hemodynamically significant and provides direct FFR and iFR estimates. This is achieved through a combination of regression and classification branches that forces the model to focus on the cut-off region of FFR (around 0.8 FFR value), which is highly critical for decision-making. We also propose a spatio-temporal factorization mechanisms that redesigns the transformer's self-attention mechanism to capture both local spatial and temporal interactions between vessel geometry, blood flow dynamics, and lesion morphology. The proposed method achieves state-of-the-art performance on a dataset of 778 exams from 389 patients. Unlike existing methods, our approach employs a single angiography view and does not require knowledge of the key frame; supervision at training time is provided by a classification loss (based on a threshold of the FFR/iFR values) and a regression loss for direct estimation. Finally, the analysis of model interpretability and calibration shows that, in spite of the complexity of angiographic imaging data, our method can robustly identify the location of the stenosis and correlate prediction uncertainty to the provided output scores.
ABSTRACT
Long term survival and its determinants after Percutaneous Coronary Intervention (PCI) on Unprotected Left Main Coronary Artery (ULMCA) remain to be appraised. In 9 European Centers 470 consecutive patients performing PCI on ULMCA between 2002 and 2005 were retrospectively enrolled. Survival from all cause and cardiovascular (CV) death were the primary end points, while their predictors at multivariate analysis the secondary ones. Among the overall cohort 81.5% of patients were male and mean age was 66 ± 12 years. After 15 years (IQR 13 to 16), 223 patients (47%) died, 81 (17.2%) due to CV etiology. At multivariable analysis, older age (HR 1.06, 95%CI 1.02 to 1.11), LVEF < 35% (HR 2.97, 95%CI 1.24 to 7.15) and number of vessels treated during the index PCI (HR 1.75, 95%CI 1.12 to 2.72) were related to all-cause mortality, while only LVEF <35% (HR 4.71, 95%CI 1.90 to 11.66) to CV death. Repeated PCI on ULMCA occurred in 91 (28%) patients during the course of follow up and did not significantly impact on freedom from all-cause or CV mortality. In conclusion, in a large, unselected population treated with PCI on ULMCA, 47% died after 15 years, 17% due to CV causes. Age, number of vessels treated during index PCI and depressed LVEF increased risk of all cause death, while re-PCI on ULMCA did not impact survival.
