J Nucl Cardiol. 2024 Jun 7:101889. doi: 10.1016/j.nuclcard.2024.101889. Online ahead of print.
ABSTRACT
BACKGROUND: We developed an explainable deep learning-based classifier to identify flow-limiting coronary artery disease (CAD) by O-15 H2O perfusion PET/CT and coronary CT angiography (CTA) imaging. The classifier uses polar map images with numerical data and visualizes data findings.
METHODS: A deep learning (DL) model was implemented and evaluated on 138 subjects, consisting of a combined image- and data-based classifier considering 35 clinical, CTA and PET variables. Data from invasive coronary angiography was used as reference. Performance was evaluated with clinical classification using accuracy (ACC), area under the receiver operating characteristic curve (AUC), F1 score (F1S), sensitivity (SEN), specificity (SPE), precision (PRE), net benefit and Cohen’s Kappa. Statistical testing was conducted using McNemar’s test.
RESULTS: The DL model had a median ACC 0.8478, AUC 0.8481, F1S 0.8293, SEN 0.8500, SPE 0.8846 and PRE 0.8500. Improved detection of TP and FN cases, increased net benefit in thresholds up to 34 %, and comparable Cohen’s kappa was seen, reaching similar performance to clinical reading. Statistical testing revealed no significant differences between DL model and clinical reading.
CONCLUSIONS: The combined DL model is a feasible and an effective method in detection of CAD, allowing to highlight important data findings individually in interpretable manner.
PMID:38852900 | DOI:10.1016/j.nuclcard.2024.101889
