A1 Refereed original research article in a scientific journal
Explainable deep-learning-based ischemia detection using hybrid O-15 H2O perfusion positron emission tomography and computed tomography imaging with clinical data
Authors: Teuho, Jarmo; Schultz, Jussi; Klén, Riku; Juarez-Orozco, Luis Eduardo; Knuuti, Juhani; Saraste, Antti; Ono, Naoaki; Kanaya, Shigehiko
Publisher: Elsevier
Publication year: 2024
Journal: Journal of Nuclear Cardiology
Journal name in source: Journal of Nuclear Cardiology
Article number: 101889
Volume: 38
ISSN: 1071-3581
eISSN: 1532-6551
DOI: https://doi.org/10.1016/j.nuclcard.2024.101889
Web address : https://doi.org/10.1016/j.nuclcard.2024.101889
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/457188887
Background:
We developed an explainable deep-learning (DL)-based classifier to identify flow-limiting coronary artery disease (CAD) by O-15 H2O perfusion positron emission tomography computed tomography (PET/CT) and coronary CT angiography (CTA) imaging. The classifier uses polar map images with numerical data and visualizes data findings.
Methods:
A DLmodel was implemented and evaluated on 138 individuals, consisting of a combined image—and data-based classifier considering 35 clinical, CTA, and PET variables. Data from invasive coronary angiography were 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 true-positive and false-negative 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.
Downloadable publication This is an electronic reprint of the original article. |  |
Funding information in the publication:
Dr Jarmo Teuho is an International Research Fellow of the Japan Society for the Promotion of Science, supported by JSPS Grant Number P19748 (Postdoctoral Fellowships for Research in Japan (Standard)). In addition, Dr Teuho would also like to acknowledge the Academy of Finland mobility funding (Academy Decision Number 322019) for supporting this research by allowing to combine both research work and family life in Japan. This research was also funded by the Maire and Aimo M\u00E4kinen Fund of the Finnish Cultural Foundation (Dr Riku Kl\u00E9n), Academy of Finland (Dr Juhani Knuuti, Academy Decision Number 351482) and by the JSPS KAKENHI grant 21KK0183 and 21K12111 (Dr Naoaki Ono), and Turku University Foundation. Funding text 2 Dr. Jarmo Teuho is an International Research Fellow of the Japan Society for the Promotion of Science, supported by JSPS Grant Number P19748 (Postdoctoral Fellowships for Research in Japan (Standard)). In addition, Dr. Teuho would also like to acknowledge the Academy of Finland mobility funding (Academy Decision Number 322019) for supporting this research by allowing to combine both research work and family life in Japan. This research was also funded by the Maire and Aimo M\u00E4kinen Fund of the Finnish Cultural Foundation (Dr. Riku Kl\u00E9n), Academy of Finland (Dr. Juhani Knuuti, Academy Decision Number 351482) and by the JSPS KAKENHI grant 21KK0183 and 21K12111 (Dr. Naoaki Ono), and Turku University Foundation. Funding text 3 Dr. Jarmo Teuho is an International Research Fellow of the Japan Society for the Promotion of Science, supported by JSPS Grant Number P19748 (Postdoctoral Fellowships for Research in Japan (Standard)). In addition, Dr. Teuho acknowledges the Academy of Finland mobility funding (Academy Decision Number 322019) for supporting this research by allowing to combine both research work and family life in Japan.
