A4 Refereed article in a conference publication
Comparison of 12 Machine Learning Methods for Polar Map Classification in Cardiac Perfusion PET
Authors: Teuho Jarmo, Schultz Jussi, Klén Riku, Saraste Antti, Ono Naoaki, Kanaya Shigehiko
Editors: Tomita Hideki, Nakamura Tatsuya
Conference name: IEEE Nuclear Science Symposium and Medical Imaging Conference
Publisher: Institute of Electrical and Electronics Engineers Inc.
Publication year: 2021
Journal: IEEE Nuclear Science Symposium and Medical Imaging Conference record
Book title : 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record, NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors, RTSD 2022
Journal name in source: 2021 IEEE Nuclear Science Symposium and Medical Imaging Conference Record, NSS/MIC 2021 and 28th International Symposium on Room-Temperature Semiconductor Detectors, RTSD 2022
Series title: IEEE Nuclear Science Symposium and Medical Imaging Conference record
ISBN: 978-1-66542-113-3
eISBN: 978-1-6654-2113-3
ISSN: 1091-0026
DOI: https://doi.org/10.1109/NSS/MIC44867.2021.9875597(external)
Web address : https://ieeexplore.ieee.org/document/9875597(external)
We evaluated 12 open source machine learning methods for classification of polar map images in cardiac perfusion positron emission tomography (PET) using a dataset consisting of 138 polar maps. Majority of the classifiers showed good accuracy in 10-fold cross-validation (mean accuracy of 0.75–0.88). Accuracy was slightly lower when applied to a separate hold-out dataset (0.70-0.87). From the evaluated classifiers, a support vector machine using a polynomial kernel, Gaussian naive Bayes classifier and a two-dimensional convolutional neural network had stable performance across both the cross-validation and hold-out datasets (accuracy of 0.78, 0.83 and 0.87).