A Deep Learning Approach with Stack of Sub-classifiers for Multi-label Classification of Obstructive Disease from Myocardial Perfusion SPECT

• Autorzy: Trieu Ninh Ngan , Phung Nhu Hai , Nguyen Chi Thanh , Nguyen Thanh Trung

Identyfikatory

DOI

10.15439/2022R07

• Języki publikacji: EN

Abstrakty

EN

Artificial intelligence applications, especially deep learning in medical imaging, have gained much attention in recent years. With the computer's aid, Coronary artery disease (CAD) - one of the most dangerous cardiovascular diseases - is diagnosed effectively without human interference and efforts. A lot of research involving predicting CAD from Myocardial Perfusion SPECT has been conducted and given impressive results. However, all existing methods detect whether there is a disease or not. They do not provide information about which obstructive areas are (mainly in the left anterior descending artery (LAD), left circumflex artery (LCx), and right coronary artery (RCA) territories) that result in CAD. To further diagnose CAD, we develop new classifiers to solve a multi-label classification problem with the highest accuracy and area under the receiver operating characteristics curve (AUC) when compared to different methods. Our proposed method is based on transfer learning to extract features from Myocardial Perfusion SPECT Polar Maps and a novel stack of sub-classifiers to detect particularly obstructive areas. We evaluated our methods with eight hundred and one obstructive images from a database of patients referred to a hospital from 2017 to 2019.

Słowa kluczowe

EN

CAD; Myocardial Perfusion SPECT; multilabel classification; transfer learning; coronary artery disease

• Wydawca: Polskie Towarzystwo Informatyczne
• Czasopismo: Annals of Computer Science and Information Systems
• Rocznik: 2022
• Tom: Vol. 33
• Strony: 261--266
• Opis fizyczny: Bibliogr. 13 poz., rys., tab., wykr.

Twórcy

autor

Trieu Ninh Ngan

• Faculty of Information Technology Le Quy Don Technical University Hanoi, Vietnam

autor

Phung Nhu Hai

• Institute of Information Technology AMST Hanoi, Vietnam

autor

Nguyen Chi Thanh

• Institute of Information Technology AMST Hanoi, Vietnam

autor

Nguyen Thanh Trung

• Department of Medical Equipment 108 Military Central Hospital Hanoi, Vietnam

Bibliografia

• [1] Cardiovascular diseases. World Health Organization, https://www.who.int/health-topics/cardiovascular-diseases, accessed on 2022-06-14
• [2] Coronary artery disease. Mayo Foundation for Medical Education and Research (May 2022), https://www.mayoclinic.org/diseases-conditions/coronary-artery-disease/symptoms-causes/syc-20350613, accessed on 2022-06-14
• [3] Apostolopoulos, I., Papathanasiou, N., Spyridonidis, T., Apostolopoulos, D.: Automatic characterization of myocardial perfusion imaging polar maps employing deep learning and data augmentation. Hellenic journal of nuclear medicine 23 (07 2020). https://doi.org/10.1967/s002449912101
• [4] Betancur, J., Commandeur, F., Motlagh, M., Sharir, T., Einstein, A.J., Bokhari, S., Fish, M.B., Ruddy, T.D., Kaufmann, P., Sinusas, A.J., et al.: Deep learning for prediction of obstructive disease from fast myocardial perfusion spect: a multicenter study. JACC: Cardiovascular Imaging 11(11), 1654–1663 (2018)
• [5] Betancur, J., Hu, L.H., Commandeur, F., Sharir, T., Einstein, A.J., Fish, M.B., Ruddy, T.D., Kaufmann, P.A., Sinusas, A.J., Miller, E.J., et al.: Deep learning analysis of upright-supine high-efficiency spect myocardial perfusion imaging for prediction of obstructive coronary artery disease: a multicenter study. Journal of Nuclear Medicine 60(5), 664–670 (2019)
• [6] He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. pp. 770–778 (06 2016). https://doi.org/10.1109/CVPR.2016.90
• [7] Hesse, B., Tägil, K., Cuocolo, A., Anagnostopoulos, C., Bardiès, M., Bax, J., Bengel, F., Busemann Sokole, E., Davies, G., Dondi, M., et al.: Eanm/esc procedural guidelines for myocardial perfusion imaging in nuclear cardiology. European journal of nuclear medicine and molecular imaging 32(7), 855–897 (2005)
• [8] Holly, T., Abbott, B., Al-Mallah, M., Calnon, D., Cohen, M., DiFilippo, F., Ficaro, E., Freeman, M., Hendel, R., Jain, D., Leonard, S., Nichols, K., Polk, D., Soman, P.: Single photon-emission computed tomography (10 2010). https://doi.org/10.1007/s12350-010-9246-y
• [9] Kaplan Berkaya, S., Ak, I., Gunal, S.: Classification models for spect myocardial perfusion imaging. Computers in Biology and Medicine 123, 103893 (07 2020). https://doi.org/10.1016/j.compbiomed.2020.103893
• [10] Papandrianos, N., Papageorgiou, E.: Automatic diagnosis of coronary artery disease in spect myocardial perfusion imaging employing deep learning. Applied Sciences 11(14), 6362 (2021)
• [11] Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv 1409.1556 (09 2014)
• [12] de Souza Filho, E.M., Fernandes, F.d.A., Wiefels, C., de Carvalho, L.N.D., dos Santos, T.F., dos Santos, A.A.S.M.D., Mesquita, E.T., Seixas, F.L., Chow, B.J.W., Mesquita, C.T., Gismondi, R.A.: Machine learning algorithms to distinguish myocardial perfusion spect polar maps. Frontiers in Cardiovascular Medicine 8, 1437 (2021). https://doi.org/10.3389/fcvm.2021.741667, https://www.frontiersin.org/article/10.3389/fcvm.2021.741667
• [13] Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. pp. 2818–2826 (06 2016). https://doi.org/10.1109/CVPR.2016.308

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2024).