Classification of ECG Using Ensemble of Residual CNNs with Attention Mechanism

0555163 - ÚPT 2022 RIV US eng C - Konferenční příspěvek (zahraniční konf.)
Nejedlý, Petr - Ivora, Adam - Smíšek, Radovan - Viščor, Ivo - Koščová, Zuzana - Jurák, Pavel - Plešinger, Filip
Classification of ECG Using Ensemble of Residual CNNs with Attention Mechanism.
2021 Computing in Cardiology (CinC). Vol. 48. New York: IEEE, 2021, č. článku 14. ISBN 978-166547916-5. ISSN 2325-8861. E-ISSN 2325-887X.
[Computing in Cardiology 2021 /48./. Brno (CZ), 12.09.2021-15.09.2021]
Grant CEP: GA TA ČR(CZ) FW01010305
Institucionální podpora: RVO:68081731
Klíčová slova: Residual CNNs * Classification of ECG * Physionet Challenge
Obor OECD: Medical engineering
https://ieeexplore.ieee.org/document/9662723

This paper introduces a winning solution (team ISIBrno-AIMT) to the PhysioNet Challenge 2021. The method is based on the ResNet deep neural network architecture with a multi-head attention mechanism for ECG classification into 26 independent groups. The model is optimized using a mixture of loss functions, i.e., binary cross-entropy, custom challenge score loss function, and sparsity loss function. Probability thresholds for each classification class are estimated using the evolutionary optimization method. The final model consists of three submodels forming a majority voting classification ensemble. The proposed method classifies ECGs with a variable number of leads, e.g., 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead. The algorithm was validated and tested on the external hidden datasets (CPSC, G12EC, undisclosed set, UMich), achieving a challenge score 0.58 for all tested lead configurations. The total training time was approximately 27 hours, i.e., 9 hours per model. The presented solution was ranked first across all 39 teams in all categories.
Trvalý link: http://hdl.handle.net/11104/0329694