Classification of ECG using ensemble of residual CNNs with or without attention mechanism

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68081731%3A_____%2F22%3A00557480" target="_blank" >RIV/68081731:_____/22:00557480 - isvavai.cz</a>

Výsledek na webu

<a href="https://iopscience.iop.org/article/10.1088/1361-6579/ac647c" target="_blank" >https://iopscience.iop.org/article/10.1088/1361-6579/ac647c</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1088/1361-6579/ac647c" target="_blank" >10.1088/1361-6579/ac647c</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Classification of ECG using ensemble of residual CNNs with or without attention mechanism

Popis výsledku v původním jazyce

Objective. This paper introduces a winning solution (team ISIBrno-AIMT) to the official round of PhysioNet Challenge 2021. The main goal of the challenge was a classification of ECG recordings into 26 multi-label pathological classes with a variable number of leads (e.g. 12, 6, 4, 3, 2). The main objective of this study is to verify whether the multi-head-attention mechanism influences the model performance. Approach. We introduced an ECG classification method based on the ResNet architecture with a multi-head attention mechanism for the official round of the challenge. However, empirical findings collected during model development suggested that the multi-head attention layer might not significantly impact the final classification performance. For this reason, during the follow-up round, we removed a multi-head attention layer to test the influence on model performance. Like the official round, the model is optimized using a mixture of loss functions, i.e. binary cross-entropy, custom challenge score loss function, and custom sparsity loss function. Probability thresholds for each classification class are estimated using the evolutionary optimization method. The final architecture consists of three submodels forming a majority voting classification ensemble. Main results. The modified model without the multi-head attention layer increased the overall challenge score to 0.59 compared to the 0.58 from the official round. Significance. Our findings from the follow-up submission support the fact that the multi-head attention layer in the proposed architecture does not significantly affect the classification performance.

Název v anglickém jazyce

Classification of ECG using ensemble of residual CNNs with or without attention mechanism

Popis výsledku anglicky

Objective. This paper introduces a winning solution (team ISIBrno-AIMT) to the official round of PhysioNet Challenge 2021. The main goal of the challenge was a classification of ECG recordings into 26 multi-label pathological classes with a variable number of leads (e.g. 12, 6, 4, 3, 2). The main objective of this study is to verify whether the multi-head-attention mechanism influences the model performance. Approach. We introduced an ECG classification method based on the ResNet architecture with a multi-head attention mechanism for the official round of the challenge. However, empirical findings collected during model development suggested that the multi-head attention layer might not significantly impact the final classification performance. For this reason, during the follow-up round, we removed a multi-head attention layer to test the influence on model performance. Like the official round, the model is optimized using a mixture of loss functions, i.e. binary cross-entropy, custom challenge score loss function, and custom sparsity loss function. Probability thresholds for each classification class are estimated using the evolutionary optimization method. The final architecture consists of three submodels forming a majority voting classification ensemble. Main results. The modified model without the multi-head attention layer increased the overall challenge score to 0.59 compared to the 0.58 from the official round. Significance. Our findings from the follow-up submission support the fact that the multi-head attention layer in the proposed architecture does not significantly affect the classification performance.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20601 - Medical engineering

Projekt

<a href="/cs/project/FW01010305" target="_blank" >FW01010305: Umělá inteligence pro autonomní klasifikaci EKG v rámci online telemedicínské platformy</a><br>

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2022

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Physiological Measurement

ISSN

0967-3334

e-ISSN

1361-6579

Svazek periodika

43

Číslo periodika v rámci svazku

4

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

12

Strana od-do

044001

Kód UT WoS článku

000790542900001

EID výsledku v databázi Scopus

2-s2.0-85129997154