Towards Domain Generalization for ECG and EEG Classification: Algorithms and Benchmarks

被引:10
作者
Ballas, Aristotelis [1 ]
Diou, Christos [2 ]
机构
[1] Harokopio Univ Athens, Informat & Telemat, Athens 15772, Greece
[2] Harokopio Univ Athens, Dept Informat & Telemat, Athens 17778, Greece
来源
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE | 2024年 / 8卷 / 01期
基金
欧盟地平线“2020”;
关键词
Biosignal classification; deep learning; domain generalization; 1D signal classification; electrocardiogram (ECG) classification; electroencephalogram (EEG) classification; ADAPTATION; DATABASE;
D O I
10.1109/TETCI.2023.3306253
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Despite their immense success in numerous fields, machine and deep learning systems have not yet been able to firmly establish themselves in mission-critical applications in healthcare. One of the main reasons lies in the fact that when models are presented with previously unseen, Out-of-Distribution samples, their performance deteriorates significantly. This is known as the Domain Generalization (DG) problem. Our objective in this work is to propose a benchmark for evaluating DG algorithms, in addition to introducing a novel architecture for tackling DG in biosignal classification. In this article, we describe the Domain Generalization problem for biosignals, focusing on electrocardiograms (ECG) and electroencephalograms (EEG) and propose and implement an open-source biosignal DG evaluation benchmark. Furthermore, we adapt state-of-the-art DG algorithms from computer vision to the problem of 1D biosignal classification and evaluate their effectiveness. Finally, we also introduce a novel neural network architecture that leverages multi-layer representations for improved model generalizability. By implementing the above DG setup we are able to experimentally demonstrate the presence of the DG problem in ECG and EEG datasets. In addition, our proposed model demonstrates improved effectiveness compared to the baseline algorithms, exceeding the state-of-the-art in both datasets. Recognizing the significance of the distribution shift present in biosignal datasets, the presented benchmark aims at urging further research into the field of biomedical DG by simplifying the evaluation process of proposed algorithms. To our knowledge, this is the first attempt at developing an open-source framework for evaluating ECG and EEG DG algorithms.
引用
收藏
页码:44 / 54
页数:11
相关论文
共 66 条
[1]  
Arjovsky M., 2020, arXiv
[2]  
Ballas A., 2022, P 2020 5 INT C COMP, P1
[3]   Multi-layer Representation Learning for Robust OOD Image Classification [J].
Ballas, Aristotelis ;
Diou, Christos .
PROCEEDINGS OF THE 12TH HELLENIC CONFERENCE ON ARTIFICIAL INTELLIGENCE, SETN 2022, 2022,
[4]   CNNs with Multi-Level Attention for Domain Generalization [J].
Ballas, Aristotelis ;
Diou, Cristos .
PROCEEDINGS OF THE 2023 ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA RETRIEVAL, ICMR 2023, 2023, :592-596
[5]   A Domain Generalization Approach for Out-Of-Distribution 12-lead ECG Classification with Convolutional Neural Networks [J].
Ballas, Aristotelis ;
Diou, Christos .
2022 IEEE EIGHTH INTERNATIONAL CONFERENCE ON BIG DATA COMPUTING SERVICE AND APPLICATIONS, BIGDATASERVICE, 2022, :9-13
[6]   Uncovering the structure of clinical EEG signals with self-supervised learning [J].
Banville, Hubert ;
Chehab, Omar ;
Hyvarinen, Aapo ;
Engemann, Denis-Alexander ;
Gramfort, Alexandre .
JOURNAL OF NEURAL ENGINEERING, 2021, 18 (04)
[7]   SELF-SUPERVISED REPRESENTATION LEARNING FROM ELECTROENCEPHALOGRAPHY SIGNALS [J].
Banville, Hubert ;
Albuquerque, Isabela ;
Hyvarinen, Aapo ;
Moffat, Graeme ;
Engemann, Denis-Alexander ;
Gramfort, Alexandre .
2019 IEEE 29TH INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), 2019,
[8]  
Blanchard G., 2011, ADV NEURAL INFORM PR, V24
[9]   Domain Generalization by Solving Jigsaw Puzzles [J].
Carlucci, Fabio M. ;
D'Innocente, Antonio ;
Bucci, Silvia ;
Caputo, Barbara ;
Tommasi, Tatiana .
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019), 2019, :2224-2233
[10]   Domain Generalization in Biosignal Classification [J].
Dissanayake, Theekshana ;
Fernando, Tharindu ;
Denman, Simon ;
Ghaemmaghami, Houman ;
Sridharan, Sridha ;
Fookes, Clinton .
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, 2021, 68 (06) :1978-1989