Identification of 27 abnormalities from multi-lead ECG signals: an ensembled SE_ResNet framework with Sign Loss function

Zhu, Zhaowei; Lan, Xiang; Zhao, Tingting; Guo, Yangming; Kojodjojo, Pipin; Xu, Zhihong; Liu, Zhuo; Liu, Siqi; Wang, Han; Sun, Xingzhi; Feng, Mengling

doi:10.1088/1361-6579/ac08e6

Cited by 29 publications

(17 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Therefore, early and accurate diagnosis of ECG plays an important role in preventing severe CVD and can improve treatment outcomes (Artis, Mark, and Moody 1991). Deep learning has been applied to improve the timeliness and accuracy of diagnosis of 12-lead ECG (Hong et al 2020(Hong et al , 2019Zhu et al 2021). However, training deep learning models in a supervised manner often requires a large volume of high-quality labels to achieve strong generalization performance.…”

Section: Introductionmentioning

confidence: 99%

Intra-Inter Subject Self-Supervised Learning for Multivariate Cardiac Signals

Lan

Hong

et al. 2022

AAAI

Self Cite

View full text Add to dashboard Cite

Learning information-rich and generalizable representations effectively from unlabeled multivariate cardiac signals to identify abnormal heart rhythms (cardiac arrhythmias) is valuable in real-world clinical settings but often challenging due to its complex temporal dynamics. Cardiac arrhythmias can vary significantly in temporal patterns even for the same patient (i.e., intra subject difference). Meanwhile, the same type of cardiac arrhythmia can show different temporal patterns among different patients due to different cardiac structures (i.e., inter subject difference). In this paper, we address the challenges by proposing an Intra-Inter Subject Self-Supervised Learning (ISL) model that is customized for multivariate cardiac signals. Our proposed ISL model integrates medical knowledge into self-supervision to effectively learn from intra-inter subject differences. In intra subject self-supervision, ISL model first extracts heartbeat-level features from each subject using a channel-wise attentional CNN-RNN encoder. Then a stationarity test module is employed to capture the temporal dependencies between heartbeats. In inter subject self-supervision, we design a set of data augmentations according to the clinical characteristics of cardiac signals and perform contrastive learning among subjects to learn distinctive representations for various types of patients. Extensive experiments on three real-world datasets were conducted. In a semi-supervised transfer learning scenario, our pre-trained ISL model leads about 10% improvement over supervised training when only 1% labeled data is available, suggesting strong generalizability and robustness of the model.

show abstract

Section: Introductionmentioning

confidence: 99%

Intra-Inter Subject Self-Supervised Learning for Multivariate Cardiac Signals

Lan

Hong

et al. 2022

AAAI

Self Cite

View full text Add to dashboard Cite

show abstract

“…Indeed, the model that generalised best to the test data had the lowest per-class metrics in the validation data (Natarajan et al 2020). We further note that our model architecture was very similar to the entry that placed third in the 2020 Physionet challenge (Zhu et al 2021). The primary difference between the two models, which may explain difference in performance, was our inclusion of age and gender features.…”

Section: Comparison To Other Models Using Validation Setmentioning

confidence: 97%

Analysis of an adaptive lead weighted ResNet for multiclass classification of 12-lead ECGs

et al. 2022

View full text Add to dashboard Cite

Background - Twelve lead ECGs are a core diagnostic tool for cardiovascular diseases. Here, we describe and analyse an ensemble deep neural network architecture to classify 24 cardiac abnormalities from 12 lead ECGs. Method - We proposed a squeeze and excite ResNet to automatically learn deep features from 12-lead ECGs, in order to identify 24 cardiac conditions. The deep features were augmented with age and gender features in the final fully connected layers. Output thresholds for each class were set using a constrained grid search. To determine why the model made incorrect predictions, two expert clinicians independently interpreted a random set of 100 misclassified ECGs concerning Left Axis Deviation. Results - Using the bespoke weighted accuracy metric, we achieved a 5-fold cross-validation score of 0.684, and sensitivity and specificity of 0.758 and 0.969, respectively. We scored 0.520 on the full test data, and ranked 2nd out of 41 in the official challenge rankings. On a random set of misclassified ECGs, agreement between two clinicians and training labels was poor (clinician 1: $\kappa = -0.057$, clinician 2: $\kappa = -0.159$). In contrast, agreement between the clinicians was very high ($\kappa = 0.92$). Discussion - The proposed prediction model performed well on the validation and hidden test data in comparison to models trained on the same data. We also discovered considerable inconsistency in training labels, which is likely to hinder development of more accurate models.

show abstract

“…Recently, researchers have begun to use more sophisticated 1D-CNN architectures, particularly ones whose 2D version achieves high image classification accuracy. Zhang et al [22] proposed using 1D-ResNet34, Zhu et al [23] ensembled two 1D-SEResNet34s and one set of expert rules to identify more types of abnormalities. Furthermore, Yao et al [24] constructed Time-Incremental ResNet18 (TI-ResNet18), a combination of a 1D-ResNet18 and an LSTM network in order to capture both spatial and temporal patterns in ECG signals.…”

Section: Related Workmentioning

confidence: 99%

“…Detailed performance is presented in Table 2. For precisely benchmarking, we compared LightX3ECG with some popular ECG classification methods, which can be considered state-of-the-art including 1D-ResNet34 [22], 1D-SEResNet34 [23], InceptionTime [40], and TI-ResNet18 [24].…”

Section: System Performancementioning

confidence: 99%

LightX3ECG: A Lightweight and eXplainable Deep Learning System for 3-lead Electrocardiogram Classification

Le¹,

Pham²,

Nguyen³

et al. 2022

Preprint

View full text Add to dashboard Cite

Cardiovascular diseases (CVDs) are a group of heart and blood vessel disorders that is one of the most serious dangers to human health, and the number of such patients is still growing. Early and accurate detection plays a key role in successful treatment and intervention. Electrocardiogram (ECG) is the gold standard for identifying a variety of cardiovascular abnormalities. In clinical practices and most of the current research, standard 12-lead ECG is mainly used. However, using a lower number of leads can make ECG more prevalent as it can be conveniently recorded by portable or wearable devices. In this research, we develop a novel deep learning system to accurately identify multiple cardiovascular abnormalities by using only three ECG leads. Specifically, we use three separate Onedimensional Convolutional Neural Networks (1D-CNNs) as backbones to extract features from three input ECG leads separately. The architecture of 1D-CNNs is redesigned for high performance and low computational cost. A novel Lead-wise Attention module is then introduced to aggregate outputs from these three backbones, resulting in a more robust representation which is then passed through a Fully-Connected (FC) layer to perform classification. Moreover, to make the system's prediction clinically explainable, the Grad-CAM technique is modified to produce a high meaningful lead-wise explanation. Finally, we employ a pruning technique to reduce system size, forcing it suitable for deployment on hardware-constrained platforms. The proposed lightweight, explainable system is named LightX3ECG. We got classification performance in terms of F1 scores of 0.9718 and 0.8004 on two large-scale ECG datasets, i.e., Chapman and CPSC-2018, respectively, which surpassed current state-of-the-art methods while achieving higher computational and storage efficiency. Visual examinations and a sanity check were also performed to demonstrate the strength of our system's interpretability. To encourage further development, our source code is publicly available at https://github.com/lhkhiem28/LightX3ECG.

show abstract

Identification of 27 abnormalities from multi-lead ECG signals: an ensembled SE_ResNet framework with Sign Loss function

Cited by 29 publications

References 30 publications

Intra-Inter Subject Self-Supervised Learning for Multivariate Cardiac Signals

Intra-Inter Subject Self-Supervised Learning for Multivariate Cardiac Signals

Analysis of an adaptive lead weighted ResNet for multiclass classification of 12-lead ECGs

LightX3ECG: A Lightweight and eXplainable Deep Learning System for 3-lead Electrocardiogram Classification

Contact Info

Product

Resources

About