|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
The role of automatic electrocardiogram (ECG) analysis in clinical practice is limited by the accuracy of existing models.
Access to electronic health record (EHR) data has motivated computational advances in medical research.
Ranked #1 on Arrhythmia Detection on The PhysioNet Computing in Cardiology Challenge 2017 (Accuracy (TRAIN-DB) metric)
We propose ENCASE to combine expert features and DNNs (Deep Neural Networks) together for ECG classification.
Ranked #1 on Time Series Classification on Physionet 2017 Atrial Fibrillation (F1 (Hidden Test Set) metric)
Finally, the models were deployed to a Docker image, trained on the provided development data, and tested on the Challenge validation set.
Ranked #1 on ECG Classification on PhysioNet Challenge 2020
Considering the quasi-periodic characteristics of ECG signals, the dynamic features can be extracted from the TMF images with the transfer learning pre-trained convolutional neural network (CNN) models.
Then, in order to alleviate the overfitting problem in two-dimensional network, we initialize AlexNet-like network with weights trained on ImageNet, to fit the training ECG images and fine-tune the model, and to further improve the accuracy and robustness of ECG classification.
Thus, it is challenging and essential to improve robustness of DNNs against adversarial noises for ECG signal classification, a life-critical application.