Combining ResNet Model with Handcrafted Temporal Features for ECG Classification with Varying Number of Leads

Abstract

This study presents PhysioNauts Team's contribution to the PhysioNet/CinC Challenge 2021 on ECG classification for variable leads. Three types of labels were identified: those affecting cardiac rhythm, ECG morphology or both. The full model integrated handcrafted rhythm features and deep learning features into a residual neural network (ResNet) with a squeeze and excitation module and a wide 10-neuron single-layer fully connected (FC) branch to leverage the learning of both feature types. The ResNet inputs were ECG segments of 4096 samples downsampled to 257 Hz. The FC inputs were standard rhythm features extracted from the RR-series. Class imbalance was mitigated by selecting only a third of normal sinus rhythm and sinus bradycardia recordings. Moreover, threshold optimization was performed based on a grid search and the Nelder-Mead method to maximize the Challenge metric (CM). Our entry failed on the UMich test data, so it was not officially ranked and it didn't receive official scores on the full test set. The CMs obtained in the unofficial entry were 0.613, 0.585, 0.603, 0,594, and 0.582 on 12-lead, 6-lead, 4-lead, 3-lead, 2-lead, respectively.

A Lightweight Unidimensional Deep Learning Model for Atrial Fibrillation Detection

“…Residual networks (and variants) were very common in the "Will two do?" challenge [14,15,21] and other ECG classification tasks [22,23]. And as our proposed model is an adaptation of the VGG-11, the original model is used to compare the impact of the reduction in complexity.…”

“…However, the computational complexity of most classification models, particularly those based on deep learning algorithms, is one of the challenges for using wearable devices in continuous rhythm monitoring. To improve accuracy, these models frequently use deeper and more complex models [13,14] or ensembles of models [15], usually without taking into account the energy consumption or computational limitations of portable devices [16].…”

Ensemble classification combining ResNet and handcrafted features with three-steps training

“…In this study we present a model for ECG classification of different lengths, sampling frequencies and leads. In contrast with past Challenge submissions (Magni et al 2021, Muscato et al 2021, in this work, we perform an analysis of the best training strategy for a model integrating both a deep network and classic machine learning features emphasizing in the integration of both types of information. In addition, in contrast with (Natarajan et al 2020, Magni et al 2021, Muscato et al 2021, the present model further elaborates the integration of the wide features by changing the network structure.…”