A deep learning approach using 3-D ECG images achieved classification accuracy scores of 0.39 to 0.40 for identifying cardiac abnormalities across variable lead configurations.
A deep learning approach using 3-D time-spatial images of ECG signals achieved moderate classification accuracy for cardiac abnormalities across variable lead configurations.
The objective of this study is to explore new imaging techniques with the use of the deep learning method for the identification of cardiac abnormalities present in ECG recordings with 2, 3, 4, 6 and 12-lead in the framework of the PhysioNet Challenge 2021. The training set is a public database of 88253 twelve-lead ECG recordings lasting from 6 seconds to 60 seconds. Each ECG recording has one or more diagnostic labels. The six-lead, four-lead, three-lead, and two-lead are reduced-lead version of the original twelve-lead data. The deep learning method considers images that are built from raw ECG signals. This technique considers innovative 3-D images of the entire ECG signal, observing the regional constraints of the leads, obtaining time-spatial images, where the x-axis is the temporal evolution of ECG signal, the y axis is the spatial location of the leads, and the z axis (color) the amplitude. These images are used for training Convolutional Neural Networks with GoogleNet for ECG diagnostic classification. The official results of the classification accuracy of our team named 'Gioₙewᵢmg’ received score of 0. 4, 0. 4, 0. 39, 0. 4 and 0. 4 (ranked 18th, 18th; 18th, 18th, 18th out of 39 teams) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden test set with the Challenge evaluation metric.
G. Bortolan (Mon,) conducted a other in Cardiac abnormalities (n=88,253). 3-D ECG images with Deep Learning Approach (Convolutional Neural Networks with GoogleNet) was evaluated on Classification accuracy (Challenge evaluation metric) on the hidden test set. A deep learning approach using 3-D ECG images achieved classification accuracy scores of 0.39 to 0.40 for identifying cardiac abnormalities across variable lead configurations.