Label noise and self-learning label correction in cardiac abnormalities classification.

Gallego Vázquez, Cristina; Breuss, Alexander; Gnarra, Oriella; Portmann, Julian; Madaffari, Antonio; Da Poian, Giulia (2022). Label noise and self-learning label correction in cardiac abnormalities classification. Physiological measurement, 43(9) Institute of Physics Publishing IOP 10.1088/1361-6579/ac89cb

Preview

Text Gallego_V_zquez_et_al_2022_Physiol._Meas._10.1088_1361-6579_ac89cb.pdf - Accepted Version Available under License Creative Commons: Attribution (CC-BY). Download (615kB) | Preview

OBJECTIVE

Learning to classify cardiac abnormalities requires large and high-quality labeled datasets, which is a challenge in medical applications. Small datasets from various sources are often aggregated to meet this requirement, resulting in a final dataset prone to label noise owing to inter- and intra-observer variability, and different expertise. It is well known that label noise can affect the performance and generalizability of the trained models. In this work, we explore the impact of label noise and self-learning label correction on the classification of cardiac abnormalities on large heterogeneous datasets of electrocardiogram (ECG) signals.

APPROACH

A state-of-the-art self-learning multi-class label correction method for image classification is adapted to learn a multi-label classifier for electrocardiogram signals. We evaluated our performance using 5-fold cross-validation on the publicly available PhysioNet/Computing in Cardiology (CinC) 2021 Challenge data, with full and reduced sets of leads. Due to the unknown label noise in the testing set, we tested our approach on the MNIST dataset. We investigated the performance under different levels of structured label noise for both datasets.

MAIN RESULTS

Under high levels of noise, the cross-validation results of self-learning label correction showed an improvement of approximately 3% in the Challenge score for the PhysioNet/CinC 2021 Challenge dataset and, an improvement in accuracy of 5$\%$ and reduction of the expected calibration error of 0.03 for the MNIST dataset. We demonstrate that self-learning label correction can be used to effectively deal with the presence of unknown label noise, also when using a reduced number of ECG leads.

Interest & Impact

Downloads

35 since deposited on 17 Aug 2022
35 in the past 12 months

Citations

5 Citations in Web of Science ®
6 Citations in Scopus

Search

in Google Scholar™

Services

Actions (login required)

Edit item

Actions (login required)

Edit item