A deep residual inception network with channel attention modules for multi-label cardiac abnormality detection from reduced-lead ECG

Simple item page
dc.contributor.authorSrivastava, Apoorva
dc.contributor.authorPratiher, Sawon
dc.contributor.authorAlam, Sazedul
dc.contributor.authorHari, Ajith
dc.contributor.authorBanerjee, Nilanjan
dc.contributor.authorGhosh, Nirmalya
dc.contributor.authorPatra, Amit
dc.date.accessioned2022-06-24T17:39:24Z
dc.date.available2022-06-24T17:39:24Z
dc.date.issued2022-05-12
dc.description.abstractObjective. Most arrhythmias due to cardiovascular diseases alter the electrical activity, resulting in morphological alterations in electrocardiogram (ECG) recordings. ECG acquisition is a low-cost, non-invasive process and is commonly used for continuous monitoring as a diagnostic tool for cardiac abnormality identification. Our objective is to diagnose twenty-nine cardiac abnormalities and sinus rhythm using varied lead ECG signals. Approach. This work proposes a deep residual inception network with channel attention mechanism (RINCA) for twenty-nine cardiac arrhythmia classification (CAC) along with normal ECG from multi-label ECG signal with different lead combinations. The RINCA architecture employing the Inception-based convolutional neural network backbone uses residual skip connections with the channel attention mechanism. The Inception model facilitates efficient computation and prevents overfitting while exploring deeper networks through dimensionality reduction and stacked 1-dimensional convolutions. The residual skip connections alleviate the vanishing gradient problem. The attention modules selectively leverage the temporally significant segments in a sequence and predominant channels for multi-lead ECG signals, contributing to the decision-making. Main results. Exhaustive experimental evaluation on the large-scale 'PhysioNet/Computing in Cardiology Challenge (2021)' dataset demonstrates RINCA efficacy. On the hidden test data set, RINCA achieves the challenge metric score of 0.55, 0.51, 0.53, 0.51, and 0.53 (ranked 2nd, 5th, 4th, 5th and 4th) for the twelve-lead, six-lead, four-lead, three-lead, and two-lead combination cases, respectively. Significance. The proposed RINCA model is more robust against varied sampling frequency, recording time, and data with heterogeneous demographics than the existing art. The explainability analysis shows RINCA potential in clinical interpretations.en_US
dc.description.urihttps://iopscience.iop.org/article/10.1088/1361-6579/ac6f40en_US
dc.format.extent20 pagesen_US
dc.genrejournal articlesen_US
dc.genrepostprintsen_US
dc.identifierdoi:10.13016/m2gih2-lrlb
dc.identifier.citationApoorva Srivastava et al 2022 Physiol. Meas. in press https://doi.org/10.1088/1361-6579/ac6f40en_US
dc.identifier.urihttps://doi.org/10.1088/1361-6579/ac6f40
dc.identifier.urihttp://hdl.handle.net/11603/25039
dc.language.isoen_USen_US
dc.publisherIOPen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Student Collection
dc.rightsThis is an author-created, un-copyedited version of an article accepted for publication/published in Physiological Measurement. IOP Publishing Ltd is not responsible for any errors or omissions in this version of the manuscript or any version derived from it. The Version of Record is available online at https://doi.org/10.1088/1361-6579/ac6f40en_US
dc.rightsAccess to this item will begin on date May 12, 2023
dc.titleA deep residual inception network with channel attention modules for multi-label cardiac abnormality detection from reduced-lead ECGen_US
dc.typeTexten_US
dcterms.creatorhttps://orcid.org/0000-0001-6887-1919en_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Srivastava+et+al_2022_Physiol._Meas._10.1088_1361-6579_ac6f40.pdf
Size:
2.94 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.56 KB
Format:
Item-specific license agreed upon to submission
Description:
Download

Collections

UMBC Computer Science and Electrical Engineering Department
UMBC Faculty Collection
UMBC Student Collection