Analyzing the performance of biomedical time-series segmentation with electrophysiology data

Simple item page
dc.contributor.authorŘedina, Richardcs
dc.contributor.authorHejč, Jakubcs
dc.contributor.authorFilipenská, Marinacs
dc.contributor.authorStárek, Zdeněkcs
dc.coverage.issue1cs
dc.coverage.volume15cs
dc.date.accessioned2025-04-15T05:56:42Z
dc.date.available2025-04-15T05:56:42Z
dc.date.issued2025-04-06cs
dc.description.abstractAccurate segmentation of biomedical time-series, such as intracardiac electrograms, is vital for understanding physiological states and supporting clinical interventions. Traditional rule-based and feature engineering approaches often struggle with complex clinical patterns and noise. Recent deep learning advancements offer solutions, showing various benefits and drawbacks in segmentation tasks. This study evaluates five segmentation algorithms, from traditional rule-based methods to advanced deep learning models, using a unique clinical dataset of intracardiac signals from 100 patients. We compared a rule-based method, a support vector machine (SVM), fully convolutional semantic neural network (UNet), region proposal network (Faster R-CNN), and recurrent neural network for electrocardiographic signals (DENS-ECG). Notably, Faster R-CNN has never been applied to 1D signals segmentation before. Each model underwent Bayesian optimization to minimize hyperparameter bias. Results indicated that deep learning models outperformed traditional methods, with UNet achieving the highest segmentation score of 88.9 % (root mean square errors for onset and offset of 8.43 ms and 7.49 ms), closely followed by DENS-ECG at 87.8 %. Faster R-CNN and SVM showed moderate performance, while the rule-based method had the lowest accuracy (77.7 %). UNet and DENS-ECG excelled in capturing detailed features and handling noise, highlighting their potential for clinical application. Despite greater computational demands, their superior performance and diagnostic potential support further exploration in biomedical time-series analysis.en
dc.formattextcs
dc.format.extent1-15cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationScientific Reports. 2025, vol. 15, issue 1, p. 1-15.en
dc.identifier.doi10.1038/s41598-025-90533-ycs
dc.identifier.issn2045-2322cs
dc.identifier.orcid0000-0002-4901-0504cs
dc.identifier.orcid0000-0001-5743-9960cs
dc.identifier.orcid0000-0003-1366-8336cs
dc.identifier.other197662cs
dc.identifier.researcheridADX-2772-2022cs
dc.identifier.researcheridQ-9341-2017cs
dc.identifier.researcheridA-1855-2016cs
dc.identifier.scopus56764705500cs
dc.identifier.scopus37104795300cs
dc.identifier.urihttps://hdl.handle.net/11012/250890
dc.language.isoencs
dc.publisherNATURE PORTFOLIOcs
dc.relation.ispartofScientific Reportscs
dc.relation.urihttps://www.nature.com/articles/s41598-025-90533-y#Sec23cs
dc.rightsCreative Commons Attribution-NonCommercial-NoDerivatives 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/2045-2322/cs
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/cs
dc.subjectTime-series Segmentationen
dc.subjectElectrophysiology Studyen
dc.subjectRule-based Delineationen
dc.subjectSupport Vector Machinesen
dc.subjectU-Neten
dc.subjectFaster R-CNNen
dc.subjectDENS-ECGen
dc.titleAnalyzing the performance of biomedical time-series segmentation with electrophysiology dataen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-197662en
sync.item.dbtypeVAVen
sync.item.insts2025.04.15 07:56:42en
sync.item.modts2025.04.15 07:33:17en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav biomedicínského inženýrstvícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
s4159802590533y.pdf
Size:
4.85 MB
Format:
Adobe Portable Document Format
Description:
file s4159802590533y.pdf
Download
Collections
Ústav biomedicínského inženýrství