EUVIMEDEUVIMED entdecken
Open Access

Automated HFrEF Diagnosis Using an Optimized TimeSformer Model in Echocardiography

Georgios Petmezas, Vasileios E Papageorgiou, Vassilios Vassilikos, Efstathios Pagourelias, Dimitrios Tachmatzidis, George Tsaklidis, Aggelos K Katsaggelos, Nicos Maglaveras

Journal of Imaging Informatics in Medicine · 2025

DOI: 10.1007/s10278-025-01758-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, 2025. Verfasst von Georgios Petmezas und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, Greece. petmezgs@auth.gr. Hauptthemen laut MEDLINE: Deep Learning, Heart Failure, Echocardiography, Image Interpretation, Computer-Assisted. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Heart failure with reduced ejection fraction (HFrEF) presents a significant diagnostic challenge, particularly in advanced stages. Deep learning (DL) models offer promising potential for automated HFrEF detection, but their effectiveness is often limited in small and imbalanced clinical datasets. In this study, we propose a novel approach to enhance HFrEF detection from echocardiographic videos. We adapt the TimeSformer architecture-a Transformer-based model optimized for spatiotemporal feature extraction in video data-and apply it for the first time in echocardiography. In addition, we introduce a domain-informed left ventricle (LV) masking method using image segmentation to guide model attention toward diagnostically critical regions, boosting overall performance. Our methodology is evaluated both directly on a large-scale benchmark dataset and on a smaller, specialized clinical dataset from our cardiology department after fine-tuning. Experimental results show that the proposed framework yields substantial performance gains: on the benchmark dataset, we observe a 3% improvement in both model accuracy and area under the curve (AUC), while on the specialized dataset, improvements reach 7% in accuracy and 30% in AUC values. Moreover, TimeSformer consistently outperforms conventional approaches after the implementation of fine-tuning and LV masking. These findings highlight a practical and generalizable strategy for improving automated HFrEF diagnosis, with strong implications for clinical decision support in data-scarce healthcare settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHeart FailureEchocardiographyImage Interpretation, Computer-AssistedHumansStroke VolumeAlgorithms

Stichwörter der Autor:innen

Deep learning (DL)EchocardiographyHeart failure with reduced ejection fraction (HFrEF)Left ventricle (LV) maskingSpatiotemporal TransformerTransfer learning

Autor:innen und Institutionen

  • School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, Greece. petmezgs@auth.gr.
  • Department of Mathematics, Aristotle University of Thessaloniki, Thessaloniki, Greece.
  • School of Medicine, Aristotle University of Thessaloniki, Thessaloniki, Greece.
  • Department of Electrical and Computer Engineering, Northwestern University, Evanston, IL, USA.

Zitieren

APA

Petmezas, G., Papageorgiou, V. E., Vassilikos, V., Pagourelias, E., Tachmatzidis, D., Tsaklidis, G., Katsaggelos, A. K., & Maglaveras, N. (2025). Automated HFrEF Diagnosis Using an Optimized TimeSformer Model in Echocardiography. Journal of Imaging Informatics in Medicine. https://doi.org/10.1007/s10278-025-01758-2

Vancouver

Petmezas G, Papageorgiou VE, Vassilikos V, Pagourelias E, Tachmatzidis D, Tsaklidis G, et al. Automated HFrEF Diagnosis Using an Optimized TimeSformer Model in Echocardiography. Journal of Imaging Informatics in Medicine. 2025. doi:10.1007/s10278-025-01758-2

BibTeX
@article{Petmezas2025,
  author = {Petmezas, Georgios and Papageorgiou, Vasileios E and Vassilikos, Vassilios and Pagourelias, Efstathios and Tachmatzidis, Dimitrios and Tsaklidis, George and Katsaggelos, Aggelos K and Maglaveras, Nicos},
  title = {Automated HFrEF Diagnosis Using an Optimized TimeSformer Model in Echocardiography},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2025},
  doi = {10.1007/s10278-025-01758-2}
}
Kostenlos starten →