EUVIMEDEUVIMED entdecken
Crossref

BEAS-Net: A Shape-Prior-Based Deep Convolutional Neural Network for Robust Left Ventricular Segmentation in 2-D Echocardiography

Somayeh Akbari, Mahdi Tabassian, Joao Pedrosa, Sandro Queiros, Konstantina Papangelopoulou, Jan D'hooge

IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control · 2024

DOI: 10.1109/tuffc.2024.3418030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2024. Verfasst von Somayeh Akbari und 5 weiteren Autor:innen. Hauptthemen laut MEDLINE: Heart Ventricles, Echocardiography, Neural Networks, Computer, Deep Learning. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 58 Literaturangaben. Gefördert von: Research Foundation Flanders, Foundation for Science and Technology (FCT) through Portuguese National funds.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Left ventricle (LV) segmentation of 2-D echocardiography images is an essential step in the analysis of cardiac morphology and function and-more generally-diagnosis of cardiovascular diseases (CVD). Several deep learning (DL) algorithms have recently been proposed for the automatic segmentation of the LV, showing significant performance improvement over the traditional segmentation algorithms. However, unlike the traditional methods, prior information about the segmentation problem, e.g., anatomical shape information, is not usually incorporated for training the DL algorithms. This can degrade the generalization performance of the DL models on unseen images if their characteristics are somewhat different from those of the training images, e.g., low-quality testing images. In this study, a new shape-constrained deep convolutional neural network (CNN)-called B-spline explicit active surface (BEAS)-Net-is introduced for automatic LV segmentation. The BEAS-Net learns how to associate the image features, encoded by its convolutional layers, with anatomical shape-prior information derived by the BEAS algorithm to generate physiologically meaningful segmentation contours when dealing with artifactual or low-quality images. The performance of the proposed network was evaluated using three different in vivo datasets and was compared with a deep segmentation algorithm based on the U-Net model. Both the networks yielded comparable results when tested on images of acceptable quality, but the BEAS-Net outperformed the benchmark DL model on artifactual and low-quality images.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Heart VentriclesEchocardiographyNeural Networks, ComputerDeep LearningImage Processing, Computer-AssistedHumansAlgorithmsConvolutional Neural Networks

Förderung

  • Research Foundation Flanders
  • Foundation for Science and Technology (FCT) through Portuguese National funds

Zitieren

APA

Akbari, S., Tabassian, M., Pedrosa, J., Queiros, S., Papangelopoulou, K., & D'hooge, J. (2024). BEAS-Net: A Shape-Prior-Based Deep Convolutional Neural Network for Robust Left Ventricular Segmentation in 2-D Echocardiography. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. https://doi.org/10.1109/tuffc.2024.3418030

Vancouver

Akbari S, Tabassian M, Pedrosa J, Queiros S, Papangelopoulou K, D'hooge J. BEAS-Net: A Shape-Prior-Based Deep Convolutional Neural Network for Robust Left Ventricular Segmentation in 2-D Echocardiography. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control. 2024. doi:10.1109/tuffc.2024.3418030

BibTeX
@article{Akbari2024,
  author = {Akbari, Somayeh and Tabassian, Mahdi and Pedrosa, Joao and Queiros, Sandro and Papangelopoulou, Konstantina and D'hooge, Jan},
  title = {BEAS-Net: A Shape-Prior-Based Deep Convolutional Neural Network for Robust Left Ventricular Segmentation in 2-D Echocardiography},
  journal = {IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control},
  year = {2024},
  doi = {10.1109/tuffc.2024.3418030}
}
Kostenlos starten →