Inhalt anspringen

Lightweight Deep Learning-Based Aortic Valve Segmentation on RGB Images

Schnelle Fakten

  • Weitere Publizierende

    Dinithi Warnakulasuriya, Dennis Schuldt, Michael Bogatzki, Francisco Javier Carrero Gomez

  • Veröffentlichung

    • 2025
    • Band 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
  • Titel des Konferenzbands

    47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society

  • Organisationseinheit

  • Fachgebiete

    • Angewandte Informatik
    • Biomedizinische Technik
    • Informatik allgemein
    • Ingenieurwissenschaften allgemein
    • Kommunikations- und Informationstechnik
    • Künstliche Intelligenz
    • Medizintechnik
  • Forschungsschwerpunkte

    • BioMedizinTechnik (BMT)
  • Format

    Konferenzpaper

Zitat

D. Fromme, T. Streckert, D. Warnakulasuriya, D. Schuldt, M. Bogatzki, F. J. C. Gomez, and J. Thiem, “Lightweight Deep Learning-Based Aortic Valve Segmentation on RGB Images,” in 47th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2025, p. 11253048.

Abstract

Accurate segmentation of aortic valve cusps is important for facilitating surgical assessment and computational modeling. This study evaluates the feasibility of MobileNetV3 + DeepLabV3+ for aortic valve segmentation using RGB images and examines the impact of synthetic data augmentation and unsupervised pretraining. A dataset of porcine aortic valves was used for training and evaluation, following a Leave-One-Heart-Out Cross-Validation (LOHO-CV) strategy. Synthetic images generated by a conditional Denoising Diffusion Probabilistic Model (cDDPM) were integrated into training, and unsupervised pretraining via a deep convolutional autoencoder (DCAE) was tested. Performance was assessed using mean Intersection over Union (mIoU) and accuracy. The model achieved an average mIoU exceeding 0.93 across LOHO-CV splits, demonstrating its capability for accurate segmentation with minimal computational cost. Synthetic data improved segmentation accuracy, while unsupervised pretraining accelerated convergence but had no significant effect on final performance. The low standard deviation suggests high robustness across different heart specimens. Our findings confirm that small, efficient deep learning models are sufficient for aortic valve segmentation, reducing the need for larger architectures. Synthetic data augmentation enhances performance, while unsupervised pretraining may help reduce annotation efforts. Future work will focus on dataset expansion and instance-based segmentation to eliminate preprocessing steps.

Schlagwörter

Image segmentation techniques

Machine learning and AI-enhanced imaging

Performance evaluation and benchmarking

Erläuterungen und Hinweise

Diese Seite verwendet Cookies, um die Funktionalität der Webseite zu gewährleisten und statistische Daten zu erheben. Sie können der statistischen Erhebung über die Datenschutzeinstellungen widersprechen (Opt-Out).

Einstellungen (Öffnet in einem neuen Tab)