EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Optimising Generalisable Deep Learning Models for CT Coronary Segmentation: A Multifactorial Evaluation

Shisheng Zhang, Ramtin Gharleghi, Sonit Singh, Chi Shen, Dona Adikari, Mingzi Zhang, Daniel Moses, Dominic Vickers, Arcot Sowmya, Susann Beier

Journal of Imaging Informatics in Medicine · 18.09.2025 · 39 (3) · 2680-2694

DOI: 10.1007/s10278-025-01677-2 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Imaging Informatics in Medicine, online erschienen am 18.09.2025. Verfasst von Shisheng Zhang und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, Australia. shisheng.zhang@unsw.edu.au. Hauptthemen laut MEDLINE: Deep Learning, Computed Tomography Angiography, Coronary Angiography, Coronary Artery Disease. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 71 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Health and Medical Research Council, NSW Ministry of Health, Australian Government.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coronary artery disease (CAD) remains a leading cause of morbidity and mortality worldwide, with incidence rates continuing to rise. Automated coronary artery medical image segmentation can ultimately improve CAD management by enabling more advanced and efficient diagnostic assessments. Deep learning-based segmentation methods have shown significant promise and offered higher accuracy while reducing reliance on manual inputs. However, achieving consistent performance across diverse datasets remains a persistent challenge due to substantial variability in imaging protocols, equipment and patient-specific factors, such as signal intensities, anatomical differences and disease severity. This study investigates the influence of image quality and resolution, governed by vessel size and common disease characteristics that introduce artefacts, such as calcification, on coronary artery segmentation accuracy in computed tomography coronary angiography (CTCA). Two datasets were utilised for model training and validation, including the publicly available ASOCA dataset (40 cases) and a GeoCAD dataset (70 cases) with more cases of coronary disease. Coronary artery segmentations were generated using three deep learning frameworks/architectures: default U-Net, Swin-UNETR, and EfficientNet-LinkNet. The impact of various factors on model generalisation was evaluated, focusing on imaging characteristics (contrast-to-noise ratio, artery contrast enhancement, and edge sharpness) and the extent of calcification at both the coronary tree and individual vessel branch levels. The calcification ranges considered were 0 (no calcification), 1–99 (low), 100–399 (moderate), and > 400 (high). The findings demonstrated that image features, including artery contrast enhancement ( r = 0.408, p < 0.001) and edge sharpness ( r = 0.239, p = 0.046), were significantly correlated with improved segmentation performance in test cases. Regardless of severity, calcification had a negative impact on segmentation accuracy, with low calcification affecting the segmentation most poorly ( p < 0.05). This may be because smaller calcified lesions produce less distinct contrast against the bright lumen, making it harder for the model to accurately identify and segment these lesions. Additionally, in males, a larger diameter of the first obtuse marginal branch (OM1) ( p = 0.036) was associated with improved segmentation performance for OM1. Similarly, in females, larger diameters of left main (LM) coronary artery ( p = 0.008) and right coronary artery (RCA) ( p < 0.001) were associated with better segmentation performance for LM and RCA, respectively. These findings emphasise the importance of accounting for imaging characteristics and anatomical variability when developing generalisable deep learning models for coronary artery segmentation. Unlike previous studies, which broadly acknowledge the role of image quality in segmentation, our work quantitatively demonstrates the extent to which contrast enhancement, edge sharpness, calcification and vessel diameter impact segmentation performance, offering a data-driven foundation for model adaptation strategies. Potential improvements include optimising pre-segmentation imaging (e.g. ensuring adequate edge sharpness in low-contrast regions) and developing algorithms to address vessel-specific challenges, such as improving segmentation of low-level calcifications and accurately identifying LM, RCA and OM1 of smaller diameters.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningComputed Tomography AngiographyCoronary AngiographyCoronary Artery DiseaseRadiographic Image Interpretation, Computer-AssistedHumansCoronary VesselsMaleFemale

Stichwörter der Autor:innen

CTCAComputed tomography coronary angiographyConvolutional neural networksCoronary artery segmentationDeep learningModel generalisability

Autor:innen und Institutionen

  • School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, Australia. shisheng.zhang@unsw.edu.au.
  • School of Mechanical and Manufacturing Engineering, University of New South Wales, Sydney, Australia.
  • School of Computer Science and Engineering, University of New South Wales, Sydney, Australia.
  • School of Medicine, University of New South Wales, Sydney, Australia.
  • Centre for Healthy Futures, Torrens University Australia, Sydney, NSW, Australia.
  • Department of Radiology, Prince of Wales Hospital, Sydney, Australia.

Förderung

  • National Health and Medical Research Council
  • NSW Ministry of Health
  • Australian Government
  • University of New South Wales

Zitieren

APA

Zhang, S., Gharleghi, R., Singh, S., Shen, C., Adikari, D., Zhang, M., Moses, D., Vickers, D., Sowmya, A., & Beier, S. (2025). Optimising Generalisable Deep Learning Models for CT Coronary Segmentation: A Multifactorial Evaluation. Journal of Imaging Informatics in Medicine, 39(3), 2680-2694. https://doi.org/10.1007/s10278-025-01677-2

Vancouver

Zhang S, Gharleghi R, Singh S, Shen C, Adikari D, Zhang M, et al. Optimising Generalisable Deep Learning Models for CT Coronary Segmentation: A Multifactorial Evaluation. Journal of Imaging Informatics in Medicine. 2025;39(3):2680-2694. doi:10.1007/s10278-025-01677-2

BibTeX
@article{Zhang2025,
  author = {Zhang, Shisheng and Gharleghi, Ramtin and Singh, Sonit and Shen, Chi and Adikari, Dona and Zhang, Mingzi and Moses, Daniel and Vickers, Dominic and Sowmya, Arcot and Beier, Susann},
  title = {Optimising Generalisable Deep Learning Models for CT Coronary Segmentation: A Multifactorial Evaluation},
  journal = {Journal of Imaging Informatics in Medicine},
  year = {2025},
  volume = {39},
  number = {3},
  pages = {2680--2694},
  doi = {10.1007/s10278-025-01677-2}
}
Kostenlos starten →