EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A fully automated deep learning approach for coronary artery segmentation and comprehensive characterization

Guido Nannini iD, Simone Saitta iD, Andrea Baggiano iD, Riccardo Maragna iD, Saima Mushtaq, Gianluca Pontone iD, Alberto Redaelli iD

APL Bioengineering · 01.03.2024 · 8 (1)

DOI: 10.1063/5.0181281 ↗

Kurz gefasst

Fachartikel in der Zeitschrift APL Bioengineering, online erschienen am 23.01.2024. Verfasst von Guido Nannini und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electronics Information and Bioengineering, Politecnico di Milano, Milan, Italy. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Coronary computed tomography angiography (CCTA) allows detailed assessment of early markers associated with coronary artery disease (CAD), such as coronary artery calcium (CAC) and tortuosity (CorT). However, their analysis can be time-demanding and biased. We present a fully automated pipeline that performs (i) coronary artery segmentation and (ii) CAC and CorT objective analysis. Our method exploits supervised learning for the segmentation of the lumen, and then, CAC and CorT are automatically quantified. 281 manually annotated CCTA images were used to train a two-stage U-Net-based architecture. The first stage employed a 2.5D U-Net trained on axial, coronal, and sagittal slices for preliminary segmentation, while the second stage utilized a multichannel 3D U-Net for refinement. Then, a geometric post-processing was implemented: vessel centerlines were extracted, and tortuosity score was quantified as the count of branches with three or more bends with change in direction forming an angle >45°. CAC scoring relied on image attenuation. CAC was detected by setting a patient specific threshold, then a region growing algorithm was applied for refinement. The application of the complete pipeline required <5 min per patient. The model trained for coronary segmentation yielded a Dice score of 0.896 and a mean surface distance of 1.027 mm compared to the reference ground truth. Tracts that presented stenosis were correctly segmented. The vessel tortuosity significantly increased locally, moving from proximal, to distal regions (p < 0.001). Calcium volume score exhibited an opposite trend (p < 0.001), with larger plaques in the proximal regions. Volume score was lower in patients with a higher tortuosity score (p < 0.001). Our results suggest a linked negative correlation between tortuosity and calcific plaque formation. We implemented a fast and objective tool, suitable for population studies, that can help clinician in the quantification of CAC and various coronary morphological parameters, which is helpful for CAD risk assessment.

Autor:innen und Institutionen

  • Department of Electronics Information and Bioengineering, Politecnico di Milano, Milan, Italy.
  • Department of Perioperative Cardiology and Cardiovascular Imaging D, Centro Cardiologico Monzino IRCCS, Italy.

ORCID-Profile: Guido Nannini, Simone Saitta, Andrea Baggiano, Riccardo Maragna, Gianluca Pontone, Alberto Redaelli

Zitieren

APA

Nannini, G., Saitta, S., Baggiano, A., Maragna, R., Mushtaq, S., Pontone, G., & Redaelli, A. (2024). A fully automated deep learning approach for coronary artery segmentation and comprehensive characterization. APL Bioengineering, 8(1). https://doi.org/10.1063/5.0181281

Vancouver

Nannini G, Saitta S, Baggiano A, Maragna R, Mushtaq S, Pontone G, et al. A fully automated deep learning approach for coronary artery segmentation and comprehensive characterization. APL Bioengineering. 2024;8(1). doi:10.1063/5.0181281

BibTeX
@article{Nannini2024,
  author = {Nannini, Guido and Saitta, Simone and Baggiano, Andrea and Maragna, Riccardo and Mushtaq, Saima and Pontone, Gianluca and Redaelli, Alberto},
  title = {A fully automated deep learning approach for coronary artery segmentation and comprehensive characterization},
  journal = {APL Bioengineering},
  year = {2024},
  volume = {8},
  number = {1},
  doi = {10.1063/5.0181281}
}
Kostenlos starten →