EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Lightweight Container Orchestration for Reproducible AI and Deep Learning Segmentation of Coronary Arteries and the Aorta in Coronary CT Angiography

Michal Iwanski, Piotr Regulski iD, Piotr Wendykier

Diagnostics · 15.07.2026 · 16 (14) · 2214

DOI: 10.3390/diagnostics16142214 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Diagnostics, online erschienen am 15.07.2026. Verfasst von Michal Iwanski und 2 weiteren Autor:innen. Beteiligte Einrichtung: Digital Imaging and Virtual Reality Laboratory, Department of Dental and Maxillofacial Radiology, Medical University of Warsaw, 02-097 Warsaw, Poland. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Centre, National Science Centre, Poland.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Deep learning segmentation of coronary CT angiography (CCTA) can support visualization, quantitative analysis, and patient-specific research workflows, but local deployment is often limited by the GPU configuration, dependency drift, heterogeneous operating systems, and limited DevOps resources.

Objective

This study aimed to develop and evaluate a cross-platform orchestrator for the reproducible execution of containerized cardiovascular segmentation models without the need for Kubernetes. The segmentation models were used as representative demonstration workloads. Materials and Methods: A lightweight container orchestrator was developed using Podman and Podman Desktop Machine. The system provides a standardized REST API, asynchronous job execution, parallel and cascaded inference modes, persistent logging, and an external evaluation module. Two containerized nnU-Net v2 services were implemented for coronary artery and aortic segmentation from CCTA. Models were trained on the ImageCAS data and evaluated on an independent external cohort of 200 CCTA examinations. The performance was assessed using the Dice similarity coefficient (DSC) and intersection-over-union (IoU). System latency, throughput, and resource utilization were also measured.

Results

The mean end-to-end latency on Linux was 52.3 ± 7.1 s with GPU acceleration and 74.1 ± 8.3 s in CPU fallback mode. Parallel execution increased throughput from 44.4 to 62.1 cases/hour, with the expected latency increase due to resource contention. As workload validation, the coronary and aortic nnU-Net services achieved DSC values of 0.93 and 0.95, respectively.

Conclusions

The proposed orchestrator enables reproducible, standardized, portable deployment of containerized CCTA segmentation models in on-premises research environments, reducing operational barriers while supporting visualization, validation, and downstream applications.

Schlagwörter

Stichwörter der Autor:innen

PodmanVisNowcontainer orchestrationcoronary CT angiographysegmentation

Autor:innen und Institutionen

  • Digital Imaging and Virtual Reality Laboratory, Department of Dental and Maxillofacial Radiology, Medical University of Warsaw, 02-097 Warsaw, Poland.

ORCID-Profile: Piotr Regulski

Förderung

  • National Science Centre
  • National Science Centre, Poland

Zitieren

APA

Iwanski, M., Regulski, P., & Wendykier, P. (2026). Lightweight Container Orchestration for Reproducible AI and Deep Learning Segmentation of Coronary Arteries and the Aorta in Coronary CT Angiography. Diagnostics, 16(14), 2214. https://doi.org/10.3390/diagnostics16142214

Vancouver

Iwanski M, Regulski P, Wendykier P. Lightweight Container Orchestration for Reproducible AI and Deep Learning Segmentation of Coronary Arteries and the Aorta in Coronary CT Angiography. Diagnostics. 2026;16(14):2214. doi:10.3390/diagnostics16142214

BibTeX
@article{Iwanski2026,
  author = {Iwanski, Michal and Regulski, Piotr and Wendykier, Piotr},
  title = {Lightweight Container Orchestration for Reproducible AI and Deep Learning Segmentation of Coronary Arteries and the Aorta in Coronary CT Angiography},
  journal = {Diagnostics},
  year = {2026},
  volume = {16},
  number = {14},
  pages = {2214},
  doi = {10.3390/diagnostics16142214}
}
Kostenlos starten →