{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T11:38:22Z","timestamp":1785411502646,"version":"3.56.0"},"reference-count":30,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T00:00:00Z","timestamp":1784073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004281","name":"National Science Centre, Poland","doi-asserted-by":"publisher","award":["2021\/43\/D\/NZ5\/02012"],"award-info":[{"award-number":["2021\/43\/D\/NZ5\/02012"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"publisher"}]},{"award":["2021\/43\/D\/NZ5\/02012"],"award-info":[{"award-number":["2021\/43\/D\/NZ5\/02012"]}],"id":[{"id":"https:\/\/ror.org\/03ha2q922","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>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 \u00b1 7.1 s with GPU acceleration and 74.1 \u00b1 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.<\/jats:p>","DOI":"10.3390\/diagnostics16142214","type":"journal-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T01:05:07Z","timestamp":1784163907000},"page":"2214","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Lightweight Container Orchestration for Reproducible AI and Deep Learning Segmentation of Coronary Arteries and the Aorta in Coronary CT Angiography"],"prefix":"10.3390","volume":"16","author":[{"given":"Michal","family":"Iwanski","sequence":"first","affiliation":[{"name":"Digital Imaging and Virtual Reality Laboratory, Department of Dental and Maxillofacial Radiology, Medical University of Warsaw, 02-097 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3692-3582","authenticated-orcid":false,"given":"Piotr","family":"Regulski","sequence":"additional","affiliation":[{"name":"Digital Imaging and Virtual Reality Laboratory, Department of Dental and Maxillofacial Radiology, Medical University of Warsaw, 02-097 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Piotr","family":"Wendykier","sequence":"additional","affiliation":[{"name":"Digital Imaging and Virtual Reality Laboratory, Department of Dental and Maxillofacial Radiology, Medical University of Warsaw, 02-097 Warsaw, Poland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,15]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"169","DOI":"10.2991\/jegh.k.201217.001","article-title":"Epidemiology and the magnitude of coronary artery disease and acute coronary syndrome: A narrative review","volume":"11","author":"Ralapanawa","year":"2021","journal-title":"J. Epidemiol. Glob. Health"},{"key":"ref_2","first-page":"e88638","article-title":"An unsupervised learning algorithm for the automatic classification of coronary artery lesions","volume":"17","author":"Szopinska","year":"2025","journal-title":"Cureus"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"779","DOI":"10.33963\/v.phj.106383","article-title":"Cardiac computed tomography for planning and guidance of coronary revascularization: An expert position of the Association of Cardiovascular Interventions of the Polish Cardiac Society","volume":"83","author":"Opolski","year":"2025","journal-title":"Kardiol. Pol."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Wang, Q., Xu, L., Wang, L., Yang, X., Sun, Y., Yang, B., and Greenwald, S.E. (2023). Automatic coronary artery segmentation of CCTA images using UNet with a local contextual transformer. Front. Physiol., 14.","DOI":"10.3389\/fphys.2023.1138257"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1809","DOI":"10.1007\/s10554-017-1169-0","article-title":"Automatic identification of coronary tree anatomy in coronary computed tomography angiography","volume":"33","author":"Cao","year":"2017","journal-title":"Int. J. Cardiovasc. Imaging"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"105908","DOI":"10.1016\/j.cmpb.2020.105908","article-title":"Automated coronary artery tree segmentation in coronary CTA using a multiobjective clustering and toroidal model-guided tracking method","volume":"199","author":"Du","year":"2021","journal-title":"Comput. Methods Programs Biomed."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"13724","DOI":"10.1038\/s41598-020-69920-0","article-title":"Variability and reproducibility in deep learning for medical image segmentation","volume":"10","author":"Renard","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"102049","DOI":"10.1016\/j.compmedimag.2022.102049","article-title":"Automated segmentation of normal and diseased coronary arteries\u2014The ASOCA challenge","volume":"97","author":"Gharleghi","year":"2022","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e55897","DOI":"10.2196\/55897","article-title":"Implementation of machine learning applications in health care organizations: Systematic review of empirical studies","volume":"26","author":"Preti","year":"2024","journal-title":"J. Med. Internet Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"100631","DOI":"10.1016\/j.smhl.2025.100631","article-title":"Integrating AI into healthcare systems: A multivocal literature review","volume":"39","author":"Mallardi","year":"2026","journal-title":"Smart Health"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"102287","DOI":"10.1016\/j.compmedimag.2023.102287","article-title":"ImageCAS: A large-scale dataset and benchmark for coronary artery segmentation based on computed tomography angiography images","volume":"109","author":"Zeng","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102503","DOI":"10.1016\/j.softx.2025.102503","article-title":"VisNow: An open-source Java-based modular dataflow visualisation platform","volume":"33","author":"Nowinski","year":"2026","journal-title":"SoftwareX"},{"key":"ref_14","first-page":"229","article-title":"VisNow-Medical\u2014A visual analysis platform for medical data processing","volume":"Volume 308","author":"Chen","year":"2022","journal-title":"Innovation in Medicine and Healthcare"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Korontanis, I., Zacharia, A., Makris, A., Pateraki, M., and Tserpes, K. (2025). Streamlining ML Training in Kubernetes: An MLOps architecture with Kubeflow. Proceedings of the 15th International Conference on the Internet of Things (IoT 2025), Association for Computing Machinery.","DOI":"10.1145\/3770501.3771304"},{"key":"ref_16","unstructured":"(2026, February 22). Kubeflow. Available online: https:\/\/www.kubeflow.org\/."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1145\/2723872.2723882","article-title":"An introduction to Docker for reproducible research","volume":"49","author":"Boettiger","year":"2015","journal-title":"ACM Oper. Syst. Rev."},{"key":"ref_18","first-page":"39","article-title":"Accelerating the Machine Learning Lifecycle with MLflow","volume":"41","author":"Zaharia","year":"2018","journal-title":"IEEE Data Eng. Bull."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Chen, A., Chow, A., Davidson, A., Dcunha, A., Ghodsi, A., Hong, S.A., Konwinski, A., Mewald, C., Murching, S., and Nykodym, T. (2020, January 14). Developments in MLflow: A System to Accelerate the Machine Learning Lifecycle. Proceedings of the 4th Workshop on Data Management for End-to-End Machine Learning, DEEM 2020\u2014In Conjunction with the 2020 ACM SIGMOD\/PODS Conference, Portland, OR, USA.","DOI":"10.1145\/3399579.3399867"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"5893","DOI":"10.1007\/s00261-025-05014-7","article-title":"Research-based clinical deployment of artificial intelligence algorithm for prostate MRI","volume":"50","author":"Harmon","year":"2025","journal-title":"Abdom. Radiol."},{"key":"ref_21","unstructured":"Ak\u00fcnal, \u00dc., Bujotzek, M., Denner, S., Hamm, B., Kades, K., Schader, P., Scherer, J., Nolden, M., Neher, P., and Floca, R. (2025). Kaapana: A comprehensive open-source platform for integrating AI in medical imaging research environments. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"102289","DOI":"10.1016\/j.compmedimag.2023.102289","article-title":"CardioVision: A fully automated deep learning package for medical image segmentation and reconstruction generating digital twins for patients with aortic stenosis","volume":"109","author":"Rouhollahi","year":"2023","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Pepe, A., Melito, G.M., and Egger, J. (2023). Segmentation of the Aorta: Towards the Automatic Segmentation, Modeling, and Meshing of the Aortic Vessel Tree from Multicenter Acquisition, Springer.","DOI":"10.1007\/978-3-031-53241-2"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"e230024","DOI":"10.1148\/ryai.230024","article-title":"TotalSegmentator: Robust segmentation of 104 anatomic structures in CT images","volume":"5","author":"Wasserthal","year":"2023","journal-title":"Radiol. Artif. Intell."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1038\/s41746-025-01434-3","article-title":"Real world federated learning with a knowledge distilled transformer for cardiac CT imaging","volume":"8","author":"Garthe","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kurtzer, G.M., Sochat, V., and Bauer, M.W. (2017). Singularity: Scientific containers for mobility of compute. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0177459"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"1900004","DOI":"10.1002\/bies.201900004","article-title":"Biomedical image processing with containers and deep learning: An automated analysis pipeline: Data architecture, artificial intelligence, automated processing, containerization, and clusters orchestration ease the transition from data acquisition to inspection","volume":"41","author":"Evans","year":"2019","journal-title":"BioEssays"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Taha, A.A., and Hanbury, A. (2015). Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool. BMC Med. Imaging, 15.","DOI":"10.1186\/s12880-015-0068-x"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"111965","DOI":"10.1016\/j.jss.2024.111965","article-title":"A qualitative and quantitative analysis of container engines","volume":"210","author":"Baresi","year":"2024","journal-title":"J. Syst. Softw."},{"key":"ref_30","unstructured":"(2026, February 28). Open Container Initiative. Available online: https:\/\/opencontainers.org\/."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/14\/2214\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T01:17:19Z","timestamp":1784164639000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/14\/2214"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,15]]},"references-count":30,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["diagnostics16142214"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16142214","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,15]]}}}