EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Simulating Federated Learning to Enable Multi‐Hospital Collaboration for Lumbopelvic Alignment Estimation

Andrea Cina iD, Miklovana Tuci, Ferran Pellisé iD, Caglar Yilgor, Ahmet Alanay, Javier Pizones, Frank Kleinstück, Ibrahim Obeid, Yann Philippe Charles, Sarah Richner-Wunderlin, Fabio Galbusera iD, Catherine R Jutzeler und 1 weitere

JOR SPINE · 2025-12 · 8 (4)

DOI: 10.1002/jsp2.70120 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JOR SPINE, online erschienen am 16.10.2025. Verfasst von Andrea Cina und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Health Sciences and Technology (D-HEST), ETH Zurich Universitätstrasse 2 Zürich Switzerland. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Accurate computation of radiological parameters related to spinal alignment is clinically crucial for diagnosing and managing conditions, such as adolescent idiopathic scoliosis and adult spinal deformities. Key parameters, including sacral slope, pelvic tilt, pelvic incidence, and lumbar lordosis, are required to assess lumbosacral alignment. Artificial Intelligence (AI) has demonstrated strong potential in automating these assessments, reducing clinician workload and improving consistency. However, AI models require large, diverse, high‐quality datasets to perform reliably across different clinical settings. Privacy concerns and data ownership issues often hinder data sharing, limiting the creation of centralized datasets.

Methods

In this study, we demonstrate that federated learning (FL) enables the training of deep learning models across four hospitals without compromising patient privacy. In particular, we compared FL against a centralized approach, where data from all the hospitals are pooled together and a model is trained on them, and a local approach consisting of training individual models exclusively on data from each respective hospital, resulting in distinct hospital‐specific models.

Results

FL achieved performance comparable to centralized training (errors ~5°), where data is pooled, and consistently outperformed models trained on data from individual hospitals, both in internal (~8°) and external (~10°) testing.

Conclusion

This work highlights FL as a viable solution for collaborative AI development in spinal imaging, facilitating the use of diverse, multi‐institutional data while circumventing privacy barriers and complex data‐sharing agreements. Additionally, FL demonstrates particular benefits for smaller hospitals, enabling them to achieve superior model performance by effectively leveraging data from hospitals with larger datasets.

Schlagwörter

Stichwörter der Autor:innen

automatic assessmentdeep learningfederated learningprivacyspine parameters

Autor:innen und Institutionen

  • Department of Health Sciences and Technology (D-HEST), ETH Zurich Universitätstrasse 2 Zürich Switzerland.
  • Schulthess Clinic, Department of Teaching, Research and Development Zürich Switzerland.
  • Swiss Institute of Bioinformatics (SIB) Lausanne Switzerland.
  • Spinal Cord Injury Center University Hospital Balgrist, University of Zürich Zürich Switzerland.
  • Spine Research Unit Vall d'Hebron Research Institute Barcelona Spain.
  • Spine Surgery Unit Vall d'Hebron University Hospital Barcelona Spain.

ORCID-Profile: Andrea Cina, Ferran Pellisé, Fabio Galbusera

Förderung

  • Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

Zitieren

APA

Cina, A., Tuci, M., Pellisé, F., Yilgor, C., Alanay, A., Pizones, J., Kleinstück, F., Obeid, I., Charles, Y. P., Richner-Wunderlin, S., Galbusera, F., Jutzeler, C. R., & European Spine Study Group (2025). Simulating Federated Learning to Enable Multi‐Hospital Collaboration for Lumbopelvic Alignment Estimation. JOR SPINE, 8(4). https://doi.org/10.1002/jsp2.70120

Vancouver

Cina A, Tuci M, Pellisé F, Yilgor C, Alanay A, Pizones J, et al. Simulating Federated Learning to Enable Multi‐Hospital Collaboration for Lumbopelvic Alignment Estimation. JOR SPINE. 2025;8(4). doi:10.1002/jsp2.70120

BibTeX
@article{Cina2025,
  author = {Cina, Andrea and Tuci, Miklovana and Pellisé, Ferran and Yilgor, Caglar and Alanay, Ahmet and Pizones, Javier and Kleinstück, Frank and Obeid, Ibrahim and Charles, Yann Philippe and Richner-Wunderlin, Sarah and Galbusera, Fabio and Jutzeler, Catherine R and European Spine Study Group, European Spine Study Group},
  title = {Simulating Federated Learning to Enable Multi‐Hospital Collaboration for Lumbopelvic Alignment Estimation},
  journal = {JOR SPINE},
  year = {2025},
  volume = {8},
  number = {4},
  doi = {10.1002/jsp2.70120}
}
Kostenlos starten →