MST-former: multiparty shared representation enabled transformer for secure medical image analysis
7 affiliations
- 1Information Technology Department, College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU)
- 2Saudi Electronic University
- 3College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU)
- 4Department of Information Systems, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University
- 5Department of Computer Science, College of Computer Engineering and Sciences, Prince Sattam Bin Abdulaziz University
- 6Department of Information System, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University
- 7Department of Intelligent Systems, KTH Royal Institute of Technology
Abstract
Privacy-preserving collaborative medical image analysis across multiple healthcare institutions remains challenging due to data heterogeneity, patient privacy constraints, and incomplete cross-institutional record alignment. To address these limitations, this paper proposes MST-Former, a multiparty shared transformer framework that enables secure embedding fusion without sharing raw medical images. The framework combines a deep reinforced autoencoder (DRA) for local representation learning with adaptive positional encoding, dynamic attention masking, and transformer-based embedding aggregation to facilitate robust cross-institutional knowledge integration. In addition, a contrastive learning strategy is employed to enhance representation consistency across heterogeneous imaging sources. Extensive experiments conducted on multiple benchmark medical imaging datasets demonstrate that MST-Former consistently outperforms existing methods in segmentation and prediction performance while preserving data confidentiality. Across multiple medical image segmentation datasets, MST-Former consistently achieved strong performance, with mDice scores ranging from 92.73 to 94.95% and mIoU scores ranging from 87.31 to 92.65%, demonstrating its effectiveness and generalization capability. These results highlight the effectiveness of MST-Former as a scalable and privacy-preserving solution for collaborative medical image analysis in distributed healthcare environments.
Related
- MedFuse: dual-stream fusion of convolutional and vision transformer-based features for enhanced medical image classification
- Artificial Intelligence-Enabled Medical Diagnosis in the Internet of Medical Things: An End-to-End Survey of Connected Sensing, Distributed Intelligence, Clinical Applications, and Validation.
- Mapping the research landscape of UAV- and eVTOL-enabled emergency medical services: a bibliometric analysis, scoping review, and policy tool assessment
- Growth, Specialty Distribution, and Regulatory Pathways of Artificial Intelligence-Enabled Medical Devices Authorized in the United States From 1995 to 2026: A Cross-Sectional Analysis
- Digital Health-Enabled Prehospital Notification for Acute Stroke Using the Brain Saver Mobile App in Emergency Medical Transport in South Korea: Pilot Quasi-Experimental Study.
BibTeX
@article{khan2026mstformer,
title = {{MST-former: multiparty shared representation enabled transformer for secure medical image analysis}},
author = {Shakir Khan and Thamer Alshammari and Fahad Omar Alomary and Hadeel Alsolai and Sultan Ahmad and Bayan Ibrahimm Alabduallah and Fatimah Alhayan and Saqib Qamar},
journal = {Scientific Reports},
year = {2026},
month = sep,
doi = {10.1038/s41598-026-72504-z},
url = {https://doi.org/10.1038/s41598-026-72504-z},
note = {CC BY},
}
RIS
TY - JOUR
TI - MST-former: multiparty shared representation enabled transformer for secure medical image analysis
AU - Shakir Khan
AU - Thamer Alshammari
AU - Fahad Omar Alomary
AU - Hadeel Alsolai
AU - Sultan Ahmad
AU - Bayan Ibrahimm Alabduallah
AU - Fatimah Alhayan
AU - Saqib Qamar
PY - 2026
DA - 2026/09/01
JO - Scientific Reports
DO - 10.1038/s41598-026-72504-z
UR - https://doi.org/10.1038/s41598-026-72504-z
AB - Privacy-preserving collaborative medical image analysis across multiple healthcare institutions remains challenging due to data heterogeneity, patient privacy constraints, and incomplete cross-institutional record alignment. To address these limitations, this paper proposes MST-Former, a multiparty shared transformer framework that enables secure embedding fusion without sharing raw medical images. The framework combines a deep reinforced autoencoder (DRA) for local representation learning with adaptive positional encoding, dynamic attention masking, and transformer-based embedding aggregation to facilitate robust cross-institutional knowledge integration. In addition, a contrastive learning strategy is employed to enhance representation consistency across heterogeneous imaging sources. Extensive experiments conducted on multiple benchmark medical imaging datasets demonstrate that MST-Former consistently outperforms existing methods in segmentation and prediction performance while preserving data confidentiality. Across multiple medical image segmentation datasets, MST-Former consistently achieved strong performance, with mDice scores ranging from 92.73 to 94.95% and mIoU scores ranging from 87.31 to 92.65%, demonstrating its effectiveness and generalization capability. These results highlight the effectiveness of MST-Former as a scalable and privacy-preserving solution for collaborative medical image analysis in distributed healthcare environments.
SN - 2045-2322
ER -