An Intelligent Federated Learning-Enabled Swin Vision Transformer Model for Automated Fetal Abnormality Monitoring and Diagnosis

DOI

10.2991/978-94-6239-616-6_84How to use a DOI?

Keywords

Fetal Abnormality Detection; Swin Vision Transformer; Federated Learning; Ultrasound Imaging; Privacy Preservation; Deep Learning; Medical Image Analysis; Distributed Intelligence; Clinical Decision Support; Telemedicine

Abstract

Early and accurate detection of fetal abnormalities is vital for maternal and neonatal health, yet centralized deep learning models face challenges from privacy concerns and data heterogeneity. This study introduces an Intelligent Federated Learning-Enabled Swin Vision Transformer (Fed-SwinViT) model for automated fetal abnormality detection using ultrasound imaging. The framework combines the Swin Vision Transformer’s hierarchical feature extraction with Federated Learning’s distributed training, ensuring data privacy and collaboration across institutions. SwinViT captures multi-scale spatial features for precise abnormality localization, while federated aggregation enhances generalization and global model performance. Experiments on benchmark datasets show that Fed-SwinViT outperforms existing CNN and Transformer models in accuracy, sensitivity, and robustness, offering a secure and scalable solution for fetal health monitoring in telemedicine.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - E. Rajkumar
AU  - V. Geetha
AU  - J. Jasmine Margret
PY  - 2026
DA  - 2026/03/31
TI  - An Intelligent Federated Learning-Enabled Swin Vision Transformer Model for Automated Fetal Abnormality Monitoring and Diagnosis
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1152
EP  - 1162
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_84
DO  - 10.2991/978-94-6239-616-6_84
ID  - Rajkumar2026
ER  -