TwinSegNet: A Digital Twin-Enabled Federated Learning Framework for Brain Tumor Analysis

TL;DR

TwinSegNet addresses privacy and heterogeneity in brain tumor segmentation by fusing a privacy-preserving federated learning framework with a hybrid CNN-ViT (ViT-UNet) architecture and client-specific digital twins. The approach enables scalable multi-institutional training without sharing raw data, while personalizing models to each hospital through lightweight DT fine-tuning. Evaluations across nine heterogeneous MRI datasets show strong segmentation performance (Dice up to ~0.90) and high sensitivity/specificity, with measurable gains from DT personalization over a global model. Compared with centralized baselines, TwinSegNet preserves privacy without sacrificing accuracy, highlighting its practicality for real-world clinical deployment.

Abstract

Brain tumor segmentation is critical in diagnosis and treatment planning for the disease. Yet, current deep learning methods rely on centralized data collection, which raises privacy concerns and limits generalization across diverse institutions. In this paper, we propose TwinSegNet, which is a privacy-preserving federated learning framework that integrates a hybrid ViT-UNet model with personalized digital twins for accurate and real-time brain tumor segmentation. Our architecture combines convolutional encoders with Vision Transformer bottlenecks to capture local and global context. Each institution fine-tunes the global model of private data to form its digital twin. Evaluated on nine heterogeneous MRI datasets, including BraTS 2019-2021 and custom tumor collections, TwinSegNet achieves high Dice scores (up to 0.90%) and sensitivity/specificity exceeding 90%, demonstrating robustness across non-independent and identically distributed (IID) client distributions. Comparative results against centralized models such as TumorVisNet highlight TwinSegNet's effectiveness in preserving privacy without sacrificing performance. Our approach enables scalable, personalized segmentation for multi-institutional clinical settings while adhering to strict data confidentiality requirements.

Figures (9)

• Figure 1: Workflow of TwinSegNet.
• Figure 2: Hybrid Learning Architecture of TwinSegNet.
• Figure 3: Sensitivity and specificity comparison.
• Figure 4: Dice Score per Class Across Nine Hospitals.
• Figure 5: IoU Score per Class Across Nine Hospitals.