Unsupervised Domain Adaptation with SAM-RefiSeR for Enhanced Brain Tumor Segmentation

2025-12-15

IEEE International Conference on Bioinformatics and Biomedicine

AI Summary

This work addresses the performance degradation in unsupervised domain adaptation for brain tumor segmentation caused by cross-domain distribution shifts. To this end, we propose SAM-RefiSeR, a novel framework that, for the first time, integrates the Segment Anything Model (SAM) into unsupervised domain adaptation. Our approach synergistically combines self-supervised learning, domain adversarial training, and an iterative pseudo-label refinement strategy. Central to this framework is the RefiSeR module, which progressively refines segmentation outputs while promoting domain-invariant feature learning. Extensive experiments across multiple cross-domain brain tumor datasets demonstrate that SAM-RefiSeR significantly outperforms existing methods, achieving superior segmentation accuracy and robustness without requiring any annotations in the target domain.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Robust brain-tumor segmentation in MRI must withstand domain shifts from heterogeneous scanners and protocols. Unsupervised domain adaptation (UDA) can exploit plentiful unlabeled data, yet many approaches erode boundaries, suppress tumor cues, or amplify errors from noisy pseudo-labels. Generalpurpose models like SAM also struggle on MRI due to the domain gap and a lack of morphology-aware consistency. We propose SAM-RefiSeR, a two-phase UDA framework that integrates SAM for reliable, annotation-efficient segmentation. Phase I reduces source-target discrepancy via Fourier-based frequency adaptation and adversarial feature alignment, aligning appearance and representations while preserving anatomy. Phase II adopts a student-teacher scheme in which SAM first refines pseudo-labels, then gates them with confidence- and morphology-aware criteria to suppress unreliable masks and curb error propagation. Across diverse cross-modality settings, SAM-RefiSeR consistently surpasses strong UDA baselines, particularly under severe shifts. By improving boundary fidelity and robustness without additional labels, SAM-RefiSeR brings brain-tumor segmentation closer to practical, generalizable clinical deployment.

Problem

• Unsupervised Domain Adaptation
• Brain Tumor Segmentation
• Domain Shift
• Medical Image Analysis

Innovation

• Unsupervised Domain Adaptation
• Brain Tumor Segmentation
• SAM
• Self-training
• Domain Generalization