Domain-invariant feature learning in brain MR imaging for content-based image retrieval

2025-01-02

AI Summary

Multi-center brain MR images exhibit significant domain shifts due to heterogeneous acquisition hardware and protocols, severely hindering cross-site pathological feature retrieval. To address this, we propose Style-Encoder Adversarial Domain Adaptation (SE-ADA), the first framework integrating style encoding, adversarial learning, and feature disentanglement for unsupervised domain-invariant representation learning. SE-ADA explicitly decouples domain-specific variations from pathology-relevant semantic features, simultaneously suppressing domain bias and preserving diagnostically critical anatomical and lesion structures within a low-dimensional latent space. Evaluated on eight public datasets across ADNI, OASIS, and PPMI, SE-ADA consistently outperforms existing domain correction methods—achieving more thorough removal of domain information and setting a new state-of-the-art in disease-relevant image retrieval accuracy.

Technology Category

• Machine Learning: Transfer, Domain Adaptation, Multi-Task Learning
• Computer Vision: Adversarial Attacks & Robustness
• Multiagent Systems: Adversarial Agents

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

When conducting large-scale studies that collect brain MR images from multiple facilities, the impact of differences in imaging equipment and protocols at each site cannot be ignored, and this domain gap has become a significant issue in recent years. In this study, we propose a new low-dimensional representation (LDR) acquisition method called style encoder adversarial domain adaptation (SE-ADA) to realize content-based image retrieval (CBIR) of brain MR images. SE-ADA reduces domain differences while preserving pathological features by separating domain-specific information from LDR and minimizing domain differences using adversarial learning. In evaluation experiments comparing SE-ADA with recent domain harmonization methods on eight public brain MR datasets (ADNI1/2/3, OASIS1/2/3/4, PPMI), SE-ADA effectively removed domain information while preserving key aspects of the original brain structure and demonstrated the highest disease search accuracy.

Problem

• MRI inconsistency
• image retrieval
• disease information extraction

Innovation

• SE-ADA
• MRI Image Processing
• Inter-site Variability Reduction