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

TL;DR

This paper introduces SE-ADA, a novel adversarial domain adaptation method that creates domain-invariant low-dimensional features for brain MRI images, improving content-based image retrieval across diverse datasets.

Contribution

The paper presents SE-ADA, a new method for reducing domain differences in brain MRI images while preserving pathological features, enhancing cross-site image retrieval accuracy.

Findings

SE-ADA effectively removes domain information from MRI features.

SE-ADA achieves the highest disease search accuracy among compared methods.

SE-ADA preserves key brain structures while reducing domain gaps.

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.