Domain-invariant feature learning in brain MR imaging for content-based image retrieval
This addresses domain invariance for brain MR imaging in large-scale studies, but it is incremental as it builds on existing domain adaptation techniques.
The study tackled the problem of domain gaps in brain MR images from multiple facilities by proposing a style encoder adversarial domain adaptation (SE-ADA) method for content-based image retrieval, which achieved the highest disease search accuracy in evaluations on eight public datasets.
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.