PRISM: Privacy-preserving Inter-Site MRI Harmonization via Disentangled Representation Learning
This addresses data privacy and distribution shift issues in medical AI/ML for multi-site MRI analysis, though it is incremental as it builds on existing disentangled representation learning methods.
The paper tackles the problem of site-specific variations in multi-site MRI studies, which compromise clinical AI/ML tasks, by introducing PRISM, a privacy-preserving framework that harmonizes structural brain MRI across sites without requiring paired data or retraining, and demonstrates its effectiveness in downstream tasks like brain tissue segmentation.
Multi-site MRI studies often suffer from site-specific variations arising from differences in methodology, hardware, and acquisition protocols, thereby compromising accuracy and reliability in clinical AI/ML tasks. We present PRISM (Privacy-preserving Inter-Site MRI Harmonization), a novel Deep Learning framework for harmonizing structural brain MRI across multiple sites while preserving data privacy. PRISM employs a dual-branch autoencoder with contrastive learning and variational inference to disentangle anatomical features from style and site-specific variations, enabling unpaired image translation without traveling subjects or multiple MRI modalities. Our modular design allows harmonization to any target site and seamless integration of new sites without the need for retraining or fine-tuning. Using multi-site structural MRI data, we demonstrate PRISM's effectiveness in downstream tasks such as brain tissue segmentation and validate its harmonization performance through multiple experiments. Our framework addresses key challenges in medical AI/ML, including data privacy, distribution shifts, model generalizability and interpretability. Code is available at https://github.com/saranggalada/PRISM