PRISM: Privacy-preserving Inter-Site MRI Harmonization via Disentangled Representation Learning

TL;DR

PRISM is a deep learning framework that harmonizes multi-site MRI data while preserving privacy, using disentangled representations to improve clinical AI/ML tasks without sharing raw data.

Contribution

PRISM introduces a novel privacy-preserving, flexible MRI harmonization method using disentangled representation learning that works without paired data or retraining for new sites.

Findings

Effective in improving brain tissue segmentation accuracy

Successfully harmonizes data across multiple sites

Addresses privacy and distribution shift challenges

Abstract

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