IHF-Harmony: Multi-Modality Magnetic Resonance Images Harmonization using Invertible Hierarchy Flow Model

2026-02-24

AI Summary

This work addresses the limited cross-modal scalability and reliance on paired data in retrospective multi-modal MRI standardization by proposing a unified framework based on Invertible Hierarchical Flows (IHF), which achieves high-fidelity, anatomy-preserving image normalization using only unpaired data. The method introduces Artifact-Aware Normalization (AAN) and an anatomy-artifact consistency loss to establish a bijective invertible mapping, ensuring distortion-free reconstruction. Experimental results demonstrate that the proposed approach significantly outperforms existing methods across multiple MRI modalities, achieving superior anatomical fidelity and enhanced performance in downstream tasks. This provides a robust and scalable solution for large-scale, multi-center neuroimaging studies.

Technology Category

• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Retrospective MRI harmonization is limited by poor scalability across modalities and reliance on traveling subject datasets. To address these challenges, we introduce IHF-Harmony, a unified invertible hierarchy flow framework for multi-modality harmonization using unpaired data. By decomposing the translation process into reversible feature transformations, IHF-Harmony guarantees bijective mapping and lossless reconstruction to prevent anatomical distortion. Specifically, an invertible hierarchy flow (IHF) performs hierarchical subtractive coupling to progressively remove artefact-related features, while an artefact-aware normalization (AAN) employs anatomy-fixed feature modulation to accurately transfer target characteristics. Combined with anatomy and artefact consistency loss objectives, IHF-Harmony achieves high-fidelity harmonization that retains source anatomy. Experiments across multiple MRI modalities demonstrate that IHF-Harmony outperforms existing methods in both anatomical fidelity and downstream task performance, facilitating robust harmonization for large-scale multi-site imaging studies. Code will be released upon acceptance.

Problem

• MRI harmonization
• multi-modality
• scalability
• traveling subject datasets
• anatomical fidelity

Innovation

• Invertible Hierarchy Flow
• Multi-modality Harmonization
• Unpaired MRI Data
• Artefact-aware Normalization
• Anatomical Fidelity