Principled Feature Disentanglement for High-Fidelity Unified Brain MRI Synthesis

TL;DR

This paper introduces HF-GAN, a novel framework for synthesizing missing MRI sequences using principled feature disentanglement, improving accuracy and clinical utility in brain MRI analysis.

Contribution

The work presents a new unified GAN architecture with feature disentanglement and dynamic fusion for high-fidelity multisequence MRI synthesis.

Findings

Achieves state-of-the-art synthesis performance on public brain MRI datasets.

Outperforms existing 3D volumetric models with a 2D slice-based approach.

Enhances downstream brain tumor segmentation accuracy.

Abstract

Multisequence Magnetic Resonance Imaging (MRI) provides a more reliable diagnosis in clinical applications through complementary information across sequences. However, in practice, the absence of certain MR sequences is a common problem that can lead to inconsistent analysis results. In this work, we propose a novel unified framework for synthesizing multisequence MR images, called hybrid-fusion GAN (HF-GAN). The fundamental mechanism of this work is principled feature disentanglement, which aligns the design of the architecture with the complexity of the features. A powerful many-to-one stream is constructed for the extraction of complex complementary features, while utilizing parallel, one-to-one streams to process modality-specific information. These disentangled features are dynamically integrated into a common latent space by a channel attention-based fusion module (CAFF) and then transformed via a modality infuser to generate the target sequence. We validated our framework on public datasets of both healthy and pathological brain MRI. Quantitative and qualitative results show that HF-GAN achieves state-of-the-art performance, with our 2D slice-based framework notably outperforming a leading 3D volumetric model. Furthermore, the utilization of HF-GAN for data imputation substantially improves the performance of the downstream brain tumor segmentation task, demonstrating its clinical relevance.