Principled Feature Disentanglement for High-Fidelity Unified Brain MRI Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cho, Jihoon, Woo, Jonghye, Park, Jinah
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911221541765120
author Cho, Jihoon
Woo, Jonghye
Park, Jinah
author_facet Cho, Jihoon
Woo, Jonghye
Park, Jinah
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14954
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Principled Feature Disentanglement for High-Fidelity Unified Brain MRI Synthesis
Cho, Jihoon
Woo, Jonghye
Park, Jinah
Image and Video Processing
Computer Vision and Pattern Recognition
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.
title Principled Feature Disentanglement for High-Fidelity Unified Brain MRI Synthesis
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.14954