Fourier Disentangled Multimodal Prior Knowledge Fusion for Red Nucleus Segmentation in Brain MRI

TL;DR

This paper introduces a novel multimodal MRI segmentation model that disentangles high-level anatomical features from contrast information, improving red nucleus segmentation especially with limited training data.

Contribution

The proposed model effectively integrates prior knowledge from multiple MRI contrasts and handles missing modalities, outperforming baseline models in small data scenarios.

Findings

Outperforms baseline UNet in small training data settings

Successfully integrates multiple MRI contrasts for improved segmentation

Handles missing modalities effectively

Abstract

Early and accurate diagnosis of parkinsonian syndromes is critical to provide appropriate care to patients and for inclusion in therapeutic trials. The red nucleus is a structure of the midbrain that plays an important role in these disorders. It can be visualized using iron-sensitive magnetic resonance imaging (MRI) sequences. Different iron-sensitive contrasts can be produced with MRI. Combining such multimodal data has the potential to improve segmentation of the red nucleus. Current multimodal segmentation algorithms are computationally consuming, cannot deal with missing modalities and need annotations for all modalities. In this paper, we propose a new model that integrates prior knowledge from different contrasts for red nucleus segmentation. The method consists of three main stages. First, it disentangles the image into high-level information representing the brain structure, and low-frequency information representing the contrast. The high-frequency information is then fed into a network to learn anatomical features, while the list of multimodal low-frequency information is processed by another module. Finally, feature fusion is performed to complete the segmentation task. The proposed method was used with several iron-sensitive contrasts (iMag, QSM, R2*, SWI). Experiments demonstrate that our proposed model substantially outperforms a baseline UNet model when the training set size is very small.