Meta-learning Slice-to-Volume Reconstruction in Fetal Brain MRI using Implicit Neural Representations

TL;DR

This paper introduces a self-supervised meta-learning approach using implicit neural representations for fast, accurate fetal brain MRI slice-to-volume reconstruction, effectively handling severe motion and artifacts.

Contribution

It presents a novel implicit neural representation-based SVR method with meta-learning for improved accuracy and speed in fetal brain MRI reconstruction under challenging conditions.

Findings

Outperforms state-of-the-art methods in reconstruction quality.

Reduces reconstruction time by up to 50%.

Effective in cases of severe motion and artifacts.

Abstract

High-resolution slice-to-volume reconstruction (SVR) from multiple motion-corrupted low-resolution 2D slices constitutes a critical step in image-based diagnostics of moving subjects, such as fetal brain Magnetic Resonance Imaging (MRI). Existing solutions struggle with image artifacts and severe subject motion or require slice pre-alignment to achieve satisfying reconstruction performance. We propose a novel SVR method to enable fast and accurate MRI reconstruction even in cases of severe image and motion corruption. Our approach performs motion correction, outlier handling, and super-resolution reconstruction with all operations being entirely based on implicit neural representations. The model can be initialized with task-specific priors through fully self-supervised meta-learning on either simulated or real-world data. In extensive experiments including over 480 reconstructions of simulated and clinical MRI brain data from different centers, we prove the utility of our method in cases of severe subject motion and image artifacts. Our results demonstrate improvements in reconstruction quality, especially in the presence of severe motion, compared to state-of-the-art methods, and up to 50% reduction in reconstruction time.