Self-Supervised Slice-to-Volume Reconstruction with Gaussian Representations for Fetal MRI

TL;DR

GaussianSVR is a self-supervised framework that reconstructs high-fidelity 3D fetal MRI volumes from motion-corrupted 2D slices using Gaussian representations and a multi-resolution training strategy.

Contribution

It introduces a self-supervised approach that eliminates the need for ground-truth volumes and improves reconstruction accuracy and efficiency.

Findings

GaussianSVR outperforms baseline methods in fetal MRI reconstruction.

The multi-resolution training strategy enhances both accuracy and efficiency.

Self-supervised training reduces reliance on ground-truth data.

Abstract

Reconstructing 3D fetal MR volumes from motion-corrupted stacks of 2D slices is a crucial and challenging task. Conventional slice-to-volume reconstruction (SVR) methods are time-consuming and require multiple orthogonal stacks for reconstruction. While learning-based SVR approaches have significantly reduced the time required at the inference stage, they heavily rely on ground truth information for training, which is inaccessible in practice. To address these challenges, we propose GaussianSVR, a self-supervised framework for slice-to-volume reconstruction. GaussianSVR represents the target volume using 3D Gaussian representations to achieve high-fidelity reconstruction. It leverages a simulated forward slice acquisition model to enable self-supervised training, alleviating the need for ground-truth volumes. Furthermore, to enhance both accuracy and efficiency, we introduce a multi-resolution training strategy that jointly optimizes Gaussian parameters and spatial transformations across different resolution levels. Experiments show that GaussianSVR outperforms the baseline methods on fetal MR volumetric reconstruction. Code is available at https://github.com/Yinsong0510/GaussianSVR-Self-Supervised-Slice-to-Volume-Reconstruction-with-Gaussian-Representations.