Automated Fetal Brain Volume Reconstruction from Motion-corrupted Stacks with Deep Learning

Motivation: The fetal brain MRI 3D volume is critical for development assessment. However, the inevitable fetal motion during MRI acquisition makes it challenging to reconstruct a high-quality fetal brain 3D volume from multiple stacks. Goal(s): Herein, we propose a novel deep learning method for automated fetal brain MRI 3D volume reconstruction. Approach: Firstly, a multi-scale feature fusion model is proposed to solve arbitrary motion correction. Secondly, an initial 3D volume is estimated by point spread function. Next, the proposed residual-based model is used to improve the quality of the initial 3D volume. Results: The results demonstrate that the proposed method is effective and efficient. Impact: The proposed end-to-end method based on deep learning can solve arbitrary motion correction of 2D slices and reconstruct high-resolution fetal brain MRI 3D volumes effectively and efficiently.