SUFFICIENT: A scan-specific unsupervised deep learning framework for high-resolution 3D isotropic fetal brain MRI reconstruction

TL;DR

SUFFICIENT is an unsupervised deep learning framework that reconstructs high-resolution 3D fetal brain MRI from motion-corrupted 2D slices without requiring large external datasets, outperforming existing methods.

Contribution

It introduces a novel unsupervised iterative SVR-SRR framework combining a CNN-based registration and a deep image prior for high-quality fetal brain MRI reconstruction.

Findings

Outperforms state-of-the-art fetal brain reconstruction methods.

Effective on both simulated and clinical motion-corrupted data.

Does not require large external training datasets.

Abstract

High-quality 3D fetal brain MRI reconstruction from motion-corrupted 2D slices is crucial for clinical diagnosis. Reliable slice-to-volume registration (SVR)-based motion correction and super-resolution reconstruction (SRR) methods are essential. Deep learning (DL) has demonstrated potential in enhancing SVR and SRR when compared to conventional methods. However, it requires large-scale external training datasets, which are difficult to obtain for clinical fetal MRI. To address this issue, we propose an unsupervised iterative SVR-SRR framework for isotropic HR volume reconstruction. Specifically, SVR is formulated as a function mapping a 2D slice and a 3D target volume to a rigid transformation matrix, which aligns the slice to the underlying location in the target volume. The function is parameterized by a convolutional neural network, which is trained by minimizing the difference between the volume slicing at the predicted position and the input slice. In SRR, a decoding network embedded within a deep image prior framework is incorporated with a comprehensive image degradation model to produce the high-resolution (HR) volume. The deep image prior framework offers a local consistency prior to guide the reconstruction of HR volumes. By performing a forward degradation model, the HR volume is optimized by minimizing loss between predicted slices and the observed slices. Comprehensive experiments conducted on large-magnitude motion-corrupted simulation data and clinical data demonstrate the superior performance of the proposed framework over state-of-the-art fetal brain reconstruction frameworks.