A Sparse Volume Reconstruction Method for Fetal Brain MRI Using Adaptive Kernel Regression.

Qian Ni,Ling Li,Tiexiang Wen,Yi Zhang,Erlei Zhang

doi:10.1155/2021/6685943

Abstract

Slice-to-volume reconstruction (SVR) method can deal well with motion artifacts and provide high-quality 3D image data for fetal brain MRI. However, the problem of sparse sampling is not well addressed in the SVR method. In this paper, we mainly focus on the sparse volume reconstruction of fetal brain MRI from multiple stacks corrupted with motion artifacts. Based on the SVR framework, our approach includes the slice-to-volume 2D/3D registration, the point spread function- (PSF-) based volume update, and the adaptive kernel regression-based volume update. The adaptive kernel regression can deal well with the sparse sampling data and enhance the detailed preservation by capturing the local structure through covariance matrix. Experimental results performed on clinical data show that kernel regression results in statistical improvement of image quality for sparse sampling data with the parameter setting of the structure sensitivity 0.4, the steering kernel size of 7 × 7 × 7 and steering smoothing bandwidth of 0.5. The computational performance of the proposed GPU-based method can be over 90 times faster than that on CPU.

Highlights

Magnetic resonance imaging (MRI) is an ideal diagnostic technique for researchers to investigate the development of the fetal brain [1]
We used the datasets from the fetal MRI datasets [16], which were acquired by a Philips Achieva 3 T MR scanner
We proposed an adaptive reconstruction method to deal with the sparse sampling dataset for fetal brain MRI

Summary

Introduction

Magnetic resonance imaging (MRI) is an ideal diagnostic technique for researchers to investigate the development of the fetal brain [1]. Its advantages are the absence of ionizing radiation, the availability of different contrast options (T1-weighted, T2-weighted, and diffusionweighted imaging), and the superior contrast of soft tissue compared with ultrasonography, and MRI is a safe and noninvasive procedure for patients and fetuses [2,3,4]. For these reasons, MRI has been widely used to investigate the developing fetal brain in vivo [5]. Fetal brain MRI can provide abundant information about aid clinical management, prognostication, and counseling [10]

Methods

Results

Conclusion