Robust Super-Resolution Volume Reconstruction From Slice Acquisitions: Application to Fetal Brain MRI

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.

Download Full-text

Deep robust residual network for super-resolution of 2D fetal brain MRI

Scientific Reports ◽

10.1038/s41598-021-03979-1 ◽

2022 ◽

Vol 12 (1) ◽

Author(s):

Liyao Song ◽

Quan Wang ◽

Ting Liu ◽

Haiwei Li ◽

Jiancun Fan ◽

...

Keyword(s):

Spatial Resolution ◽

High Efficiency ◽

Brain Mri ◽

Fetal Brain ◽

Super Resolution ◽

Adult Brain ◽

Superior Performance ◽

Residual Learning ◽

2D Data

AbstractSpatial resolution is a key factor of quantitatively evaluating the quality of magnetic resonance imagery (MRI). Super-resolution (SR) approaches can improve its spatial resolution by reconstructing high-resolution (HR) images from low-resolution (LR) ones to meet clinical and scientific requirements. To increase the quality of brain MRI, we study a robust residual-learning SR network (RRLSRN) to generate a sharp HR brain image from an LR input. Due to the Charbonnier loss can handle outliers well, and Gradient Difference Loss (GDL) can sharpen an image, we combined the Charbonnier loss and GDL to improve the robustness of the model and enhance the texture information of SR results. Two MRI datasets of adult brain, Kirby 21 and NAMIC, were used to train and verify the effectiveness of our model. To further verify the generalizability and robustness of the proposed model, we collected eight clinical fetal brain MRI 2D data for evaluation. The experimental results have shown that the proposed deep residual-learning network achieved superior performance and high efficiency over other compared methods.

Download Full-text

Fetal Brain Biometric Measurements on 3D Super-Resolution Reconstructed T2-Weighted MRI: An Intra- and Inter-observer Agreement Study

Frontiers in Pediatrics ◽

10.3389/fped.2021.639746 ◽

2021 ◽

Vol 9 ◽

Author(s):

Marie Khawam ◽

Priscille de Dumast ◽

Pierre Deman ◽

Hamza Kebiri ◽

Thomas Yu ◽

...

Keyword(s):

Brain Mri ◽

Fetal Brain ◽

Super Resolution ◽

Multiple Comparisons ◽

Observer Agreement ◽

Pediatric Radiologist ◽

Level Of Confidence ◽

Reconstructed Volume ◽

Significant Difference ◽

Biometric Measurements

We present the comparison of two-dimensional (2D) fetal brain biometry on magnetic resonance (MR) images using orthogonal 2D T2-weighted sequences (T2WSs) vs. one 3D super-resolution (SR) reconstructed volume and evaluation of the level of confidence and concordance between an experienced pediatric radiologist (obs1) and a junior radiologist (obs2). Twenty-five normal fetal brain MRI scans (18–34 weeks of gestation) including orthogonal 3-mm-thick T2WSs were analyzed retrospectively. One 3D SR volume was reconstructed per subject based on multiple series of T2WSs. The two observers performed 11 2D biometric measurements (specifying their level of confidence) on T2WS and SR volumes. Measurements were compared using the paired Wilcoxon rank sum test between observers for each dataset (T2WS and SR) and between T2WS and SR for each observer. Bland–Altman plots were used to assess the agreement between each pair of measurements. Measurements were made with low confidence in three subjects by obs1 and in 11 subjects by obs2 (mostly concerning the length of the corpus callosum on T2WS). Inter-rater intra-dataset comparisons showed no significant difference (p > 0.05), except for brain axial biparietal diameter (BIP) on T2WS and for brain and skull coronal BIP and coronal transverse cerebellar diameter (DTC) on SR. None of them remained significant after correction for multiple comparisons. Inter-dataset intra-rater comparisons showed statistical differences in brain axial and coronal BIP for both observers, skull coronal BIP for obs1, and axial and coronal DTC for obs2. After correction for multiple comparisons, only axial brain BIP remained significantly different, but differences were small (2.95 ± 1.73 mm). SR allows similar fetal brain biometry as compared to using the conventional T2WS while improving the level of confidence in the measurements and using a single reconstructed volume.

Download Full-text

Deep Robust Residual Network for Brain MRI Super-Resolution

10.21203/rs.3.rs-117695/v1 ◽

2020 ◽

Author(s):

Liyao Song ◽

Quan Wang ◽

Ting Liu ◽

Haiwei Li ◽

Jiancun Fan ◽

...

Keyword(s):

Spatial Resolution ◽

High Efficiency ◽

Brain Mri ◽

Fetal Brain ◽

Super Resolution ◽

Adult Brain ◽

Superior Performance ◽

Residual Learning ◽

Key Factor

Abstract Spatial resolution is a key factor of quantitatively evaluating the quality of magnetic resonance imagery (MRI). Super-resolution (SR) approaches can improve its spatial resolution by reconstructing high-resolution (HR) images from low-resolution (LR) ones to meet clinical and scientific requirements. To increase the quality of brain MRI, we study a robust residual-learning SR network (RRLSRN) to generate a sharp HR brain image from an LR input. Given that the Charbonnier loss can handle outliers well, and Gradient Difference Loss (GDL) can sharpen an image, we combine the Charbonnier loss and GDL to improve the robustness of the model and enhance the texture information of SR results. Two MRI datasets of adult brain, Kirby 21 and NAMIC, were used to train and verify the effectiveness of our model. To further verify the generalizability and robustness of the proposed model, we collected eight clinical fetal brain MRI data for evaluation. The experimental results show that the proposed deep residual-learning network achieved superior performance and high efficiency over other compared methods.

Download Full-text

An automated framework for localization, segmentation and super-resolution reconstruction of fetal brain MRI

NeuroImage ◽

10.1016/j.neuroimage.2019.116324 ◽

2020 ◽

Vol 206 ◽

pp. 116324 ◽

Cited By ~ 6

Author(s):

Michael Ebner ◽

Guotai Wang ◽

Wenqi Li ◽

Michael Aertsen ◽

Premal A. Patel ◽

...

Keyword(s):

Brain Mri ◽

Fetal Brain ◽

Super Resolution

Download Full-text

3D Registration of pre-surgical prostate MRI and histopathology images via super-resolution volume reconstruction

Medical Image Analysis ◽

10.1016/j.media.2021.101957 ◽

2021 ◽

Vol 69 ◽

pp. 101957

Author(s):

Rewa R. Sood ◽

Wei Shao ◽

Christian Kunder ◽

Nikola C. Teslovich ◽

Jeffrey B. Wang ◽

...

Keyword(s):

Super Resolution ◽

3D Registration ◽

Volume Reconstruction ◽

Prostate Mri ◽

Histopathology Images

Download Full-text

In utero MRI identifies consequences of early-gestation alcohol drinking on fetal brain development in rhesus macaques

Proceedings of the National Academy of Sciences ◽

10.1073/pnas.1919048117 ◽

2020 ◽

Vol 117 (18) ◽

pp. 10035-10044

Author(s):

Xiaojie Wang ◽

Verginia C. Cuzon Carlson ◽

Colin Studholme ◽

Natali Newman ◽

Matthew M. Ford ◽

...

Keyword(s):

White Matter ◽

Brain Development ◽

Ex Vivo ◽

Early Recognition ◽

Brain Mri ◽

Fetal Brain ◽

Fetal Mri ◽

Diffusion Anisotropy ◽

Self Administration ◽

White Matter Tracts

One factor that contributes to the high prevalence of fetal alcohol spectrum disorder (FASD) is binge-like consumption of alcohol before pregnancy awareness. It is known that treatments are more effective with early recognition of FASD. Recent advances in retrospective motion correction for the reconstruction of three-dimensional (3D) fetal brain MRI have led to significant improvements in the quality and resolution of anatomical and diffusion MRI of the fetal brain. Here, a rhesus macaque model of FASD, involving oral self-administration of 1.5 g/kg ethanol per day beginning prior to pregnancy and extending through the first 60 d of a 168-d gestational term, was utilized to determine whether fetal MRI could detect alcohol-induced abnormalities in brain development. This approach revealed differences between ethanol-exposed and control fetuses at gestation day 135 (G135), but not G110 or G85. At G135, ethanol-exposed fetuses had reduced brainstem and cerebellum volume and water diffusion anisotropy in several white matter tracts, compared to controls. Ex vivo electrophysiological recordings performed on fetal brain tissue obtained immediately following MRI demonstrated that the structural abnormalities observed at G135 are of functional significance. Specifically, spontaneous excitatory postsynaptic current amplitudes measured from individual neurons in the primary somatosensory cortex and putamen strongly correlated with diffusion anisotropy in the white matter tracts that connect these structures. These findings demonstrate that exposure to ethanol early in gestation perturbs development of brain regions associated with motor control in a manner that is detectable with fetal MRI.

Download Full-text