Showing papers by "Maria Deprez published in 2020"

Deformable Slice-to-Volume Registration for Motion Correction of Fetal Body and Placenta MRI

Abstract: In in-utero MRI, motion correction for fetal body and placenta poses a particular challenge due to the presence of local non-rigid transformations of organs caused by bending and stretching. The existing slice-to-volume registration (SVR) reconstruction methods are widely employed for motion correction of fetal brain that undergoes only rigid transformation. However, for reconstruction of fetal body and placenta, rigid registration cannot resolve the issue of misregistrations due to deformable motion, resulting in degradation of features in the reconstructed volume. We propose a Deformable SVR (DSVR), a novel approach for non-rigid motion correction of fetal MRI based on a hierarchical deformable SVR scheme to allow high resolution reconstruction of the fetal body and placenta. Additionally, a robust scheme for structure-based rejection of outliers minimises the impact of registration errors. The improved performance of DSVR in comparison to SVR and patch-to-volume registration (PVR) methods is quantitatively demonstrated in simulated experiments and 20 fetal MRI datasets from 28–31 weeks gestational age (GA) range with varying degree of motion corruption. In addition, we present qualitative evaluation of 100 fetal body cases from 20–34 weeks GA range.

Fetal whole heart blood flow imaging using 4D cine MRI.

Abstract: Prenatal detection of congenital heart disease facilitates the opportunity for potentially life-saving care immediately after the baby is born. Echocardiography is routinely used for screening of morphological malformations, but functional measurements of blood flow are scarcely used in fetal echocardiography due to technical assumptions and issues of reliability. Magnetic resonance imaging (MRI) is readily used for quantification of abnormal blood flow in adult hearts, however, existing in utero approaches are compromised by spontaneous fetal motion. Here, we present and validate a novel method of MRI velocity-encoding combined with a motion-robust reconstruction framework for four-dimensional visualization and quantification of blood flow in the human fetal heart and major vessels. We demonstrate simultaneous 4D visualization of the anatomy and circulation, which we use to quantify flow rates through various major vessels. The framework introduced here could enable new clinical opportunities for assessment of the fetal cardiovascular system in both health and disease.

Higher Order Spherical Harmonics Reconstruction of Fetal Diffusion MRI With Intensity Correction

Abstract: We present a novel method for higher order reconstruction of fetal diffusion MRI signal that enables detection of fiber crossings. We combine data-driven motion and intensity correction with super-resolution reconstruction and spherical harmonic parametrisation to reconstruct data scattered in both spatial and angular domains into consistent fetal dMRI signal suitable for further diffusion analysis. We show that intensity correction is essential for good performance of the method and identify anatomically plausible fiber crossings. The proposed methodology has potential to facilitate detailed investigation of developing brain connectivity and microstructure in-utero.

Assessment of radial glia in the frontal lobe of fetuses with Down syndrome.

Abstract: Down syndrome (DS) occurs with triplication of human chromosome 21 and is associated with deviations in cortical development evidenced by simplified gyral appearance and reduced cortical surface area. Radial glia are neuronal and glial progenitors that also create a scaffolding structure essential for migrating neurons to reach cortical targets and therefore play a critical role in cortical development. The aim of this study was to characterise radial glial expression pattern and morphology in the frontal lobe of the developing human fetal brain with DS and age-matched controls. Secondly, we investigated whether microstructural information from in vivo magnetic resonance imaging (MRI) could reflect histological findings from human brain tissue samples. Immunohistochemistry was performed on paraffin-embedded human post-mortem brain tissue from nine fetuses and neonates with DS (15–39 gestational weeks (GW)) and nine euploid age-matched brains (18–39 GW). Radial glia markers CRYAB, HOPX, SOX2, GFAP and Vimentin were assessed in the Ventricular Zone, Subventricular Zone and Intermediate Zone. In vivo diffusion MRI was used to assess microstructure in these regions in one DS (21 GW) and one control (22 GW) fetal brain. We found a significant reduction in radial glial progenitor SOX2 and subtle deviations in radial glia expression (GFAP and Vimentin) prior to 24 GW in DS. In vivo, fetal MRI demonstrates underlying radial projections consistent with immunohistopathology. Radial glial alterations may contribute to the subsequent simplified gyral patterns and decreased cortical volumes observed in the DS brain. Recent advances in fetal MRI acquisition and analysis could provide non-invasive imaging-based biomarkers of early developmental deviations.

Deformable Slice-to-Volume Registration for Reconstruction of Quantitative T2* Placental and Fetal MRI.

Abstract: In 4D T2* placental MRI studies, motion correction is generally considered a prerequisite for quantitative analysis. However, the existing approaches use only global spatio-temporal alignment based on the classical 3D nonrigid registration and do not correct inter-slice motion. Alignment of T2* and T2 volumes in one reference space could also address the limitation of low resolution of T2* stacks and allow analysis of finer anatomical features. This work introduces a novel pipeline for motion correction in 4D T2* and 3D T2*+T2 placental MRI datasets based on the deformable slice-to-volume registration (DSVR) method. The pipelines are evaluated on 60 T2* placental MRI datasets.

Multi-channel Registration for Diffusion MRI: Longitudinal Analysis for the Neonatal Brain

Abstract: In multi-channel (MC) registration, fusion of structural and diffusion brain MRI provides information on both cortex and white matter (WM) structures thus decreasing the uncertainty of deformation fields. However, the existing solutions employ only diffusion tensor imaging (DTI) derived metrics which are limited by inconsistencies in fiber-crossing regions. In this work, we extend the pipeline for registration of multi-shell high angular resolution diffusion imaging (HARDI) [15] with a novel similarity metric based on angular correlation and an option for multi-channel registration that allows incorporation of structural MRI. The contributions of channels to the displacement field are weighted with spatially varying certainty maps. The implementation is based on MRtrix3 (MRtrix3: https://www.mrtrix.org) toolbox. The approach is quantitatively evaluated on intra-patient longitudinal registration of diffusion MRI datasets of 20 preterm neonates with 7–11 weeks gap between the scans. In addition, we present an example of an MC template generated using the proposed method.

Diffusion tensor driven image registration: a deep learning approach

Abstract: Tracking microsctructural changes in the developing brain relies on accurate inter-subject image registration. However, most methods rely on either structural or diffusion data to learn the spatial correspondences between two or more images, without taking into account the complementary information provided by using both. Here we propose a deep learning registration framework which combines the structural information provided by \(T_2\)-weighted (\(T_2\)w) images with the rich microstructural information offered by diffusion tensor imaging (DTI) scans. This allows our trained network to register pairs of images in a single pass. We perform a leave-one-out cross-validation study where we compare the performance of our multi-modality registration model with a baseline model trained on structural data only, in terms of Dice scores and differences in fractional anisotropy (FA) maps. Our results show that in terms of average Dice scores our model performs better in subcortical regions when compared to using structural data only. Moreover, average sum-of-squared differences between warped and fixed FA maps show that our proposed model performs better at aligning the diffusion data.

Predicting age and clinical risk from the neonatal connectome

Abstract: The development of perinatal brain connectivity underpins motor, cognitive and behavioural abilities in later life. With the rise of advanced imaging methods such as diffusion MRI, the study of brain connectivity has emerged as an important tool to understand subtle alterations associated with neurodevelopmental conditions. Brain connectivity derived from diffusion MRI is complex, multi-dimensional and noisy, and hence it can be challenging to interpret on an individual basis. Machine learning methods have proven to be a powerful tool to uncover hidden patterns in such data, thus opening an opportunity for early identification of atypical development and potentially more efficient treatment. In this work, we used Deep Neural Networks and Random Forests to predict neurodevelopmental characteristics from neonatal structural connectomes, in a large sample of neonates (N = 524) derived from the developing Human Connectome Project. We achieved a highly accurate prediction of post menstrual age (PMA) at scan on term-born infants (Mean absolute error (MAE) = 0.72 weeks, r = 0.83, p<<0.001). We also achieved good accuracy when predicting gestational age at birth on a cohort of term and preterm babies scanned at term equivalent age (MAE = 2.21 weeks, r = 0.82, p<<0.001). From our models of PMA at scan for infants born at term, we computed the brain maturation index (i.e. predicted minus actual age) of individual preterm neonates and found significant correlation of this index with motor outcome at 18 months corrected age. Our results suggest that the neural substrate for later neurological functioning is detectable within a few weeks after birth in the structural connectome.

Harmonised Segmentation of Neonatal Brain MRI: A Domain Adaptation Approach

Abstract: Medical image deep learning segmentation has shown great potential in becoming an ubiquitous part of the clinical analysis pipeline. However, these methods cannot guarantee high quality predictions when the source and target domains are dissimilar due to different acquisition protocols, or biases in patient cohorts. Recently, unsupervised domain adaptation techniques have shown great potential in alleviating this problem by minimizing the shift between the source and target distributions. In this work, we aim to predict tissue segmentation maps on an unseen dataset, which has both different acquisition parameters and population bias when compared to our training data. We achieve this by investigating two unsupervised domain adaptation (UDA) techniques with the objective of finding the best solution for our problem. We compare the two methods with a baseline fully-supervised segmentation network in terms of cortical thickness measures.

Author Correction: Fetal whole heart blood flow imaging using 4D cine MRI.

Abstract: A Correction to this paper has been published: https://doi.org/10.1038/s41467-020-20353-3

Diffusion tensor driven image registration: a deep learning approach

Abstract: Tracking microsctructural changes in the developing brain relies on accurate inter-subject image registration However, most methods rely on either structural or diffusion data to learn the spatial correspondences between two or more images, without taking into account the complementary information provided by using both Here we propose a deep learning registration framework which combines the structural information provided by T2-weighted (T2w) images with the rich microstructural information offered by diffusion tensor imaging (DTI) scans We perform a leave-one-out cross-validation study where we compare the performance of our multi-modality registration model with a baseline model trained on structural data only, in terms of Dice scores and differences in fractional anisotropy (FA) maps Our results show that in terms of average Dice scores our model performs better in subcortical regions when compared to using structural data only Moreover, average sum-of-squared differences between warped and fixed FA maps show that our proposed model performs better at aligning the diffusion data