dStripe: Slice artefact correction in diffusion MRI via constrained neural network

Deep learning microstructure estimation of developing brains from diffusion MRI: A newborn and fetal study

Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. Fiber orientation distribution functions (FODs) are a common way of representing the orientation and density of white matter fibers. However, with standard FOD computation methods, accurate estimation requires a large number of measurements that usually cannot be acquired for newborns and fetuses. We propose to overcome this limitation by using a deep learning method to map as few as six diffusion-weighted measurements to the target FOD. To train the model, we use the FODs computed using multi-shell high angular resolution measurements as target. Extensive quantitative evaluations show that the new deep learning method, using significantly fewer measurements, achieves comparable or superior results than standard methods such as Constrained Spherical Deconvolution and two state-of-the-art deep learning methods. For voxels with one and two fibers, respectively, our method shows an agreement rate in terms of the number of fibers of 77.5% and 22.2%, which is 3% and 5.4% higher than other deep learning methods, and an angular error of 10° and 20°, which is 6° and 5° lower than other deep learning methods. To determine baselines for assessing the performance of our method, we compute agreement metrics using densely sampled newborn data. Moreover, we demonstrate the generalizability of the new deep learning method across scanners, acquisition protocols, and anatomy on two clinical external datasets of newborns and fetuses. We validate fetal FODs, successfully estimated for the first time with deep learning, using post-mortem histological data. Our results show the advantage of deep learning in computing the fiber orientation density for the developing brain from in-vivo dMRI measurements that are often very limited due to constrained acquisition times. Our findings also highlight the intrinsic limitations of dMRI for probing the developing brain microstructure.

Deep learning microstructure estimation of developing brains from diffusion MRI: a newborn and fetal study

Diffusion-weighted magnetic resonance imaging (dMRI) is widely used to assess the brain white matter. Fiber orientation distribution functions (FODs) are a common way of representing the orientation and density of white matter fibers. However, with standard FOD computation methods, accurate estimation of FODs requires a large number of measurements that usually cannot be acquired for newborns and fetuses. We propose to overcome this limitation by using a deep learning method to map as few as six diffusion-weighted measurements to the target FOD. To train the model, we use the FODs computed using multi-shell high angular resolution measurements as target. Extensive quantitative evaluations show that the new deep learning method, using significantly fewer measurements, achieves comparable or superior results to standard methods such as Constrained Spherical Deconvolution. We demonstrate the generalizability of the new deep learning method across scanners, acquisition protocols, and anatomy on two clinical datasets of newborns and fetuses. Additionally, we compute agreement metrics within the HARDI newborn dataset, and validate fetal FODs with post-mortem histological data. The results of this study show the advantage of deep learning in inferring the microstructure of the developing brain from in-vivo dMRI measurements that are often very limited due to subject motion and limited acquisition times, but also highlight the intrinsic limitations of dMRI in the analysis of the developing brain microstructure. These findings, therefore, advocate for the need for improved methods that are tailored to studying the early development of human brain.

Maternal depressive symptoms, neonatal white matter, and toddler social-emotional development

Maternal prenatal depression is associated with increased likelihood of neurodevelopmental and psychiatric conditions in offspring. The relationship between maternal depression and offspring outcome may be mediated by in-utero changes in brain development. Recent advances in magnetic resonance imaging (MRI) have enabled in vivo investigations of neonatal brains, minimising the effect of postnatal influences. The aim of this study was to examine associations between maternal prenatal depressive symptoms, infant white matter, and toddler behaviour. 413 mother-infant dyads enrolled in the developing Human Connectome Project. Mothers completed the Edinburgh Postnatal Depression Scale (median = 5, range = 0-28, n = 52 scores ≥ 11). Infants (n = 223 male) (median gestational age at birth = 40 weeks, range 32.14-42.29) underwent MRI (median postmenstrual age at scan = 41.29 weeks, range 36.57-44.71). Fixel-based fibre metrics (mean fibre density, fibre cross-section, and fibre density modulated by cross-section) were calculated from diffusion imaging data in the left and right uncinate fasciculi and cingulum bundle. For n = 311, internalising and externalising behaviour, and social-emotional abilities were reported at a median corrected age of 18 months (range 17-24). Statistical analysis used multiple linear regression and mediation analysis with bootstrapping. Maternal depressive symptoms were positively associated with infant fibre density in the left (B = 0.0005, p = 0.003, q = 0.027) and right (B = 0.0006, p = 0.003, q = 0.027) uncinate fasciculus, with left uncinate fasciculus fibre density, in turn, positively associated with social-emotional abilities in toddlerhood (B = 105.70, p = 0.0007, q = 0.004). In a mediation analysis, higher maternal depressive symptoms predicted toddler social-emotional difficulties (B = 0.342, t(307) = 3.003, p = 0.003), but this relationship was not mediated by fibre density in the left uncinate fasciculus (Sobel test p = 0.143, bootstrapped indirect effect = 0.035, SE = 0.02, 95% CI: [-0.01, 0.08]). There was no evidence of an association between maternal depressive and cingulum fibre properties. These findings suggest that maternal perinatal depressive symptoms are associated with neonatal uncinate fasciculi microstructure, but not fibre bundle size, and toddler behaviour.

The Developing Human Connectome Project Neonatal Data Release

The Developing Human Connectome Project has created a large open science resource which provides researchers with data for investigating typical and atypical brain development across the perinatal period. It has collected 1228 multimodal magnetic resonance imaging (MRI) brain datasets from 1173 fetal and/or neonatal participants, together with collateral demographic, clinical, family, neurocognitive and genomic data from 1173 participants, together with collateral demographic, clinical, family, neurocognitive and genomic data. All subjects were studied in utero and/or soon after birth on a single MRI scanner using specially developed scanning sequences which included novel motion-tolerant imaging methods. Imaging data are complemented by rich demographic, clinical, neurodevelopmental, and genomic information. The project is now releasing a large set of neonatal data; fetal data will be described and released separately. This release includes scans from 783 infants of whom: 583 were healthy infants born at term; as well as preterm infants; and infants at high risk of atypical neurocognitive development. Many infants were imaged more than once to provide longitudinal data, and the total number of datasets being released is 887. We now describe the dHCP image acquisition and processing protocols, summarize the available imaging and collateral data, and provide information on how the data can be accessed.