Altered structural fetal brain development has been linked to neuro-developmental disorders. These structural alterations can be potentially detected in utero using diffusion tensor imaging (DTI). However, acquisition and reconstruction of in utero fetal brain DTI remains challenging. Until now, motion-robust DTI methods have been employed for reconstruction of in utero fetal DTIs. However, due to the unconstrained fetal motion and permissible in utero acquisition times, these methods yielded limited success and have typically resulted in noisy DTIs. Consequently, atlases and methods that could enable groupwise studies, multi-modality imaging, and computer-aided diagnosis from in utero DTIs have not yet been developed. This paper presents the first DTI atlas of the fetal brain computed from in utero diffusion-weighted images. For this purpose an algorithm for computing an unbiased spatiotemporal DTI atlas, which integrates kernel-regression in age with a diffeomorphic tensor-to-tensor registration of motion-corrected and reconstructed individual fetal brain DTIs, was developed. Our new algorithm was applied to a set of 67 fetal DTI scans acquired from healthy fetuses each scanned at a gestational age between 21 and 39 weeks. The neurodevelopmental trends in the fetal brain, characterized by the atlas, were qualitatively and quantitatively compared with the observations reported in prior ex vivo and in utero studies, and with results from imaging gestational-age equivalent preterm infants. Our major findings revealed early presence of limbic fiber bundles, followed by the appearance and maturation of projection pathways (characterized by an age related increase in FA) during late 2nd and early 3rd trimesters. During the 3rd trimester association fiber bundles become evident. In parallel with the appearance and maturation of fiber bundles, from 21 to 39 gestational weeks gradual disappearance of the radial coherence of the telencephalic wall was qualitatively identified. These results and analyses show that our DTI atlas of the fetal brain is useful for reliable detection of major neuronal fiber bundle pathways and for characterization of the fetal brain reorganization that occurs in utero. The atlas can also serve as a useful resource for detection of normal and abnormal fetal brain development in utero.
With an aim to increase the capture range and accelerate the performance of state-of-the-art inter-subject and subject-to-template 3-D rigid registration, we propose deep learning-based methods that are trained to find the 3-D position of arbitrarily-oriented subjects or anatomy in a canonical space based on slices or volumes of medical images. For this, we propose regression convolutional neural networks (CNNs) that learn to predict the angle-axis representation of 3-D rotations and translations using image features. We use and compare mean square error and geodesic loss to train regression CNNs for 3-D pose estimation used in two different scenarios: slice-to-volume registration and volume-to-volume registration. As an exemplary application, we applied the proposed methods to register arbitrarily oriented reconstructed images of fetuses scanned in-utero at a wide gestational age range to a standard atlas space. Our results show that in such registration applications that are amendable to learning, the proposed deep learning methods with geodesic loss minimization achieved 3-D pose estimation with a wide capture range in real-time (<100ms). We also tested the generalization capability of the trained CNNs on an expanded age range and on images of newborn subjects with similar and different MR image contrasts. We trained our models on T2-weighted fetal brain MRI scans and used them to predict the 3-D pose of newborn brains based on T1-weighted MRI scans. We showed that the trained models generalized well for the new domain when we performed image contrast transfer through a conditional generative adversarial network. This indicates that the domain of application of the trained deep regression CNNs can be further expanded to image modalities and contrasts other than those used in training. A combination of our proposed methods with accelerated optimization-based registration algorithms can dramatically enhance the performance of automatic imaging devices and image processing methods of the future.
Fetuses with congenital heart disease (CHD) have third trimester alterations in cortical development on brain magnetic resonance imaging (MRI). However, the intersulcal relationships contributing to global sulcal pattern remain unknown. This study applied a novel method for examining the geometric and topological relationships between sulci to fetal brain MRIs from 21-30 gestational weeks in CHD fetuses (n = 19) and typically developing (TD) fetuses (n = 17). Sulcal pattern similarity index (SI) to template fetal brain MRIs was determined for the position, area, and depth for corresponding sulcal basins and intersulcal relationships for each subject. CHD fetuses demonstrated altered global sulcal patterns in the left hemisphere compared with TD fetuses (TD [SI, mean ± SD]: 0.822 ± 0.023, CHD: 0.795 ± 0.030, P = 0.002). These differences were present in the earliest emerging sulci and were driven by differences in the position of corresponding sulcal basins (TD: 0.897 ± 0.024, CHD: 0.878 ± 0.019, P = 0.006) and intersulcal relationships (TD: 0.876 ± 0.031, CHD: 0.857 ± 0.018, P = 0.033). No differences in cortical gyrification index, mean curvature, or surface area were present. These data suggest our methods may be more sensitive than traditional measures for evaluating cortical developmental alterations early in gestation.
PURPOSE: To achieve motion-robust diffusion compartment imaging (DCI) in near continuously moving subjects based on simultaneous multi-slice, diffusion-weighted brain MRI.
METHODS: Simultaneous multi-slice (SMS) acquisition enables fast and dense sampling of k- and q-space. We propose to achieve motion-robust DCI via slice-level motion correction by exploiting the rigid coupling between simultaneously acquired slices. This coupling provides 3D coverage of the anatomy that substantially constraints the slice-to-volume alignment problem. This is incorporated into an explicit model of motion dynamics that handles continuous and large subject motion in robust DCI reconstruction.
RESULTS: We applied the proposed technique, called Motion Tracking based on Simultanous Multislice Registration (MT-SMR) to multi b-value SMS diffusion-weighted brain MRI of healthy volunteers and motion-corrupted scans of 20 pediatric subjects. Quantitative and qualitative evaluation based on fractional anisotropy in unidirectional fiber regions, and DCI in crossing-fiber regions show robust reconstruction in the presence of motion.
CONCLUSION: The proposed approach has the potential to extend routine use of SMS DCI in very challenging populations, such as young children, newborns, and non-cooperative patients.
Altered brain development is a common feature of the neurological sequelae of complex congenital heart disease (CHD). These alterations include abnormalities in brain size and growth that begin prenatally and persist postnatally. However, the longitudinal trajectory of changes in brain volume from the prenatal to postnatal environment have not been investigated. We aimed to evaluate the trajectory of brain growth in a cohort of patients with complex CHD (n = 16) and healthy controls (n = 15) to test the hypothesis that patients with complex CHD would have smaller total brain volume (TBV) prenatally, which would become increasingly prominent by three months of age. Participants underwent fetal magnetic resonance imaging (MRI) at a mean of 32 weeks gestation, a preoperative/neonatal MRI shortly after birth, a postoperative MRI (CHD only), and a 3-month MRI to evaluate the trajectory of brain growth. Three-dimensional volumetric analysis was applied to the MRI data to measure TBV, as well as tissue-specific volumes of the cortical gray matter (CGM), white matter (WM), subcortical (deep nuclear) gray matter (SCGM), cerebellum, and cerebrospinal fluid (CSF). A random coefficients model was used to investigate longitudinal changes in TBV and demonstrated an altered trajectory of brain growth in the CHD population. The estimated slope for TBV from fetal to 3-month MRI was 11.5 cm per week for CHD infants compared to 16.7 cm per week for controls (p = 0.0002). Brain growth followed a similar trajectory for the CGM (p < 0.0001), SCGM (p = 0.002), and cerebellum (p = 0.005). There was no difference in growth of the WM (p = 0.30) or CSF (p = 0.085). Brain injury was associated with reduced TBV at 3-month MRI (p = 0.02). After removing infants with brain injury from the model, an altered trajectory of brain growth persisted in CHD infants (p = 0.006). These findings extend the existing literature by demonstrating longitudinal impairments in brain development in the CHD population and emphasize the global nature of disrupted brain growth from the prenatal environment through early infancy.
PURPOSE: To compare knee MRI performed with the integrated parallel acquisition technique (PAT) and simultaneous multislice (SMS) turbo spin echo (TSE) T2-weighted (T2w) sequences with conventional TSE sequences in pediatric patients.
MATERIALS AND METHODS: This was a retrospective IRB-approved study. Seventy-four subjects (26 male, 48 female, mean age 15.3 years, range 8-20) underwent 3-T MRI of the knee with a T2w TSE pulse sequence prototype with four-fold PAT and SMS acceleration as well as the standard PAT-only accelerated sequences. Images were anonymized and two study folders were created: one examination with only T2w PAT2 images (conventional examination) and one examination with only T2w SMS2/PAT2 sequences (SMS examination). Two readers rated examinations for 15 specific imaging findings and 5 quality metrics. Interreader agreement was measured. Signal to noise (SNR) and contrast to noise (CNR) were measured for SMS and conventional T2w sequences.
RESULTS: Consensus review demonstrated diagnostic quality performance of SMS examinations with respect to all 15 structures. Average area under the curve (AROC) was 0.95 and 0.97 for readers 1 and 2, respectively. The conventional sequence was favored over SMS for four out of five quality metrics (p < 0.001). SNR and CNR were higher for the conventional sequences compared to SMS.
CONCLUSION: SMS accelerated T2w TSE sequences offer a faster alternative for knee imaging in pediatric patients without compromise in diagnostic performance despite diminished SNR. The four-fold acceleration of SMS is beneficial to pediatric patients who often have difficulty staying still for long MRI examinations.
Brain segmentation is a fundamental first step in neuroimage analysis. In the case of fetal MRI, it is particularly challenging and important due to the arbitrary orientation of the fetus, organs that surround the fetal head, and intermittent fetal motion. Several promising methods have been proposed but are limited in their performance in challenging cases and in real-time segmentation. We aimed to develop a fully automatic segmentation method that independently segments sections of the fetal brain in 2D fetal MRI slices in real-time. To this end, we developed and evaluated a deep fully convolutional neural network based on 2D U-net and autocontext, and compared it to two alternative fast methods based on 1) a voxelwise fully convolutional network and 2) a method based on SIFT features, random forest and conditional random field. We trained the networks with manual brain masks on 250 stacks of training images, and tested on 17 stacks of normal fetal brain images as well as 18 stacks of extremely challenging cases based on extreme motion, noise, and severely abnormal brain shape. Experimental results show that our U-net approach outperformed the other methods and achieved average Dice metrics of 96.52% and 78.83% in the normal and challenging test sets, respectively. With an unprecedented performance and a test run time of about 1 second, our network can be used to segment the fetal brain in real-time while fetal MRI slices are being acquired. This can enable real-time motion tracking, motion detection, and 3D reconstruction of fetal brain MRI.
Brain extraction or whole brain segmentation is an important first step in many of the neuroimage analysis pipelines. The accuracy and the robustness of brain extraction, therefore, are crucial for the accuracy of the entire brain analysis process. The state-of-the-art brain extraction techniques rely heavily on the accuracy of alignment or registration between brain atlases and query brain anatomy, and/or make assumptions about the image geometry, and therefore have limited success when these assumptions do not hold or image registration fails. With the aim of designing an accurate, learning-based, geometry-independent, and registration-free brain extraction tool, in this paper, we present a technique based on an auto-context convolutional neural network (CNN), in which intrinsic local and global image features are learned through 2-D patches of different window sizes. We consider two different architectures: 1) a voxelwise approach based on three parallel 2-D convolutional pathways for three different directions (axial, coronal, and sagittal) that implicitly learn 3-D image information without the need for computationally expensive 3-D convolutions and 2) a fully convolutional network based on the U-net architecture. Posterior probability maps generated by the networks are used iteratively as context information along with the original image patches to learn the local shape and connectedness of the brain to extract it from non-brain tissue. The brain extraction results we have obtained from our CNNs are superior to the recently reported results in the literature on two publicly available benchmark data sets, namely, LPBA40 and OASIS, in which we obtained the Dice overlap coefficients of 97.73% and 97.62%, respectively. Significant improvement was achieved via our auto-context algorithm. Furthermore, we evaluated the performance of our algorithm in the challenging problem of extracting arbitrarily oriented fetal brains in reconstructed fetal brain magnetic resonance imaging (MRI) data sets. In this application, our voxelwise auto-context CNN performed much better than the other methods (Dice coefficient: 95.97%), where the other methods performed poorly due to the non-standard orientation and geometry of the fetal brain in MRI. Through training, our method can provide accurate brain extraction in challenging applications. This, in turn, may reduce the problems associated with image registration in segmentation tasks.
Most fetal brain MRI reconstruction algorithms rely only on brain tissue-relevant voxels of low-resolution (LR) images to enhance the quality of inter-slice motion correction and image reconstruction. Consequently the fetal brain needs to be localized and extracted as a first step, which is usually a laborious and time consuming manual or semi-automatic task. We have proposed in this work to use age-matched template images as prior knowledge to automatize brain localization and extraction. This has been achieved through a novel automatic brain localization and extraction method based on robust template-to-slice block matching and deformable slice-to-template registration. Our template-based approach has also enabled the reconstruction of fetal brain images in standard radiological anatomical planes in a common coordinate space. We have integrated this approach into our new reconstruction pipeline that involves intensity normalization, inter-slice motion correction, and super-resolution (SR) reconstruction. To this end we have adopted a novel approach based on projection of every slice of the LR brain masks into the template space using a fusion strategy. This has enabled the refinement of brain masks in the LR images at each motion correction iteration. The overall brain localization and extraction algorithm has shown to produce brain masks that are very close to manually drawn brain masks, showing an average Dice overlap measure of 94.5%. We have also demonstrated that adopting a slice-to-template registration and propagation of the brain mask slice-by-slice leads to a significant improvement in brain extraction performance compared to global rigid brain extraction and consequently in the quality of the final reconstructed images. Ratings performed by two expert observers show that the proposed pipeline can achieve similar reconstruction quality to reference reconstruction based on manual slice-by-slice brain extraction. The proposed brain mask refinement and reconstruction method has shown to provide promising results in automatic fetal brain MRI segmentation and volumetry in 26 fetuses with gestational age range of 23 to 38 weeks.
In this work, we introduce a novel motion-robust spatially constrained parameter estimation (MOSCOPE) technique for kidney diffusion-weighted MRI. The proposed motion compensation technique does not require a navigator, trigger, or breath-hold but only uses the intrinsic features of the acquired data to track and compensate for motion to reconstruct precise models of the renal diffusion signal. We have developed a technique for physiological motion tracking based on robust state estimation and sequential registration of diffusion sensitized slices acquired within 200ms. This allows a sampling rate of 5Hz for state estimation in motion tracking that is sufficiently faster than both respiratory and cardiac motion rates in children and adults, which range between 0.8 to 0.2Hz, and 2.5 to 1Hz, respectively. We then apply the estimated motion parameters to data from each slice and use motion-compensated data for 1) robust intra-voxel incoherent motion (IVIM) model estimation in the kidney using a spatially constrained model fitting approach, and 2) robust weighted least squares estimation of the diffusion tensor model. Experimental results, including precision of IVIM model parameters using bootstrap-sampling and whole kidney tractography, showed significant improvement in precision and accuracy of these models using the proposed method compared to models based on the original data and volumetric registration.
In magnetic resonance (MR), hardware limitations, scan time constraints, and patient movement often result in the acquisition of anisotropic 3-D MR images with limited spatial resolution in the out-of-plane views. Our goal is to construct an isotropic high-resolution (HR) 3-D MR image through upsampling and fusion of orthogonal anisotropic input scans. We propose a multiframe super-resolution (SR) reconstruction technique based on sparse representation of MR images. Our proposed algorithm exploits the correspondence between the HR slices and the low-resolution (LR) sections of the orthogonal input scans as well as the self-similarity of each input scan to train pairs of overcomplete dictionaries that are used in a sparse-land local model to upsample the input scans. The upsampled images are then combined using wavelet fusion and error backprojection to reconstruct an image. Features are learned from the data and no extra training set is needed. Qualitative and quantitative analyses were conducted to evaluate the proposed algorithm using simulated and clinical MR scans. Experimental results show that the proposed algorithm achieves promising results in terms of peak signal-to-noise ratio, structural similarity image index, intensity profiles, and visualization of small structures obscured in the LR imaging process due to partial volume effects. Our novel SR algorithm outperforms the nonlocal means (NLM) method using self-similarity, NLM method using self-similarity and image prior, self-training dictionary learning-based SR method, averaging of upsampled scans, and the wavelet fusion method. Our SR algorithm can reduce through-plane partial volume artifact by combining multiple orthogonal MR scans, and thus can potentially improve medical image analysis, research, and clinical diagnosis.
Longitudinal characterization of early brain growth in-utero has been limited by a number of challenges in fetal imaging, the rapid change in size, shape and volume of the developing brain, and the consequent lack of suitable algorithms for fetal brain image analysis. There is a need for an improved digital brain atlas of the spatiotemporal maturation of the fetal brain extending over the key developmental periods. We have developed an algorithm for construction of an unbiased four-dimensional atlas of the developing fetal brain by integrating symmetric diffeomorphic deformable registration in space with kernel regression in age. We applied this new algorithm to construct a spatiotemporal atlas from MRI of 81 normal fetuses scanned between 19 and 39 weeks of gestation and labeled the structures of the developing brain. We evaluated the use of this atlas and additional individual fetal brain MRI atlases for completely automatic multi-atlas segmentation of fetal brain MRI. The atlas is available online as a reference for anatomy and for registration and segmentation, to aid in connectivity analysis, and for groupwise and longitudinal analysis of early brain growth.
Diffusion weighted magnetic resonance imaging, or DWI, is one of the most promising tools for the analysis of neural microstructure and the structural connectome of the human brain. The application of DWI to map early development of the human connectome in-utero, however, is challenged by intermittent fetal and maternal motion that disrupts the spatial correspondence of data acquired in the relatively long DWI acquisitions. Fetuses move continuously during DWI scans. Reliable and accurate analysis of the fetal brain structural connectome requires careful compensation of motion effects and robust reconstruction to avoid introducing bias based on the degree of fetal motion. In this paper we introduce a novel robust algorithm to reconstruct in-vivo diffusion-tensor MRI (DTI) of the moving fetal brain and show its effect on structural connectivity analysis. The proposed algorithm involves multiple steps of image registration incorporating a dynamic registration-based motion tracking algorithm to restore the spatial correspondence of DWI data at the slice level and reconstruct DTI of the fetal brain in the standard (atlas) coordinate space. A weighted linear least squares approach is adapted to remove the effect of intra-slice motion and reconstruct DTI from motion-corrected data. The proposed algorithm was tested on data obtained from 21 healthy fetuses scanned in-utero at 22-38 weeks gestation. Significantly higher fractional anisotropy values in fiber-rich regions, and the analysis of whole-brain tractography and group structural connectivity, showed the efficacy of the proposed method compared to the analyses based on original data and previously proposed methods. The results of this study show that slice-level motion correction and robust reconstruction is necessary for reliable in-vivo structural connectivity analysis of the fetal brain. Connectivity analysis based on graph theoretic measures show high degree of modularity and clustering, and short average characteristic path lengths indicative of small-worldness property of the fetal brain network. These findings comply with previous findings in newborns and a recent study on fetuses. The proposed algorithm can provide valuable information from DWI of the fetal brain not available in the assessment of the original 2D slices and may be used to more reliably study the developing fetal brain connectome.
PURPOSE: Current diagnosis of fetal posterior fossa anomalies by sonography and conventional MRI is limited by fetal position, motion, and by two-dimensional (2D), rather than three-dimensional (3D), representation. In this study, we aimed to validate the use of a novel magnetic resonance imaging (MRI) technique, 3D super-resolution motion-corrected MRI, to image the fetal posterior fossa.
METHODS: From a database of pregnant women who received fetal MRIs at our institution, images of 49 normal fetal brains were reconstructed. Six measurements of the cerebellum, vermis, and pons were obtained for all cases on 2D conventional and 3D reconstructed MRI, and the agreement between the two methods was determined using concordance correlation coefficients. Concordance of axial and coronal measurements of the transcerebellar diameter was also assessed within each method.
RESULTS: Between the two methods, the concordance of measurements was high for all six structures (P < .001), and was highest for larger structures such as the transcerebellar diameter. Within each method, agreement of axial and coronal measurements of the transcerebellar diameter was superior in 3D reconstructed MRI compared to 2D conventional MRI (P < .001).
CONCLUSIONS: This comparison study validates the use of 3D super-resolution motion-corrected MRI for imaging the fetal posterior fossa, as this technique results in linear measurements that have high concordance with 2D conventional MRI measurements. Lengths of the transcerebellar diameter measured within a 3D reconstruction are more concordant between imaging planes, as they correct for fetal motion and orthogonal slice acquisition. This technique will facilitate further study of fetal abnormalities of the posterior fossa.