Early folding patterns and asymmetries of the normal human brain detected from in utero MRI.

Early cortical folding and the emergence of structural brain asymmetries have been previously analyzed by neuropathology as well as qualitative analysis of magnetic resonance imaging (MRI) of fetuses and preterm neonates. In this study, we present a dedicated image analysis framework and its application for the detection of folding patterns during the critical period for the formation of many primary sulci (20-28 gestational weeks). Using structural information from in utero MRI, we perform morphometric analysis of cortical plate surface development and modeling of early folding in the normal fetal brain. First, we identify regions of the fetal brain surface that undergo significant folding changes during this developmental period and provide precise temporal staging of these changes for each region of interest. Then, we highlight the emergence of interhemispheric structural asymmetries that may be related to future functional specialization of cortical areas. Our findings complement previous descriptions of early sulcogenesis based on neuropathology and qualitative evaluation of 2D in utero MRI by accurate spatial and temporal mapping of the emergence of individual sulci as well as structural brain asymmetries. The study provides the missing starting point for their developmental trajectories and extends our understanding of normal cortical folding.

Local tissue growth patterns underlying normal fetal human brain gyrification quantified in utero.

Existing knowledge of growth patterns in the living fetal human brain is based upon in utero imaging studies by magnetic resonance imaging (MRI) and ultrasound, which describe overall growth and provide mainly qualitative findings. However, formation of the complex folded cortical structure of the adult brain requires, in part, differential rates of regional tissue growth. To better understand these local tissue growth patterns, we applied recent advances in fetal MRI motion correction and computational image analysis techniques to 40 normal fetal human brains covering a period of primary sulcal formation (20-28 gestational weeks). Growth patterns were mapped by quantifying tissue locations that were expanding more or less quickly than the overall cerebral growth rate, which reveal increasing structural complexity. We detected increased local relative growth rates in the formation of the precentral and postcentral gyri, right superior temporal gyrus, and opercula, which differentiated between the constant growth rate in underlying cerebral mantle and the accelerating rate in the cortical plate undergoing folding. Analysis focused on the cortical plate revealed greater volume increases in parietal and occipital regions compared to the frontal lobe. Cortical plate growth patterns constrained to narrower age ranges showed that gyrification, reflected by greater growth rates, was more pronounced after 24 gestational weeks. Local hemispheric volume asymmetry was located in the posterior peri-Sylvian area associated with structural lateralization in the mature brain. These maps of fetal brain growth patterns construct a spatially specific baseline of developmental biomarkers with which to correlate abnormal development in the human.

Mapping directionality specific volume changes using tensor based morphometry: an application to the study of gyrogenesis and lateralization of the human fetal brain.

Tensor based morphometry (TBM) is a powerful approach to analyze local structural changes in brain anatomy. However, conventional scalar TBM methods do not completely capture all direction specific volume changes required to model complex changes such as those during brain growth. In this paper, we describe novel TBM descriptors for studying direction-specific changes in a subject population which can be used in conjunction with scalar TBM to analyze local patterns in directionality of volume change during brain development. We also extend the methodology to provide a new approach to mapping directional asymmetry in deformation tensors associated with the emergence of structural asymmetry in the developing brain. We illustrate the use of these methods by studying developmental patterns in the human fetal brain, in vivo. Results show that fetal brain development exhibits a distinct spatial pattern of anisotropic growth. The most significant changes in the directionality of growth occur in the cortical plate at major sulci. Our analysis also detected directional growth asymmetry in the peri-Sylvian region and the medial frontal lobe of the fetal brain.

3D morphometric analysis of human fetal cerebellar development.

To date, growth of the human fetal cerebellum has been estimated primarily from linear measurements from ultrasound and 2D magnetic resonance imaging (MRI). In this study, we use 3D analytical methods to develop normative growth trajectories for the cerebellum in utero. We measured cerebellar volume, linear dimensions, and local surface curvature from 3D reconstructed MRI of the human fetal brain (N = 46). We found that cerebellar volume increased approximately 7-fold from 20 to 31 gestational weeks. The better fit of the exponential curve (R (2) = 0.96) compared to the linear curve (R (2) = 0.92) indicated acceleration in growth. Within-subject cerebellar and cerebral volumes were highly correlated (R (2) = 0.94), though the cerebellar percentage of total brain volume increased from approximately 2.4% to 3.7% (R (2) = 0.63). Right and left hemispheric volumes did not significantly differ. Transcerebellar diameter, vermal height, and vermal anterior to posterior diameter increased significantly at constant rates. From the local curvature analysis, we found that expansion along the inferior and superior aspects of the hemispheres resulted in decreased convexity, which is likely due to the physical constraints of the dura surrounding the cerebellum and the adjacent brainstem. The paired decrease in convexity along the inferior vermis and increased convexity of the medial hemisphere represents development of the paravermian fissure, which becomes more visible during this period. In this 3D morphometric analysis of the human fetal cerebellum, we have shown that cerebellar growth is accelerating at a greater pace than the cerebrum and described how cerebellar growth impacts the shape of the structure.

Fetal hippocampal development: analysis by magnetic resonance imaging volumetry.

The hippocampal formation plays an important role in learning and memory; however, data on its development in utero in humans are limited. This study was performed to evaluate hippocampal development in healthy fetuses using 3D reconstructed MRI. A cohort of 20 healthy pregnant women underwent prenatal MRI at a median GA of 24.9 wk (range, 21.3-31.9 wk); six of the women also had a second fetal MRI performed at a 6-wk interval. Routine 2D ultrafast T2-weighted images were used to reconstruct a 3D volume image, which was then used to manually segment the right and left hippocampi. Total hippocampal volume was calculated for each subject and compared against GA. There was a linear increase in total hippocampal volume with increasing GA (p < 0.001). For subjects scanned twice, there was an increase in hippocampal size on the second fetal MRI (p = 0.0004). This represents the first volumetric study of fetal hippocampal development in vivo. This normative volumetric data will be helpful for future comparison studies of suspected developmental abnormalities of hippocampal structure and function.

A spatiotemporal atlas of MR intensity, tissue probability and shape of the fetal brain with application to segmentation.

Modeling and analysis of MR images of the developing human brain is a challenge due to rapid changes in brain morphology and morphometry. We present an approach to the construction of a spatiotemporal atlas of the fetal brain with temporal models of MR intensity, tissue probability and shape changes. This spatiotemporal model is created from a set of reconstructed MR images of fetal subjects with different gestational ages. Groupwise registration of manual segmentations and voxelwise nonlinear modeling allow us to capture the appearance, disappearance and spatial variation of brain structures over time. Applying this model to atlas-based segmentation, we generate age-specific MR templates and tissue probability maps and use them to initialize automatic tissue delineation in new MR images. The choice of model parameters and the final performance are evaluated using clinical MR scans of young fetuses with gestational ages ranging from 20.57 to 24.71 weeks. Experimental results indicate that quadratic temporal models can correctly capture growth-related changes in the fetal brain anatomy and provide improvement in accuracy of atlas-based tissue segmentation.

Atlas-based segmentation of developing tissues in the human brain with quantitative validation in young fetuses.

Imaging of the human fetus using magnetic resonance (MR) is an essential tool for quantitative studies of normal as well as abnormal brain development in utero. However, because of fundamental differences in tissue types, tissue properties and tissue distribution between the fetal and adult brain, automated tissue segmentation techniques developed for adult brain anatomy are unsuitable for this data. In this paper, we describe methodology for automatic atlas-based segmentation of individual tissue types in motion-corrected 3D volumes reconstructed from clinical MR scans of the fetal brain. To generate anatomically correct automatic segmentations, we create a set of accurate manual delineations and build an in utero 3D statistical atlas of tissue distribution incorporating developing gray and white matter as well as transient tissue types such as the germinal matrix. The probabilistic atlas is associated with an unbiased average shape and intensity template for registration of new subject images to the space of the atlas. Quantitative whole brain 3D validation of tissue labeling performed on a set of 14 fetal MR scans (20.57-22.86 weeks gestational age) demonstrates that this atlas-based EM segmentation approach achieves consistently high DSC performance for the main tissue types in the fetal brain. This work indicates that reliable measures of brain development can be automatically derived from clinical MR imaging and opens up possibility of further 3D volumetric and morphometric studies with multiple fetal subjects.

Decision optimization of case-based computer-aided decision systems using genetic algorithms with application to mammography.

This paper presents an optimization framework for improving case-based computer-aided decision (CB-CAD) systems. The underlying hypothesis of the study is that each example in the knowledge database of a medical decision support system has different importance in the decision making process. A new decision algorithm incorporating an importance weight for each example is proposed to account for these differences. The search for the best set of importance weights is defined as an optimization problem and a genetic algorithm is employed to solve it. The optimization process is tailored to maximize the system's performance according to clinically relevant evaluation criteria. The study was performed using a CAD system developed for the classification of regions of interests (ROIs) in mammograms as depicting masses or normal tissue. The system was constructed and evaluated using a dataset of ROIs extracted from the Digital Database for Screening Mammography (DDSM). Experimental results show that, according to receiver operator characteristic (ROC) analysis, the proposed method significantly improves the overall performance of the CAD system as well as its average specificity for high breast mass detection rates.

Training neural network classifiers for medical decision making: the effects of imbalanced datasets on classification performance.

This study investigates the effect of class imbalance in training data when developing neural network classifiers for computer-aided medical diagnosis. The investigation is performed in the presence of other characteristics that are typical among medical data, namely small training sample size, large number of features, and correlations between features. Two methods of neural network training are explored: classical backpropagation (BP) and particle swarm optimization (PSO) with clinically relevant training criteria. An experimental study is performed using simulated data and the conclusions are further validated on real clinical data for breast cancer diagnosis. The results show that classifier performance deteriorates with even modest class imbalance in the training data. Further, it is shown that BP is generally preferable over PSO for imbalanced training data especially with small data sample and large number of features. Finally, it is shown that there is no clear preference between oversampling and no compensation approach and some guidance is provided regarding a proper selection.

Reliability analysis framework for computer-assisted medical decision systems.

We present a technique that enhances computer-assisted decision (CAD) systems with the ability to assess the reliability of each individual decision they make. Reliability assessment is achieved by measuring the accuracy of a CAD system with known cases similar to the one in question. The proposed technique analyzes the feature space neighborhood of the query case to dynamically select an input-dependent set of known cases relevant to the query. This set is used to assess the local (query-specific) accuracy of the CAD system. The estimated local accuracy is utilized as a reliability measure of the CAD response to the query case. The underlying hypothesis of the study is that CAD decisions with higher reliability are more accurate. The above hypothesis was tested using a mammographic database of 1337 regions of interest (ROIs) with biopsy-proven ground truth (681 with masses, 656 with normal parenchyma). Three types of decision models, (i) a back-propagation neural network (BPNN), (ii) a generalized regression neural network (GRNN), and (iii) a support vector machine (SVM), were developed to detect masses based on eight morphological features automatically extracted from each ROI. The performance of all decision models was evaluated using the Receiver Operating Characteristic (ROC) analysis. The study showed that the proposed reliability measure is a strong predictor of the CAD system's case-specific accuracy. Specifically, the ROC area index for CAD predictions with high reliability was significantly better than for those with low reliability values. This result was consistent across all decision models investigated in the study. The proposed case-specific reliability analysis technique could be used to alert the CAD user when an opinion that is unlikely to be reliable is offered. The technique can be easily deployed in the clinical environment because it is applicable with a wide range of classifiers regardless of their structure and it requires neither additional training nor building multiple decision models to assess the case-specific CAD accuracy.

Volumetric and surface-based 3D MRI analyses of fetal isolated mild ventriculomegaly: brain morphometry in ventriculomegaly.

Diagnosis of fetal isolated mild ventriculomegaly (IMVM) is the most common brain abnormality on prenatal ultrasound. We have set to identify potential alterations in brain development specific to IMVM in tissue volume and cortical and ventricular local surface curvature derived from in utero magnetic resonance imaging (MRI). Multislice 2D T2-weighted MRI were acquired from 32 fetuses (16 IMVM, 16 controls) between 22 and 25.5 gestational weeks. The images were motion-corrected and reconstructed into 3D volumes for volumetric and curvature analyses. The brain images were automatically segmented into cortical plate, cerebral mantle, deep gray nuclei, and ventricles. Volumes were compared between IMVM and control subjects. Surfaces were extracted from the segmentations for local mean surface curvature measurement on the inner cortical plate and the ventricles. Linear models were estimated for age-related and ventricular volume-associated changes in local curvature in both the inner cortical plate and ventricles. While ventricular volume was enlarged in IMVM, all other tissue volumes were not different from the control group. Ventricles increased in curvature with age along the atrium and anterior body. Increasing ventricular volume was associated with reduced curvature over most of the ventricular surface. The cortical plate changed in curvature with age at multiple sites of primary sulcal formation. Reduced cortical folding was detected near the parieto-occipital sulcus in IMVM subjects. While tissue volume appears to be preserved in brains with IMVM, cortical folding may be affected in regions where ventricles are dilated.

A supervised patch-based approach for human brain labeling.

We propose in this work a patch-based image labeling method relying on a label propagation framework. Based on image intensity similarities between the input image and an anatomy textbook, an original strategy which does not require any nonrigid registration is presented. Following recent developments in nonlocal image denoising, the similarity between images is represented by a weighted graph computed from an intensity-based distance between patches. Experiments on simulated and in vivo magnetic resonance images show that the proposed method is very successful in providing automated human brain labeling.

Spatiotemporal morphometry of adjacent tissue layers with application to the study of sulcal formation.

The process of brain growth involves the expansion of tissue at different rates at different points within the brain. As the layers within the developing brain evolve they can thicken or increase in area as the brain surface begins to fold. In this work we propose a new spatiotemporal formulation of tensor based volume morphometry that is derived in relation to tissue boundaries. This allows the study of the directional properties of tissue growth by separately characterizing the changes in area and thickness of the adjacent layers. The approach uses temporally weighted, local regression across a population of anatomies with different ages to model changes in components of the growth radial and tangential to the boundary between tissue layers. The formulation is applied to the study of sulcal formation from in-utero MR imaging of human fetal brain anatomy. Results show that the method detects differential growth of tissue layers adjacent to the cortical surface, particularly at sulcal locations, as early as 22 gestational weeks.

Bias field inconsistency correction of motion-scattered multislice MRI for improved 3D image reconstruction.

A common solution to clinical MR imaging in the presence of large anatomical motion is to use fast multislice 2D studies to reduce slice acquisition time and provide clinically usable slice data. Recently, techniques have been developed which retrospectively correct large scale 3D motion between individual slices allowing the formation of a geometrically correct 3D volume from the multiple slice stacks. One challenge, however, in the final reconstruction process is the possibility of varying intensity bias in the slice data, typically due to the motion of the anatomy relative to imaging coils. As a result, slices which cover the same region of anatomy at different times may exhibit different sensitivity. This bias field inconsistency can induce artifacts in the final 3D reconstruction that can impact both clinical interpretation of key tissue boundaries and the automated analysis of the data. Here we describe a framework to estimate and correct the bias field inconsistency in each slice collectively across all motion corrupted image slices. Experiments using synthetic and clinical data show that the proposed method reduces intensity variability in tissues and improves the distinction between key tissue types.

Growth trajectories of the human fetal brain tissues estimated from 3D reconstructed in utero MRI.

In the latter half of gestation (20-40 gestational weeks), human brain growth accelerates in conjunction with cortical folding and the deceleration of ventricular zone progenitor cell proliferation. These processes are reflected in changes in the volume of respective fetal tissue zones. Thus far, growth trajectories of the fetal tissue zones have been extracted primarily from 2D measurements on histological sections and magnetic resonance imaging (MRI). In this study, the volumes of major fetal zones-cortical plate (CP), subplate and intermediate zone (SP+IZ), germinal matrix (GMAT), deep gray nuclei (DG), and ventricles (VENT)--are calculated from automatic segmentation of motion-corrected, 3D reconstructed MRI. We analyzed 48 T2-weighted MRI scans from 39 normally developing fetuses in utero between 20.57 and 31.14 gestational weeks (GW). The supratentorial volume (STV) increased linearly at a rate of 15.22% per week. The SP+IZ (14.75% per week) and DG (15.56% per week) volumes increased at similar rates. The CP increased at a greater relative rate (18.00% per week), while the VENT (9.18% per week) changed more slowly. Therefore, CP increased as a fraction of STV and the VENT fraction declined. The total GMAT volume slightly increased then decreased after 25 GW. We did not detect volumetric sexual dimorphisms or total hemispheric volume asymmetries, which may emerge later in gestation. Further application of the automated fetal brain segmentation to later gestational ages will bridge the gap between volumetric studies of premature brain development and normal brain development in utero.

Intersection based motion correction of multislice MRI for 3-D in utero fetal brain image formation.

In recent years, postprocessing of fast multislice magnetic resonance imaging (MRI) to correct fetal motion has provided the first true 3-D MR images of the developing human brain in utero. Early approaches have used reconstruction based algorithms, employing a two-step iterative process, where slices from the acquired data are realigned to an approximate 3-D reconstruction of the fetal brain, which is then refined further using the improved slice alignment. This two step slice-to-volume process, although powerful, is computationally expensive in needing a 3-D reconstruction, and is limited in its ability to recover subvoxel alignment. Here, we describe an alternative approach which we term slice intersection motion correction (SIMC), that seeks to directly co-align multiple slice stacks by considering the matching structure along all intersecting slice pairs in all orthogonally planned slices that are acquired in clinical imaging studies. A collective update scheme for all slices is then derived, to simultaneously drive slices into a consistent match along their lines of intersection. We then describe a 3-D reconstruction algorithm that, using the final motion corrected slice locations, suppresses through-plane partial volume effects to provide a single high isotropic resolution 3-D image. The method is tested on simulated data with known motions and is applied to retrospectively reconstruct 3-D images from a range of clinically acquired imaging studies. The quantitative evaluation of the registration accuracy for the simulated data sets demonstrated a significant improvement over previous approaches. An initial application of the technique to studying clinical pathology is included, where the proposed method recovered up to 15 mm of translation and 30 degrees of rotation for individual slices, and produced full 3-D reconstructions containing clinically useful additional information not visible in the original 2-D slices.

Measures for characterizing directionality specific volume changes in TBM of brain growth.

Tensor based morphology (TBM) is a powerful approach to analyze local structural changes in brain anatomy. However, conventional scalar TBM methods are unable to present direction-specific analysis of volume changes required to model complex changes such as those during brain growth. In this paper, we describe novel TBM descriptors for studying direction-specific changes in a subject population which can be used in conjunction with scalar TBM to analyze local patterns in directionality of volume change during brain development. We illustrate the use of these methods by studying brain developmental patterns in fetuses. Results show that this approach detects early changes local growth that are related to the early stages of sulcal and gyral formation.

A spatio-temporal atlas of the human fetal brain with application to tissue segmentation.

Modeling and analysis of MR images of the early developing human brain is a challenge because of the transient nature of different tissue classes during brain growth. To address this issue, a statistical model that can capture the spatial variation of structures over time is needed. Here, we present an approach to building a spatio-temporal model of tissue distribution in the developing brain which can incorporate both developed tissues as well as transient tissue classes such as the germinal matrix by using constrained higher order polynomial models. This spatiotemporal model is created from a set of manual segmentations through groupwise registration and voxelwise non-linear modeling of tissue class membership, that allows us to represent the appearance as well as disappearance of the transient brain structures over time. Applying this model to atlas-based segmentation, we generate age-specific tissue probability maps and use them to initialize an EM segmentation of the fetal brain tissues. The approach is evaluated using clinical MR images of young fetuses with gestational ages ranging from 20.57 to 24.71 weeks. Results indicate improvement in performance of atlas-based EM segmentation provided by higher order temporal models that capture the variation of tissue occurrence over time.

Atlas-based segmentation of the germinal matrix from in utero clinical MRI of the fetal brain.

Recently developed techniques for reconstruction of high-resolution 3D images from fetal MR scans allows us to study the morphometry of developing brain tissues in utero. However, existing adult brain analysis methods cannot be directly applied as the anatomy of the fetal brain is significantly different in terms of geometry and tissue morphology. We describe an approach to atlas-based segmentation of the fetal brain with particular focus on the delineation of the germinal matrix, a transient structure related to brain growth. We segment 3D images reconstructed from in utero clinical MR scans and measure volumes of different brain tissue classes for a group of fetal subjects at gestational age 20.5-22.5 weeks. We also include a partial validation of the approach using manual tracing of the germinal matrix at different gestational ages.

Probabilistic framework for reliability analysis of information-theoretic CAD systems in mammography.

The purpose of this study is to develop and evaluate a probabilistic framework for reliability analysis of information-theoretic computer-assisted detection (IT-CAD) systems in mammography. The study builds upon our previous work on a feature-based reliability analysis technique tailored to traditional CAD systems developed with a supervised learning scheme. The present study proposes a probabilistic framework to facilitate application of the reliability analysis technique for knowledge-based CAD systems that are not feature-based. The study was based on an information-theoretic CAD system developed for detection of masses in screening mammograms from the Digital Database for Screening Mammography (DDSM). The experimental results reveal that the query-specific reliability estimate provided by the proposed probabilistic framework is an accurate predictor of CAD performance for the query case. It can also be successfully applied as a base for stratification of CAD predictions into clinically meaningful reliability groups (i.e., HIGH, MEDIUM, and LOW). Based on a leave-one-out sampling scheme and ROC analysis, the study demonstrated that the diagnostic performance of the IT-CAD is significantly higher for cases with HIGH reliability (A(z) = 0.92 +/- 0.03) than for those stratified as MEDIUM (A(z) = 0.84 +/- 0.02) or LOW reliability predictions (A(z) = 0.78 +/- 0.02).