SCI Publications

As the capabilities of convolutional neural networks (CNNs) for image classification tasks have advanced, interest in applying deep learning techniques for determining the natural and anthropogenic origins of uranium ore concentrates (UOCs) and other unknown nuclear materials by their surface morphology characteristics has grown. But before CNNs can join the nuclear forensics toolbox along more traditional analytical techniques – such as scanning electron microscopy (SEM), X-ray diffractometry, mass spectrometry, radiation counting, and any number of spectroscopic methods – a deeper understanding of “black box” image classification will be required. This paper explores uncertainty quantification for convolutional neural networks and their ability to generalize to out-of-distribution (OOD) image data sets. For prediction uncertainty, Monte Carlo (MC) dropout and random image crops as variational inference techniques are implemented and characterized. Convolutional neural networks and classifiers using image features from unsupervised vector-quantized variational autoencoders (VQ-VAE) are trained using SEM images of pure, unaged, unmixed uranium ore concentrates considered “unperturbed.” OOD data sets are developed containing perturbations from the training data with respect to the chemical and physical properties of the UOCs or data collection parameters; predictions made on the perturbation sets identify where significant shortcomings exist in the current training data and techniques used to develop models for classifying uranium process history, and provides valuable insights into how datasets and classification models can be improved for better generalizability to out-of-distribution examples.

Identifying the precise composition of a mixed material is important in various applications. For instance, in nuclear forensics analysis, knowing the process history of unknown or illicitly trafficked nuclear materials when they are discovered is desirable to prevent future losses or theft of material from the processing facilities. Motivated by this open problem, we describe a novel machine learning approach to determine the composition of a mixture from SEM images. In machine learning, the training data distribution should reflect the distribution of the data the model is expected to make predictions for, which can pose a hurdle. However, a key advantage of our proposed framework is that it requires reference images of pure material samples only. Removing the need for reference samples of various mixed material compositions reduces the time and monetary cost associated with reference sample preparation and imaging. Moreover, our proposed framework can determine the composition of a mixture composed of chemically similar materials, whereas other elemental analysis tools such as powder X-ray diffraction (p-XRD) have trouble doing so. For example, p-XRD is unable to discern mixtures composed of triuranium octoxide (U3O8) synthesized from different synthetic routes such as uranyl peroxide (UO4) and ammonium diuranate (ADU) [1]. In contrast, our proposed framework can easily determine the composition of uranium oxides mixture synthesized from different synthetic routes, as we illustrate in the experiments.

Determining the composition of a mixed material is an open problem that has attracted the interest of researchers in many fields. In our recent work, we proposed a novel approach to determine the composition of a mixed material using convolutional neural networks (CNNs). In machine learning, a model “learns” a specific task for which it is designed through data. Hence, obtaining a dataset of mixed materials is required to develop CNNs for the task of estimating the composition. However, the proposed method instead creates the synthetic data of mixed materials generated from using only images of pure materials present in those mixtures. Thus, it eliminates the prohibitive cost and tedious process of collecting images of mixed materials. The motivation for this study is to provide mathematical details of the proposed approach in addition to extensive experiments and analyses. We examine the approach on two datasets to demonstrate the ease of extending the proposed approach to any mixtures. We perform experiments to demonstrate that the proposed approach can accurately determine the presence of the materials, and sufficiently estimate the precise composition of a mixed material. Moreover, we provide analyses to strengthen the validation and benefits of the proposed approach.

Many tools, such as mass spectrometry, X-ray diffraction, X-ray fluorescence, ion chromatography, etc., are currently available to scientists investigating interdicted nuclear material. These tools provide an analysis of physical, chemical, or isotopic characteristics of the seized material to identify its origin. In this study, a novel technique that characterizes physical attributes is proposed to provide insight into the processing route of unknown uranium ore concentrates (UOCs) and their calcination products. In particular, this study focuses on the characteristics of the surface structure captured in scanning electron microscopy (SEM) images at different magnification levels. Twelve common commercial processing routes of UOCs and their calcination products are investigated. Multiple-input single-output (MISO) convolution neural networks (CNNs) are implemented to differentiate the processing routes. The proposed technique can determine the processing route of a given sample in under a second running on a graphics processing unit (GPU) with an accuracy of more than 95%. The accuracy and speed of this proposed technique enable nuclear scientists to provide the preliminary identification results of interdicted material in a short time period. Furthermore, this proposed technique uses a predetermined set of magnifications, which in turn eliminates the human bias in selecting the magnification during the image acquisition process.

The morphological effect of impurities on α-U₃O₈ has been investigated. This study provides the first evidence that the presence of impurities can alter nuclear material morphology, and these changes can be quantified to aid in revealing processing history. Four elements: Ca, Mg, V, and Zr were implemented in the uranyl peroxide synthesis route and studied individually within the α-U₃O₈. Six total replicates were synthesized, and replicates 1–3 were filtered and washed with Millipore water (18.2 MΩ) to remove any residual nitrates. Replicates 4–6 were filtered but not washed to determine the amount of impurities removed during washing. Inductively coupled plasma mass spectrometry (ICP-MS) was employed at key points during the synthesis to quantify incorporation of the impurity. Each sample was characterized using powder X-ray diffraction (p-XRD), high-resolution scanning electron microscopy (HRSEM), and SEM with energy dispersive X-ray spectroscopy (SEM-EDS). p-XRD was utilized to evaluate any crystallographic changes due to the impurities; HRSEM imagery was analyzed with Morphological Analysis for MAterials (MAMA) software and machine learning classification for quantification of the morphology; and SEM-EDS was utilized to locate the impurity within the α-U₃O₈. All samples were found to be quantifiably distinguishable, further demonstrating the utility of quantitative morphology as a signature for the processing history of nuclear material.

In the present study, surface morphological differences of mixtures of triuranium octoxide (U₃O₈), synthesized from uranyl peroxide (UO₄) and ammonium diuranate (ADU), were investigated. The purity of each sample was verified using powder X-ray diffractometry (p-XRD), and scanning electron microscopy (SEM) images were collected to identify unique morphological features. The U₃O₈ from ADU and UO₄ was found to be unique. Qualitatively, both particles have similar features being primarily circular in shape. Using the morphological analysis of materials (MAMA) software, particle shape and size were quantified. UO₄ was found to produce U₃O₈ particles three times the area of those produced from ADU. With the starting morphologies quantified, U₃O₈ samples from ADU and UO₄ were physically mixed in known quantities. SEM images were collected of the mixed samples, and the MAMA software was used to quantify particle attributes. As U₃O₈ particles from ADU were unique from UO₄, the composition of the mixtures could be quantified using SEM imaging coupled with particle analysis. This provides a novel means of quantifying processing histories of mixtures of uranium oxides. Machine learning was also used to help further quantify characteristics in the image database through direct classification and particle segmentation using deep learning techniques based on Convolutional Neural Networks (CNN). It demonstrates that these techniques can distinguish the mixtures with high accuracy as well as showing significant differences in morphology between the mixtures. Results from this study demonstrate the power of quantitative morphological analysis for determining the processing history of nuclear materials.

Knowledge of what spatial elements of medical images deep learning methods use as evidence is important for model interpretability, trustiness, and validation. There is a lack of such techniques for models in regression tasks. We propose a method, called visualization for regression with a generative adversarial network (VR-GAN), for formulating adversarial training specifically for datasets containing regression target values characterizing disease severity. We use a conditional generative adversarial network where the generator attempts to learn to shift the output of a regressor through creating disease effect maps that are added to the original images. Meanwhile, the regressor is trained to predict the original regression value for the modified images. A model trained with this technique learns to provide visualization for how the image would appear at different stages of the disease. We analyze our method in a dataset of chest x-rays associated with pulmonary function tests, used for diagnosing chronic obstructive pulmonary disease (COPD). For validation, we compute the difference of two registered x-rays of the same patient at different time points and correlate it to the generated disease effect map. The proposed method outperforms a technique based on classification and provides realistic-looking images, making modifications to images following what radiologists usually observe for this disease. Implementation code is available athttps://github.com/ricbl/vrgan.

The brain undergoes rapid development during early childhood as a series of biophysical and chemical processes occur, which can be observed in magnetic resonance (MR) images as a change over time of white matter intensity relative to gray matter. Such a contrast change manifests in specific patterns in different imaging modalities, suggesting that brain maturation is encoded by appearance changes in multi-modal MRI. In this paper, we explore the patterns of early brain growth encoded by multi-modal contrast changes in a longitudinal study of children. For a given modality, contrast is measured by comparing histograms of intensity distributions between white and gray matter. Multivariate non-linear mixed effects (NLME) modeling provides subject-specific as well as population growth trajectories which accounts for contrast from multiple modalities. The multivariate NLME procedure and resulting non-linear contrast functions enable the study of maturation in various regions of interest. Our analysis of several brain regions in a study of 70 healthy children reveals a posterior to anterior pattern of timing of maturation in the major lobes of the cerebral cortex, with posterior regions maturing earlier than anterior regions. Furthermore, we find significant differences between maturation rates between males and females.

Background
Restricted and repetitive behaviors are defining features of autism spectrum disorder (ASD). Under revised diagnostic criteria for ASD, this behavioral domain now includes atypical responses to sensory stimuli. To date, little is known about the neural circuitry underlying these features of ASD early in life.

Methods
Longitudinal diffusion tensor imaging data were collected from 217 infants at high familial risk for ASD. Forty-four of these infants were diagnosed with ASD at age 2. Targeted cortical, cerebellar, and striatal white matter pathways were defined and measured at ages 6, 12, and 24 months. Dependent variables included the Repetitive Behavior Scale-Revised and the Sensory Experiences Questionnaire.

Results
Among children diagnosed with ASD, repetitive behaviors and sensory response patterns were strongly correlated, even when accounting for developmental level or social impairment. Longitudinal analyses indicated that the genu and cerebellar pathways were significantly associated with both repetitive behaviors and sensory responsiveness but not social deficits. At age 6 months, fractional anisotropy in the genu significantly predicted repetitive behaviors and sensory responsiveness at age 2. Cerebellar pathways significantly predicted later sensory responsiveness. Exploratory analyses suggested a possible disordinal interaction based on diagnostic status for the association between fractional anisotropy and repetitive behavior.

Conclusions
Our findings suggest that restricted and repetitive behaviors contributing to a diagnosis of ASD at age 2 years are associated with structural properties of callosal and cerebellar white matter pathways measured during infancy and toddlerhood. We further identified that repetitive behaviors and unusual sensory response patterns co-occur and share common brain-behavior relationships. These results were strikingly specific given the absence of association between targeted pathways and social deficits.

Diffusion-weighted (DW) MRI has become a widely adopted imaging modality to reveal the underlying brain connectivity. Long acquisition times and/or non-cooperative patients increase the chances of motion-related artifacts. Whereas slow bulk motion results in inter-gradient misalignment which can be handled via retrospective motion correction algorithms, fast bulk motion usually affects data during the application of a single diffusion gradient causing signal dropout artifacts. Common practices opt to discard gradients bearing signal attenuation due to the difficulty of their retrospective correction, with the disadvantage to lose full gradients for further processing. Nonetheless, such attenuation might only affect limited number of slices within a gradient volume. Q-space resampling has recently been proposed to recover corrupted slices while saving gradients for subsequent reconstruction. However, few corrupted gradients are implicitly assumed which might not hold in case of scanning unsedated infants or patients in pain. In this paper, we propose to adopt recent advances in compressive sensing based reconstruction of the diffusion orientation distribution functions (ODF) with under sampled measurements to resample corrupted slices. We make use of Simple Harmonic Oscillator based Reconstruction and Estimation (SHORE) basis functions which can analytically model ODF from arbitrary sampled signals. We demonstrate the impact of the proposed resampling strategy compared to state-of-art resampling and gradient exclusion on simulated intra-gradient motion as well as samples from real DWI data.

The quantification of local surface morphology in the human cortex is important for examining population differences as well as developmental changes in neurodegenerative or neurodevelopmental disorders. We propose a novel cortical shape measure, referred to as the 'shape complexity index' (SCI), that represents localized shape complexity as the difference between the observed distributions of local surface topology, as quantified by the shape index (SI) measure, to its best fitting simple topological model within a given neighborhood. We apply a relatively small, adaptive geodesic kernel to calculate the SCI. Due to the small size of the kernel, the proposed SCI measure captures fine differences of cortical shape. With this novel cortical feature, we aim to capture comparatively small local surface changes that capture a) the widening versus deepening of sulcal and gyral regions, as well as b) the emergence and development of secondary and tertiary sulci. Current cortical shape measures, such as the gyrification index (GI) or intrinsic curvature measures, investigate the cortical surface at a different scale and are less well suited to capture these particular cortical surface changes. In our experiments, the proposed SCI demonstrates higher complexity in the gyral/sulcal wall regions, lower complexity in wider gyral ridges and lowest complexity in wider sulcal fundus regions. In early postnatal brain development, our experiments show that SCI reveals a pattern of increased cortical shape complexity with age, as well as sexual dimorphisms in the insula, middle cingulate, parieto-occipital sulcal and Broca's regions. Overall, sex differences were greatest at 6months of age and were reduced at 24months, with the difference pattern switching from higher complexity in males at 6months to higher complexity in females at 24months. This is the first study of longitudinal, cortical complexity maturation and sex differences, in the early postnatal period from 6 to 24months of age with fine scale, cortical shape measures. These results provide information that complement previous studies of gyrification index in early brain development.

PURPOSE:
To evaluate the performance of an edge-based registration technique in correcting for respiratory motion artifacts in magnetic resonance renographic (MRR) data and to examine the efficiency of a semiautomatic software package in processing renographic data from a cohort of clinical patients.

MATERIALS AND METHODS:
The developed software incorporates an image-registration algorithm based on the generalized Hough transform of edge maps. It was used to estimate glomerular filtration rate (GFR), renal plasma flow (RPF), and mean transit time (MTT) from 36 patients who underwent free-breathing MRR at 3T using saturation-recovery turbo-FLASH. The processing time required for each patient was recorded. Renal parameter estimates and model-fitting residues from the software were compared to those from a previously reported technique. Interreader variability in the software was quantified by the standard deviation of parameter estimates among three readers. GFR estimates from our software were also compared to a reference standard from nuclear medicine.

RESULTS:
The time taken to process one patient's data with the software averaged 12 ± 4 minutes. The applied image registration effectively reduced motion artifacts in dynamic images by providing renal tracer-retention curves with significantly smaller fitting residues (P < 0.01) than unregistered data or data registered by the previously reported technique. Interreader variability was less than 10% for all parameters. GFR estimates from the proposed method showed greater concordance with reference values (P < 0.05).

CONCLUSION:
These results suggest that the proposed software can process MRR data efficiently and accurately. Its incorporated registration technique based on the generalized Hough transform effectively reduces respiratory motion artifacts in free-breathing renographic acquisitions. J. Magn. Reson. Imaging 2015.

Purpose
Statistical shape analysis of anatomical structures plays an important role in many medical image analysis applications such as understanding the structural changes in anatomy in various stages of growth or disease. Establishing accurate correspondence across object populations is essential for such statistical shape analysis studies.

Methods
In this paper, we present an entropy-based correspondence framework for computing point-based correspondence among populations of surfaces in a groupwise manner. This robust framework is parameterization-free and computationally efficient. We review the core principles of this method as well as various extensions to deal effectively with surfaces of complex geometry and application-driven correspondence metrics.

Results
We apply our method to synthetic and biological datasets to illustrate the concepts proposed and compare the performance of our framework to existing techniques.

Conclusions
Through the numerous extensions and variations presented here, we create a very flexible framework that can effectively handle objects of various topologies, multi-object complexes, open surfaces, and objects of complex geometry such as high-curvature regions or extremely thin features.

Prenatal drug exposure, particularly prenatal cocaine exposure (PCE), incurs great public and scientific interest because of its associated neurodevelopmental consequences. However, the neural underpinnings of PCE remain essentially uncharted, and existing studies in school-aged children and adolescents are confounded greatly by postnatal environmental factors. In this study, leveraging a large neonate sample (N = 152) and non-invasive resting-state functional magnetic resonance imaging, we compared human infants with PCE comorbid with other drugs (such as nicotine, alcohol, marijuana, and antidepressant) with infants with similar non-cocaine poly drug exposure and drug-free controls. We aimed to characterize the neural correlates of PCE based on functional connectivity measurements of the amygdala and insula at the earliest stage of development. Our results revealed common drug exposure-related connectivity disruptions within the amygdala–frontal, insula–frontal, and insula–sensorimotor circuits. Moreover, a cocaine-specific effect was detected within a subregion of the amygdala–frontal network. This pathway is thought to play an important role in arousal regulation, which has been shown to be irregular in PCE infants and adolescents. These novel results provide the earliest human-based functional delineations of the neural-developmental consequences of prenatal drug exposure and thus open a new window for the advancement of effective strategies aimed at early risk identification and intervention.

The association between developmental trajectories of language-related white matter fiber pathways from 6 to 24 months of age and individual differences in language production at 24 months of age was investigated. The splenium of the corpus callosum, a fiber pathway projecting through the posterior hub of the default mode network to occipital visual areas, was examined as well as pathways implicated in language function in the mature brain, including the arcuate fasciculi, uncinate fasciculi, and inferior longitudinal fasciculi. The hypothesis that the development of neural circuitry supporting domain-general orienting skills would relate to later language performance was tested in a large sample of typically developing infants. The present study included 77 infants with diffusion weighted MRI scans at 6, 12 and 24 months and language assessment at 24 months. The rate of change in splenium development varied significantly as a function of language production, such that children with greater change in fractional anisotropy (FA) from 6 to 24 months produced more words at 24 months. Contrary to findings from older children and adults, significant associations between language production and FA in the arcuate, uncinate, or left inferior longitudinal fasciculi were not observed. The current study highlights the importance of tracing brain development trajectories from infancy to fully elucidate emerging brain–behavior associations while also emphasizing the role of the splenium as a key node in the structural network that supports the acquisition of spoken language.

Numerous brain imaging studies indicate that the corpus callosum is smaller in older children and adults with autism spectrum disorder. However, there are no published studies examining the morphological development of this connective pathway in infants at-risk for the disorder. Magnetic resonance imaging data were collected from 270 infants at high familial risk for autism spectrum disorder and 108 low-risk controls at 6, 12 and 24 months of age, with 83% of infants contributing two or more data points. Fifty-seven children met criteria for ASD based on clinical-best estimate diagnosis at age 2 years. Corpora callosa were measured for area, length and thickness by automated segmentation. We found significantly increased corpus callosum area and thickness in children with autism spectrum disorder starting at 6 months of age. These differences were particularly robust in the anterior corpus callosum at the 6 and 12 month time points. Regression analysis indicated that radial diffusivity in this region, measured by diffusion tensor imaging, inversely predicted thickness. Measures of area and thickness in the first year of life were correlated with repetitive behaviours at age 2 years. In contrast to work from older children and adults, our findings suggest that the corpus callosum may be larger in infants who go on to develop autism spectrum disorder. This result was apparent with or without adjustment for total brain volume. Although we did not see a significant interaction between group and age, cross-sectional data indicated that area and thickness differences diminish by age 2 years. Regression data incorporating diffusion tensor imaging suggest that microstructural properties of callosal white matter, which includes myelination and axon composition, may explain group differences in morphology.

Post-acquisition motion correction is widely performed in diffusionweighted imaging (DWI) to guarantee voxel-wise correspondence between DWIs. Whereas this is primarily motivated to save as many scans as possible if corrupted by motion, users do not fully understand the consequences of different types of interpolation schemes on the final analysis. Nonetheless, interpolation might increase the partial volume effect while not preserving the volume of the diffusion profile, whereas excluding poor DWIs may affect the ability to resolve crossing fibers especially with small separation angles. In this paper, we investigate the effect of interpolating diffusion measurements as well as the elimination of bad directions on the reconstructed fiber orientation diffusion functions and on the estimated fiber orientations. We demonstrate such an effect on synthetic and real HARDI datasets. Our experiments demonstrate that the effect of interpolation is more significant with small fibers separation angles where the exclusion of motion-corrupted directions decreases the ability to resolve such crossing fibers.

Keywords: Diffusion MRI, HARDI, motion correction, interpolation

Diffusion-weighted imaging (DWI) is known to be prone to artifacts related to motion originating from subject movement, cardiac pulsation and breathing, but also to mechanical issues such as table vibrations. Given the necessity for rigorous quality control and motion correction, users are often left to use simple heuristics to select correction schemes, which involves simple qualitative viewing of the set of DWI data, or the selection of transformation parameter thresholds for detection of motion outliers. The scientific community offers strong theoretical and experimental work on noise reduction and orientation distribution function (ODF) reconstruction techniques for HARDI data, where postacquisition motion correction is widely performed, e.g., using the open-source DTIprep software (Oguz et al., 2014), FSL (the FMRIB Software Library) (Jenkinson et al., 2012) or TORTOISE ( Pierpaoli et al. , 2010). Nonetheless, effects and consequences of the selection of motion correction schemes on the final analysis, and the eventual risk of introducing confounding factors when comparing populations, are much less known and far beyond simple intuitive guessing. Hence, standard users lack clear guidelines and recommendations in practical settings. This paper reports a comprehensive evaluation framework to systematically assess the outcome of different motion correction choices commonly used by the scientific community on different DWI-derived measures. We make use of human brain HARDI data from a well-controlled motion experiment to simulate various degrees of motion corruption and noise contamination. Choices for correction include exclusion/scrubbing or registration of motion corrupted directions with different choices of interpolation, as well as the option of interpolation of all directions. The comparative evaluation is based on a study of the impact of motion correction using four metrics that quantify (1) similarity of fiber orientation distribution functions (fODFs), (2) deviation of local fiber orientations, (3) global brain connectivity via Graph Diffusion Distance (GDD) and (4) the reproducibility of prominent and anatomically defined fiber tracts. Effects of various motion correction choices are systematically explored and illustrated, leading to a general conclusion of discouraging users from setting ad-hoc thresholds on the estimated motion parameters beyond which volumes are claimed to be corrupted.

Prenatal cocaine exposure (PCE) is related to subtle deficits in cognitive and behavioral function in infancy, childhood and adolescence. Very little is known about the effects of in utero PCE on early brain development that may contribute to these impairments. The purpose of this study was to examine brain structural differences in infants with and without PCE. We conducted MRI scans of newborns (mean age = 5 weeks) to determine cocaine's impact on early brain structural development. Subjects were three groups of infants: 33 with PCE co-morbid with other drugs, 46 drug-free controls and 40 with prenatal exposure to other drugs (nicotine, alcohol, marijuana, opiates, SSRIs) but without cocaine. Infants with PCE exhibited lesser total gray matter (GM) volume and greater total cerebral spinal fluid (CSF) volume compared with controls and infants with non-cocaine drug exposure. Analysis of regional volumes revealed that whole brain GM differences were driven primarily by lesser GM in prefrontal and frontal brain regions in infants with PCE, while more posterior regions (parietal, occipital) did not differ across groups. Greater CSF volumes in PCE infants were present in prefrontal, frontal and parietal but not occipital regions. Greatest differences (GM reduction, CSF enlargement) in PCE infants were observed in dorsal prefrontal cortex. Results suggest that PCE is associated with structural deficits in neonatal cortical gray matter, specifically in prefrontal and frontal regions involved in executive function and inhibitory control. Longitudinal study is required to determine whether these early differences persist and contribute to deficits in cognitive functions and enhanced risk for drug abuse seen at school age and in later life.

Altered renal function commonly affects patients with cirrhosis, a consequence of chronic liver disease. From lowdose contrast material-enhanced magnetic resonance (MR) renography, we can estimate the Glomerular Filtration Rate (GFR), an important parameter to assess renal function. Two-dimensional MR images are acquired every 2 seconds for approximately 5 minutes during free breathing, which results in a dynamic series of 140 images representing kidney filtration over time. This specific acquisition presents dynamic contrast changes but is also challenged by organ motion due to breathing. Rather than use conventional image registration techniques, we opted for an alternative method based on object detection. We developed a novel analysis framework available under a stand-alone toolkit to efficiently register dynamic kidney series, manually select regions of interest, visualize the concentration curves for these ROIs, and fit them into a model to obtain GFR values. This open-source cross-platform application is written in C++, using the Insight Segmentation and Registration Toolkit (ITK) library, and QT4 as a graphical user interface.