Faculty Bibliography

The corpus callosum (CC) is the most important interhemispheric white matter (WM) structure composed of several anatomically and functionally distinct WM tracts. Resolving these tracts is a challenge since the callosum appears relatively homogenous in conventional structural imaging. Commonly used callosal parcellation methods such as the Hofer/Frahm scheme rely on rigid geometric guidelines to separate the substructures that are limited to consider individual variation. Here we present a novel subject-specific and microstructurally-informed method for callosal parcellation based on axonal water fraction (ƒ) known as a diffusion metric reflective of axon caliber and density. We studied 30 healthy subjects from the Human Connectome Project (HCP) dataset with multi-shell diffusion MRI. The biophysical parameter ƒ was derived from compartment-specific WM modeling. Inflection points were identified where there were concavity changes in ƒ across the CC to delineate callosal subregions. We observed relatively higher ƒ in anterior and posterior areas consisting of a greater number of small diameter fibers and lower ƒ in posterior body areas of the CC consisting of a greater number of large diameter fibers. Based on degree of change in ƒ along the callosum, seven callosal subregions can be consistently delineated for each individual. We observe that ƒ can capture differences in underlying tissue microstructures and seven subregions can be identified across CC. Therefore, this method provides microstructurally informed callosal parcellation in a subject-specific way, allowing for more accurate analysis in the corpus callosum.

PURPOSE/OBJECTIVE:Repeated head impacts (RHI) without concussion may cause long-term sequelae. A growing array of diffusion MRI metrics exist, both empiric and modeled and it is hard to know which are potentially important biomarkers. Common conventional statistical methods fail to consider interactions between metrics and rely on group-level comparisons. This study uses a classification pipeline as a means towards identifying important diffusion metrics associated with subconcussive RHI. METHODS:36 collegiate contact sport athletes and 45 non-contact sport controls from FITBIR CARE were included. Regional/whole brain WM statistics were computed from 7 diffusion metrics. Wrapper-based feature selection was applied to 5 classifiers representing a range of learning capacities. Best 2 classifiers were interpreted to identify the most RHI-related diffusion metrics. RESULTS:Mean diffusivity (MD) and mean kurtosis (MK) are found to be the most important metrics for discriminating between athletes with and without RHI exposure history. Regional features outperformed global statistics. Linear approaches outperformed non-linear approaches with good generalizability (test AUC 0.80-0.81). CONCLUSION/CONCLUSIONS:) are found to be the most influential metrics. This work provides proof of concept that applying such approach to small, multidimensional dataset can be successful given attention to optimizing learning capacity without overfitting and serves an example of methods that lead to better understanding of the myriad of diffusion metrics as they relate to injury and disease.

The thalamus consists of several functionally distinct nuclei, some of which serve as targets for functional neurosurgery. Visualization of such nuclei is a major challenge due to their low signal contrast on conventional imaging. We introduce MR susceptibility imaging with a short TE, leveraging susceptibility differences among thalamic nuclei, to automatically delineate 15 thalamic subregions. The technique has the potential to enable direct targeting of thalamic nuclei for functional neurosurgical guidance.

Quantitative, volumetric analysis of Magnetic Resonance Imaging (MRI) is a fundamental way researchers study the brain in a host of neurological conditions including normal maturation and aging. Despite the availability of open-source brain segmentation software, widespread clinical adoption of volumetric analysis has been hindered due to processing times and reliance on manual corrections. Here, we extend the use of deep learning models from proof-of-concept, as previously reported, to present a comprehensive segmentation of cortical and deep gray matter brain structures matching the standard regions of aseg+ aparc included in the commonly used open-source tool, Freesurfer. The work presented here provides a real-life, rapid deep learning-based brain segmentation tool to enable clinical translation as well as research application of quantitative brain segmentation. The advantages of the presented tool include short (~ 1 minute) processing time and improved segmentation quality. This is the first study to perform quick and accurate segmentation of 102 brain regions based on the surface-based protocol (DMK protocol), widely used by experts in the field. This is also the first work to include an expert reader study to assess the quality of the segmentation obtained using a deep-learning-based model. We show the superior performance of our deep-learning-based models over the traditional segmentation tool, Freesurfer. We refer to the proposed deep learning-based tool as DARTS (DenseUnet-based Automatic Rapid Tool for brain Segmentation)

In this work, we propose bag of adversarial features (BAF) for identifying mild traumatic brain injury (MTBI) patients from their diffusion magnetic resonance images (MRI) (obtained within one month of injury) by incorporating unsupervised feature learning techniques. MTBI is a growing public health problem with an estimated incidence of over 1.7 million people annually in US. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. Unlike most of previous works, which use hand-crafted features extracted from different parts of brain for MTBI classification, we employ feature learning algorithms to learn more discriminative representation for this task. A major challenge in this field thus far is the relatively small number of subjects available for training. This makes it difficult to use an end-to-end convolutional neural network to directly classify a subject from MR images. To overcome this challenge, we first apply an adversarial auto-encoder (with convolutional structure) to learn patch-level features, from overlapping image patches extracted from different brain regions. We then aggregate these features through a bag-of-word approach. We perform an extensive experimental study on a dataset of 227 subjects (including 109 MTBI patients, and 118 age and sex matched healthy controls), and compare the bag-of-deep-features with several previous approaches. Our experimental results show that the BAF significantly outperforms earlier works relying on the mean values of MR metrics in selected brain regions.

BACKGROUND AND PURPOSE/OBJECTIVE:Working memory impairment is one of the most troubling and persistent symptoms after mild traumatic brain injury (MTBI). Here we investigate how working memory deficits relate to detectable WM microstructural injuries to discover robust biomarkers that allow early identification of patients with MTBI at the highest risk of working memory impairment. MATERIALS AND METHODS/METHODS:Multi-shell diffusion MR imaging was performed on a 3T scanner with 5 b-values. Diffusion metrics of fractional anisotropy, diffusivity and kurtosis (mean, radial, axial), and WM tract integrity were calculated. Auditory-verbal working memory was assessed using the Wechsler Adult Intelligence Scale, 4th ed, subtests: 1) Digit Span including Forward, Backward, and Sequencing; and 2) Letter-Number Sequencing. We studied 19 patients with MTBI within 4 weeks of injury and 20 healthy controls. Tract-Based Spatial Statistics and ROI analyses were performed to reveal possible correlations between diffusion metrics and working memory performance, with age and sex as covariates. RESULTS:= .04), mainly present in the right superior longitudinal fasciculus, which was not observed in healthy controls. Patients with MTBI also appeared to lose the normal associations typically seen in fractional anisotropy and axonal water fraction with Letter-Number Sequencing. Tract-Based Spatial Statistics results also support our findings. CONCLUSIONS:Differences between patients with MTBI and healthy controls with regard to the relationship between microstructure measures and working memory performance may relate to known axonal perturbations occurring after injury.

Mild traumatic brain injury is a growing public health problem with an estimated incidence of over 1.7 million people annually in US. Diagnosis is based on clinical history and symptoms, and accurate, concrete measures of injury are lacking. This work aims to directly use diffusion MR images obtained within one month of trauma to detect injury, by incorporating deep learning techniques. To overcome the challenge due to limited training data, we describe each brain region using the bag of word representation, which specifies the distribution of representative patch patterns. We apply a convolutional auto-encoder to learn the patch-level features, from overlapping image patches extracted from the MR images, to learn features from diffusion MR images of brain using an unsupervised approach. Our experimental results show that the bag of word representation using patch level features learnt by the auto encoder provides similar performance as that using the raw patch patterns, both significantly outperform earlier work relying on the mean values of MR metrics in selected brain regions.

We seek to elucidate the underlying pathophysiology of injury sustained after mild traumatic brain injury (MTBI) using multi-shell diffusion MRI, deriving compartment-specific WM tract integrity (WMTI) metrics. WMTI allows a more biophysical interpretation of WM changes by describing microstructural characteristics in both intra- and extra-axonal environments. Thirty-two patients with MTBI within 30 days of injury and twenty-one age- and sex-matched controls were imaged on a 3T MR scanner. Multi-shell diffusion acquisition was performed with 5 b-values (250 - 2500 s/mm²) along 6 - 60 diffusion encoding directions. Tract-based spatial statistics (TBSS) was used with family-wise error (FWE) correction for multiple comparisons. TBSS results demonstrate focally lower intra-axonal diffusivity (D_axon) in MTBI patients in the splenium of the corpus callosum (sCC) (p < 0.05, FWE-corrected). The Area Under the Curve (AUC)-value for was 0.76 with low sensitivity of 46.9%, but 100% specificity. These results indicate that D_axon may be a useful imaging biomarker highly specific for MTBI-related WM injury. The observed decrease in D_axon suggests restriction of the diffusion along the axons occurring shortly after injury.

Working memory is a complex cognitive process at the intersection of sensory processing, learning, and short-term memory and also has a general executive attention component. Impaired working memory is associated with a range of neurological and psychiatric disorders, but very little is known about how working memory relates to underlying white matter (WM) microstructure. In this study, we investigate the association between WM microstructure and performance on working memory tasks in healthy adults (right-handed, native English speakers). We combine compartment specific WM tract integrity (WMTI) metrics derived from multi-shell diffusion MRI as well as diffusion tensor/kurtosis imaging (DTI/DKI) metrics with Wechsler Adult Intelligence Scale-Fourth Edition (WAIS-IV) subtests tapping auditory working memory. WMTI is a novel tool that helps us describe the microstructural characteristics in both the intra- and extra-axonal environments of WM such as axonal water fraction (AWF), intra-axonal diffusivity, extra-axonal axial and radial diffusivities, allowing a more biophysical interpretation of WM changes. We demonstrate significant positive correlations between AWF and letter-number sequencing (LNS), suggesting that higher AWF with better performance on complex, more demanding auditory working memory tasks goes along with greater axonal volume and greater myelination in specific regions, causing efficient and faster information process.