Augmented surgical decision-making for glioblastoma: integrating AI tools into education and practice

Surgical decision-making for glioblastoma poses significant challenges due to its complexity and variability. This study investigates the potential of artificial intelligence (AI) tools in improving "decision-making processes" for glioblastoma surgery. A systematic review of literature identified 10 relevant studies, primarily focused on predicting resectability and surgery-related neurological outcomes. AI tools, especially rooted in radiomics and connectomics, exhibited promise in predicting resection extent through precise tumor segmentation and tumor-network relationships. However, they demonstrated limited effectiveness in predicting postoperative neurological due to dynamic and less quantifiable nature of patient-related factors. Recognizing these challenges, including limited datasets and the interpretability requirement in medical applications, underscores the need for standardization, algorithm optimization, and addressing variability in model performance and then further validation in clinical settings. While AI holds potential, it currently does not possess the capacity to emulate the nuanced decision-making process utilized by experienced neurosurgeons in the comprehensive approach to glioblastoma surgery.

Bilateral focused ultrasound medial thalamotomies for trigeminal neuropathic pain: a randomized controlled study

OBJECTIVE

Medial thalamotomy has been shown to benefit patients with neuropathic pain, but widespread adoption of this procedure has been limited by reporting of clinical outcomes in studies without a control group. This study aimed to minimize confounders associated with medial thalamotomy for treating chronic pain by using modern MRI-guided stereotactic lesioning and a rigorous clinical design.

METHODS

This prospective, double-blinded, randomized controlled trial in 10 patients with trigeminal neuropathic pain used sham procedures as controls. Participants underwent assessments by a pain psychologist and pain management clinician, including use of the following measures: the Numeric Pain Rating Scale (NPRS); patient-reported outcome measures; and patient's impression of improvement at baseline, 1 day, 1 week, 1 month, and 3 months postprocedure. Patients in the treated group underwent bilateral focused ultrasound (FUS) medial thalamotomy targeting the central lateral nucleus. Patients in the control group underwent sham procedures with energy output disabled. The primary efficacy outcome measure was between-group differences in pain intensity (using the NPRS) at baseline and at 3 months postprocedure. Adverse events were measured for safety and included MRI analysis. Exploratory measures of connectivity and metabolism were analyzed using diffusion tensor imaging, functional MRI, and PET, respectively.

RESULTS

There were no serious complications from the FUS procedures. MRI confirmed bilateral medial thalamic ablations. There was no significant improvement in pain intensity from baseline to 3 months, either for patients undergoing FUS medial thalamotomy or for sham controls; and the between-group change in NPRS score as the primary efficacy outcome measure was not significantly different. Patient-reported outcome assessments demonstrated improvement (i.e., a decrease) only in pain interference with enjoyment of life at 3 months. There was a perception of benefit at 1 week, but only for patients treated with FUS and not for the sham cohort. Advanced neuroimaging showed that these medial thalamic lesions altered structural connectivity with the postcentral gyrus and demonstrated a trend toward hypometabolism in the insula and amygdala.

CONCLUSIONS

This randomized controlled trial of bilateral FUS medial thalamotomy did not reduce the intensity of trigeminal neuropathic pain, although it should be noted that the ability to estimate the magnitude of treatment effects is limited by the small cohort.

QUANTIFYING HIPPOCAMPAL SHAPE ASYMMETRY IN ALZHEIMER'S DISEASE USING OPTIMAL SHAPE CORRESPONDENCES

Hippocampal atrophy in Alzheimer's disease (AD) is asymmetric and spatially inhomogeneous. While extensive work has been done on volume and shape analysis of atrophy of the hippocampus in AD, less attention has been given to hippocampal asymmetry specifically. Previous studies of hippocampal asymmetry are limited to global volume or shape measures, which don't localize shape asymmetry at the point level. In this paper, we propose to quantify localized shape asymmetry by optimizing point correspondences between left and right hippocampi within a subject, while simultaneously favoring a compact statistical shape model of the entire sample. To account for related variables that have an impact on AD and healthy subject differences, we build linear models with other confounding factors. Our results on the OASIS3 dataset demonstrate that compared to volumetric information, shape asymmetry reveals fine-grained, localized differences that inform us about the hippocampal regions of most significant shape asymmetry in AD patients.

Autism Classification Using Topological Features and Deep Learning: A Cautionary Tale

The identification of autistic individuals using resting state functional connectivity networks can provide an objective diagnostic method for autism spectrum disorder (ASD). The present state-of-the-art machine learning model using deep learning has a classification accuracy of 70.2% on the ABIDE (Autism Brain Imaging Data Exchange) data set. In this paper, we explore the utility of topological features in the classification of ASD versus typically developing control subjects. These topological features have been shown to provide a complementary source of discriminative information in applications such as 2D object classification and social network analysis. We evaluate the performance of three different representations of topological features - persistence diagrams, persistence images, and persistence landscapes - for autism classification using neural networks, support vector machines and random forests. We also propose a hybrid approach of augmenting topological features with functional correlations, which typically outperforms the models that use functional correlations alone. With this approach, even with a simple 3-layer neural network, we are able to achieve a classification accuracy of 69.2% on the ABIDE data set. However, our experiments also show that the improvement due to topological features is not always statistically significant. Therefore, we offer a cautionary tale to the practitioners regarding the limited discriminative power of topological features derived from fMRI data for the classification of autism.

Image-based analysis and long-term clinical outcomes of deep brain stimulation for Tourette syndrome: a multisite study

BACKGROUND

Deep brain stimulation (DBS) can be an effective therapy for tics and comorbidities in select cases of severe, treatment-refractory Tourette syndrome (TS). Clinical responses remain variable across patients, which may be attributed to differences in the location of the neuroanatomical regions being stimulated. We evaluated active contact locations and regions of stimulation across a large cohort of patients with TS in an effort to guide future targeting.

METHODS

We collected retrospective clinical data and imaging from 13 international sites on 123 patients. We assessed the effects of DBS over time in 110 patients who were implanted in the centromedial (CM) thalamus (n=51), globus pallidus internus (GPi) (n=47), nucleus accumbens/anterior limb of the internal capsule (n=4) or a combination of targets (n=8). Contact locations (n=70 patients) and volumes of tissue activated (n=63 patients) were coregistered to create probabilistic stimulation atlases.

RESULTS

Tics and obsessive-compulsive behaviour (OCB) significantly improved over time (p<0.01), and there were no significant differences across brain targets (p>0.05). The median time was 13 months to reach a 40% improvement in tics, and there were no significant differences across targets (p=0.84), presence of OCB (p=0.09) or age at implantation (p=0.08). Active contacts were generally clustered near the target nuclei, with some variability that may reflect differences in targeting protocols, lead models and contact configurations. There were regions within and surrounding GPi and CM thalamus that improved tics for some patients but were ineffective for others. Regions within, superior or medial to GPi were associated with a greater improvement in OCB than regions inferior to GPi.

CONCLUSION

The results collectively indicate that DBS may improve tics and OCB, the effects may develop over several months, and stimulation locations relative to structural anatomy alone may not predict response. This study was the first to visualise and evaluate the regions of stimulation across a large cohort of patients with TS to generate new hypotheses about potential targets for improving tics and comorbidities.

Surface-Based Spatial Pyramid Matching of Cortical Regions for Analysis of Cognitive Performance

We propose a method to analyze the relationship between the shape of functional regions of the cortex and cognitive measures, such as reading ability and vocabulary knowledge. Functional regions on the cortical surface can vary not only in size and shape but also in topology and position relative to neighboring regions. Standard diffeomorphism-based shape analysis tools do not work well here because diffeomorphisms are unable to capture these topological differences, which include region splitting and merging across subjects. State-of-the-art cortical surface shape analyses compute derived regional properties (scalars), such as regional volume, cortical thickness, curvature, and gyrification index. However, these methods cannot compare the full extent of topological or shape differences in cortical regions. We propose icosahedral spatial pyramid matching (ISPM) of region borders computed on the surface of a sphere to capture this variation in regional topology, position, and shape. We then analyze how this variation corresponds to measures of cognitive performance. We compare our method to other approaches and find that it is indeed informative to consider aspects of shape beyond the standard approaches. Analysis is performed using a subset of 27 test/retest subjects from the Human Connectome Project in order to understand both the effectiveness and reproducibility of this method.

Revisiting Abnormalities in Brain Network Architecture Underlying Autism Using Topology-Inspired Statistical Inference

A large body of evidence relates autism with abnormal structural and functional brain connectivity. Structural covariance magnetic resonance imaging (scMRI) is a technique that maps brain regions with covarying gray matter densities across subjects. It provides a way to probe the anatomical structure underlying intrinsic connectivity networks (ICNs) through analysis of gray matter signal covariance. In this article, we apply topological data analysis in conjunction with scMRI to explore network-specific differences in the gray matter structure in subjects with autism versus age-, gender-, and IQ-matched controls. Specifically, we investigate topological differences in gray matter structure captured by structural correlation graphs derived from three ICNs strongly implicated in autism, namely the salience network, default mode network, and executive control network. By combining topological data analysis with statistical inference, our results provide evidence of statistically significant network-specific structural abnormalities in autism.

Riemannian Regression and Classification Models of Brain Networks Applied to Autism

Functional connectivity from resting-state functional MRI (rsfMRI) is typically represented as a symmetric positive definite (SPD) matrix. Analysis methods that exploit the Riemannian geometry of SPD matrices appropriately adhere to the positive definite constraint, unlike Euclidean methods. Recently proposed approaches for rsfMRI analysis have achieved high accuracy on public datasets, but are computationally intensive and difficult to interpret. In this paper, we show that we can get comparable results using connectivity matrices under the log-Euclidean and affine-invariant Riemannian metrics with relatively simple and interpretable models. On ABIDE Preprocessed dataset, our methods classify autism versus control subjects with 71.1% accuracy. We also show that Riemannian methods beat baseline in regressing connectome features to subject autism severity scores.

Nonparametric Aggregation of Geodesic Trends for Longitudinal Data Analysis

We propose a technique for analyzing longitudinal imaging data that models individual changes with diffeomorphic geodesic regression and aggregates these geodesics into a nonparametric group average trend. Our model is specifically tailored to the unbalanced and sparse characteristics of longitudinal imaging studies. That is, each individual has few data points measured over a short period of time, while the study population as a whole spans a wide age range. We use geodesic regression to estimate individual trends, which is an appropriate model for capturing shape changes over a short time window, as is typically found within an individual. Geodesics are also adept at handling the low sample sizes found within individuals, and can model the change between as few as two timepoints. However, geodesics are limited for modeling longer-term trends, where constant velocity may not be appropriate. Therefore, we develop a novel nonparametric regression to aggregate individual trends into an average group trend. We demonstrate the power of our method to capture non-geodesic group trends on hippocampal volume (real-valued data) and diffeomorphic registration of full 3D MRI from the longitudinal OASIS data.

Efficient Parallel Transport in the Group of Diffeomorphisms via Reduction to the Lie Algebra

This paper presents an efficient, numerically stable algorithm for parallel transport of tangent vectors in the group of diffeomorphisms. Previous approaches to parallel transport in large deformation diffeomorphic metric mapping (LDDMM) of images represent a momenta field, the dual of a tangent vector to the diffeomorphism group, as a scalar field times the image gradient. This "scalar momenta" constraint couples tangent vectors with the images being deformed and leads to computationally costly horizontal lifts in parallel transport. This paper uses the vector momenta formulation of LDDMM, which decouples the diffeomorphisms from the structures being transformed, e.g., images, point sets, etc. This decoupling leads to parallel transport expressed as a linear ODE in the Lie algebra. Solving this ODE directly is numerically stable and significantly faster than other LDDMM parallel transport methods. Results on 2D synthetic data and 3D brain MRI demonstrate that our algorithm is fast and conserves the inner products of the transported tangent vectors.

Multivariate characterization of white matter heterogeneity in autism spectrum disorder

The complexity and heterogeneity of neuroimaging findings in individuals with autism spectrum disorder has suggested that many of the underlying alterations are subtle and involve many brain regions and networks. The ability to account for multivariate brain features and identify neuroimaging measures that can be used to characterize individual variation have thus become increasingly important for interpreting and understanding the neurobiological mechanisms of autism. In the present study, we utilize the Mahalanobis distance, a multidimensional counterpart of the Euclidean distance, as an informative index to characterize individual brain variation and deviation in autism. Longitudinal diffusion tensor imaging data from 149 participants (92 diagnosed with autism spectrum disorder and 57 typically developing controls) between 3.1 and 36.83 years of age were acquired over a roughly 10-year period and used to construct the Mahalanobis distance from regional measures of white matter microstructure. Mahalanobis distances were significantly greater and more variable in the autistic individuals as compared to control participants, demonstrating increased atypicalities and variation in the group of individuals diagnosed with autism spectrum disorder. Distributions of multivariate measures were also found to provide greater discrimination and more sensitive delineation between autistic and typically developing individuals than conventional univariate measures, while also being significantly associated with observed traits of the autism group. These results help substantiate autism as a truly heterogeneous neurodevelopmental disorder, while also suggesting that collectively considering neuroimaging measures from multiple brain regions provides improved insight into the diversity of brain measures in autism that is not observed when considering the same regions separately. Distinguishing multidimensional brain relationships may thus be informative for identifying neuroimaging-based phenotypes, as well as help elucidate underlying neural mechanisms of brain variation in autism spectrum disorders.

KERNEL PARTIAL LEAST SQUARES REGRESSION FOR RELATING FUNCTIONAL BRAIN NETWORK TOPOLOGY TO CLINICAL MEASURES OF BEHAVIOR

In this paper we present a novel method for analyzing the relationship between functional brain networks and behavioral phenotypes. Drawing from topological data analysis, we first extract topological features using persistent homology from functional brain networks that are derived from correlations in resting-state fMRI. Rather than fixing a discrete network topology by thresholding the connectivity matrix, these topological features capture the network organization across all continuous threshold values. We then propose to use a kernel partial least squares (kPLS) regression to statistically quantify the relationship between these topological features and behavior measures. The kPLS also provides an elegant way to combine multiple image features by using linear combinations of multiple kernels. In our experiments we test the ability of our proposed brain network analysis to predict autism severity from rs-fMRI. We show that combining correlations with topological features gives better prediction of autism severity than using correlations alone.

Investigating the Microstructural Correlation of White Matter in Autism Spectrum Disorder

White matter microstructure forms a complex and dynamical system that is critical for efficient and synchronized brain function. Neuroimaging findings in children with autism spectrum disorder (ASD) suggest this condition is associated with altered white matter microstructure, which may lead to atypical macroscale brain connectivity. In this study, we used diffusion tensor imaging measures to examine the extent that white matter tracts are interrelated within ASD and typical development. We assessed the strength of inter-regional white matter correlations between typically developing and ASD diagnosed individuals. Using hierarchical clustering analysis, clustering patterns of the pairwise white matter correlations were constructed and revealed to be different between the two groups. Additionally, we explored the use of graph theory analysis to examine the characteristics of the patterns formed by inter-regional white matter correlations and compared these properties between ASD and typical development. We demonstrate that the ASD sample has significantly less coherence in white matter microstructure across the brain compared to that in the typical development sample. The ASD group also presented altered topological characteristics, which may implicate less efficient brain networking in ASD. These findings highlight the potential of graph theory based network characteristics to describe the underlying networks as measured by diffusion magnetic resonance imaging and furthermore indicates that ASD may be associated with altered brain network characteristics. Our findings are consistent with those of a growing number of studies and hypotheses that have suggested disrupted brain connectivity in ASD.

Bayesian Covariate Selection in Mixed-Effects Models For Longitudinal Shape Analysis

The goal of longitudinal shape analysis is to understand how anatomical shape changes over time, in response to biological processes, including growth, aging, or disease. In many imaging studies, it is also critical to understand how these shape changes are affected by other factors, such as sex, disease diagnosis, IQ, etc. Current approaches to longitudinal shape analysis have focused on modeling age-related shape changes, but have not included the ability to handle covariates. In this paper, we present a novel Bayesian mixed-effects shape model that incorporates simultaneous relationships between longitudinal shape data and multiple predictors or covariates to the model. Moreover, we place an Automatic Relevance Determination (ARD) prior on the parameters, that lets us automatically select which covariates are most relevant to the model based on observed data. We evaluate our proposed model and inference procedure on a longitudinal study of Huntington's disease from PREDICT-HD. We first show the utility of the ARD prior for model selection in a univariate modeling of striatal volume, and next we apply the full high-dimensional longitudinal shape model to putamen shapes.

Bayesian principal geodesic analysis for estimating intrinsic diffeomorphic image variability

In this paper, we present a generative Bayesian approach for estimating the low-dimensional latent space of diffeomorphic shape variability in a population of images. We develop a latent variable model for principal geodesic analysis (PGA) that provides a probabilistic framework for factor analysis in the space of diffeomorphisms. A sparsity prior in the model results in automatic selection of the number of relevant dimensions by driving unnecessary principal geodesics to zero. To infer model parameters, including the image atlas, principal geodesic deformations, and the effective dimensionality, we introduce an expectation maximization (EM) algorithm. We evaluate our proposed model on 2D synthetic data and the 3D OASIS brain database of magnetic resonance images, and show that the automatically selected latent dimensions from our model are able to reconstruct unobserved testing images with lower error than both linear principal component analysis (LPCA) in the image space and tangent space principal component analysis (TPCA) in the diffeomorphism space.

A Transformation Similarity Constraint for Groupwise Nonlinear Registration in Longitudinal Neuro Imaging Studies

Patients with Alzheimer's disease and other brain disorders often show a similar spatial distribution of volume change throughout the brain over time,^1,2 but this information is not yet used in registration algorithms to refine the quantification of change. Here, we develop a mathematical basis to incorporate that prior information into a longitudinal structural neuroimaging study. We modify the canonical minimization problem for non-linear registration to include a term that couples a collection of registrations together to enforce group similarity. More specifically, throughout the computation we maintain a group-level representation of the transformations and constrain updates to individual transformations to be similar to this representation. The derivations necessary to produce the Euler-Lagrange equations for the coupling term are presented and a gradient descent algorithm based on the formulation was implemented. We demonstrate using 57 longitudinal image pairs from the Alzheimer's Disease Neuroimaging Initiative (ADNI) that longitudinal registration with such a groupwise coupling prior is more robust to noise in estimating change, suggesting such change maps may have several important applications.

Atypical development of white matter microstructure of the corpus callosum in males with autism: a longitudinal investigation

BACKGROUND

The corpus callosum is the largest white matter structure in the brain, and it is the most consistently reported to be atypical in diffusion tensor imaging studies of autism spectrum disorder. In individuals with typical development, the corpus callosum is known to undergo a protracted development from childhood through young adulthood. However, no study has longitudinally examined the developmental trajectory of corpus callosum in autism past early childhood.

METHODS

The present study used a cohort sequential design over 9 years to examine age-related changes of the corpus callosum in 100 males with autism and 56 age-matched males with typical development from early childhood (when autism can first be reliably diagnosed) to mid-adulthood (after development of the corpus callosum has been completed) (3 to 41 years of age).

RESULTS

The group with autism demonstrated a different developmental trajectory of white matter microstructure in the anterior corpus callosum's (genu and body) fractional anisotropy, which suggests atypical brain maturation in these regions in autism. When analyses were broken down by age group, atypical developmental trajectories were present only in the youngest participants (10 years of age and younger). Significant main effects for group were found in terms of decreased fractional anisotropy across all three subregions of the corpus callosum (genu, body, and splenium) and increased mean diffusivity, radial diffusivity, and axial diffusivity in the posterior corpus callosum.

CONCLUSIONS

These longitudinal results suggest atypical early childhood development of the corpus callosum microstructure in autism that transitions into sustained group differences in adolescence and adulthood. This pattern of results provides longitudinal evidence consistent with a growing number of published studies and hypotheses regarding abnormal brain connectivity across the life span in autism.

Simultaneous Longitudinal Registration with Group-Wise Similarity Prior

Here we present an algorithm for the simultaneous registration of N longitudinal image pairs such that information acquired by each pair is used to constrain the registration of each other pair. More specifically, in the geodesic shooting setting for Large Deformation Diffeomorphic Metric Mappings (LDDMM) an average of the initial momenta characterizing the N transformations is maintained throughout and updates to individual momenta are constrained to be similar to this average. In this way, the N registrations are coupled and explore the space of diffeomorphisms as a group, the variance of which is constrained to be small. Our approach is motivated by the observation that transformations learned from images in the same diagnostic category share characteristics. The group-wise consistency prior serves to strengthen the contribution of the common signal among the N image pairs to the transformation for a specific pair, relative to features particular to that pair. We tested the algorithm on 57 longitudinal image pairs of Alzheimer's Disease patients from the Alzheimer's Disease Neuroimaging Initiative and evaluated the ability of the algorithm to produce momenta that better represent the long-term biological processes occurring in the underlying anatomy. We found that for many image pairs, momenta learned with the group-wise prior better predict a third time point image unobserved in the registration.

A Riemannian Framework for Intrinsic Comparison of Closed Genus-Zero Shapes

We present a framework for intrinsic comparison of surface metric structures and curvatures. This work parallels the work of Kurtek et al. on parameterization-invariant comparison of genus zero shapes. Here, instead of comparing the embedding of spherically parameterized surfaces in space, we focus on the first fundamental form. To ensure that the distance on spherical metric tensor fields is invariant to parameterization, we apply the conjugation-invariant metric arising from the L2 norm on symmetric positive definite matrices. As a reparameterization changes the metric tensor by a congruent Jacobian transform, this metric perfectly suits our purpose. The result is an intrinsic comparison of shape metric structure that does not depend on the specifics of a spherical mapping. Further, when restricted to tensors of fixed volume form, the manifold of metric tensor fields and its quotient of the group of unitary diffeomorphisms becomes a proper metric manifold that is geodesically complete. Exploiting this fact, and augmenting the metric with analogous metrics on curvatures, we derive a complete Riemannian framework for shape comparison and reconstruction. A by-product of our framework is a near-isometric and curvature-preserving mapping between surfaces. The correspondence is optimized using the fast spherical fluid algorithm. We validate our framework using several subcortical boundary surface models from the ADNI dataset.

Longitudinal volumetric brain changes in autism spectrum disorder ages 6-35 years

Since the impairments associated with autism spectrum disorder (ASD) tend to persist or worsen from childhood into adulthood, it is of critical importance to examine how the brain develops over this growth epoch. We report initial findings on whole and regional longitudinal brain development in 100 male participants with ASD (226 high-quality magnetic resonance imaging [MRI] scans; mean inter-scan interval 2.7 years) compared to 56 typically developing controls (TDCs) (117 high-quality scans; mean inter-scan interval 2.6 years) from childhood into adulthood, for a total of 156 participants scanned over an 8-year period. This initial analysis includes between one and three high-quality scans per participant that have been processed and segmented to date, with 21% having one scan, 27% with two scans, and 52% with three scans in the ASD sample; corresponding percentages for the TDC sample are 30%, 30%, and 40%. The proportion of participants with multiple scans (79% of ASDs and 68% of TDCs) was high in comparison to that of large longitudinal neuroimaging studies of typical development. We provide volumetric growth curves for the entire brain, total gray matter (GM), frontal GM, temporal GM, parietal GM, occipital GM, total cortical white matter (WM), corpus callosum, caudate, thalamus, total cerebellum, and total ventricles. Mean volume of cortical WM was reduced significantly. Mean ventricular volume was increased in the ASD sample relative to the TDCs across the broad age range studied. Decreases in regional mean volumes in the ASD sample most often were due to decreases during late adolescence and adulthood. The growth curve of whole brain volume over time showed increased volumes in young children with autism, and subsequently decreased during adolescence to meet the TDC curve between 10 and 15 years of age. The volume of many structures continued to decline atypically into adulthood in the ASD sample. The data suggest that ASD is a dynamic disorder with complex changes in whole and regional brain volumes that change over time from childhood into adulthood.

PARAMETRIC REGRESSION SCHEME FOR DISTRIBUTIONS: ANALYSIS OF DTI FIBER TRACT DIFFUSION CHANGES IN EARLY BRAIN DEVELOPMENT

Temporal modeling frameworks often operate on scalar variables by summarizing data at initial stages as statistical summaries of the underlying distributions. For instance, DTI analysis often employs summary statistics, like mean, for regions of interest and properties along fiber tracts for population studies and hypothesis testing. This reduction via discarding of variability information may introduce significant errors which propagate through the procedures. We propose a novel framework which uses distribution-valued variables to retain and utilize the local variability information. Classic linear regression is adapted to employ these variables for model estimation. The increased stability and reliability of our proposed method when compared with regression using single-valued statistical summaries, is demonstrated in a validation experiment with synthetic data. Our driving application is the modeling of age-related changes along DTI white matter tracts. Results are shown for the spatiotemporal population trajectory of genu tract estimated from 45 healthy infants and compared with a Krabbe's patient.

A functional network estimation method of resting-state fMRI using a hierarchical Markov random field

We propose a hierarchical Markov random field model for estimating both group and subject functional networks simultaneously. The model takes into account the within-subject spatial coherence as well as the between-subject consistency of the network label maps. The statistical dependency between group and subject networks acts as a regularization, which helps the network estimation on both layers. We use Gibbs sampling to approximate the posterior density of the network labels and Monte Carlo expectation maximization to estimate the model parameters. We compare our method with two alternative segmentation methods based on K-Means and normalized cuts, using synthetic and real fMRI data. The experimental results show that our proposed model is able to identify both group and subject functional networks with higher accuracy on synthetic data, more robustness, and inter-session consistency on the real data.

Longitudinal changes in cortical thickness in autism and typical development

The natural history of brain growth in autism spectrum disorders remains unclear. Cross-sectional studies have identified regional abnormalities in brain volume and cortical thickness in autism, although substantial discrepancies have been reported. Preliminary longitudinal studies using two time points and small samples have identified specific regional differences in cortical thickness in the disorder. To clarify age-related trajectories of cortical development, we examined longitudinal changes in cortical thickness within a large mixed cross-sectional and longitudinal sample of autistic subjects and age- and gender-matched typically developing controls. Three hundred and forty-five magnetic resonance imaging scans were examined from 97 males with autism (mean age = 16.8 years; range 3-36 years) and 60 males with typical development (mean age = 18 years; range 4-39 years), with an average interscan interval of 2.6 years. FreeSurfer image analysis software was used to parcellate the cortex into 34 regions of interest per hemisphere and to calculate mean cortical thickness for each region. Longitudinal linear mixed effects models were used to further characterize these findings and identify regions with between-group differences in longitudinal age-related trajectories. Using mean age at time of first scan as a reference (15 years), differences were observed in bilateral inferior frontal gyrus, pars opercularis and pars triangularis, right caudal middle frontal and left rostral middle frontal regions, and left frontal pole. However, group differences in cortical thickness varied by developmental stage, and were influenced by IQ. Differences in age-related trajectories emerged in bilateral parietal and occipital regions (postcentral gyrus, cuneus, lingual gyrus, pericalcarine cortex), left frontal regions (pars opercularis, rostral middle frontal and frontal pole), left supramarginal gyrus, and right transverse temporal gyrus, superior parietal lobule, and paracentral, lateral orbitofrontal, and lateral occipital regions. We suggest that abnormal cortical development in autism spectrum disorders undergoes three distinct phases: accelerated expansion in early childhood, accelerated thinning in later childhood and adolescence, and decelerated thinning in early adulthood. Moreover, cortical thickness abnormalities in autism spectrum disorders are region-specific, vary with age, and may remain dynamic well into adulthood.

4D ACTIVE CUT: AN INTERACTIVE TOOL FOR PATHOLOGICAL ANATOMY MODELING

4D pathological anatomy modeling is key to understanding complex pathological brain images. It is a challenging problem due to the difficulties in detecting multiple appearing and disappearing lesions across time points and estimating dynamic changes and deformations between them. We propose a novel semi-supervised method, called 4D active cut, for lesion recognition and deformation estimation. Existing interactive segmentation methods passively wait for user to refine the segmentations which is a difficult task in 3D images that change over time. 4D active cut instead actively selects candidate regions for querying the user, and obtains the most informative user feedback. A user simply answers 'yes' or 'no' to a candidate object without having to refine the segmentation slice by slice. Compared to single-object detection of the existing methods, our method also detects multiple lesions with spatial coherence using Markov random fields constraints. Results show improvement on the lesion detection, which subsequently improves deformation estimation.