Publications

2014
Parmar C, Rios Velazquez E, Leijenaar R, Jermoumi M, Carvalho S, Mak RH, Mitra S, Shankar UB, Kikinis R, Haibe-Kains B, et al. Robust Radiomics feature quantification using semiautomatic volumetric segmentation. PLoS One. 2014;9 (7) :e102107.Abstract
Due to advances in the acquisition and analysis of medical imaging, it is currently possible to quantify the tumor phenotype. The emerging field of Radiomics addresses this issue by converting medical images into minable data by extracting a large number of quantitative imaging features. One of the main challenges of Radiomics is tumor segmentation. Where manual delineation is time consuming and prone to inter-observer variability, it has been shown that semi-automated approaches are fast and reduce inter-observer variability. In this study, a semiautomatic region growing volumetric segmentation algorithm, implemented in the free and publicly available 3D-Slicer platform, was investigated in terms of its robustness for quantitative imaging feature extraction. Fifty-six 3D-radiomic features, quantifying phenotypic differences based on tumor intensity, shape and texture, were extracted from the computed tomography images of twenty lung cancer patients. These radiomic features were derived from the 3D-tumor volumes defined by three independent observers twice using 3D-Slicer, and compared to manual slice-by-slice delineations of five independent physicians in terms of intra-class correlation coefficient (ICC) and feature range. Radiomic features extracted from 3D-Slicer segmentations had significantly higher reproducibility (ICC = 0.85±0.15, p = 0.0009) compared to the features extracted from the manual segmentations (ICC = 0.77±0.17). Furthermore, we found that features extracted from 3D-Slicer segmentations were more robust, as the range was significantly smaller across observers (p = 3.819e-07), and overlapping with the feature ranges extracted from manual contouring (boundary lower: p = 0.007, higher: p = 5.863e-06). Our results show that 3D-Slicer segmented tumor volumes provide a better alternative to the manual delineation for feature quantification, as they yield more reproducible imaging descriptors. Therefore, 3D-Slicer can be employed for quantitative image feature extraction and image data mining research in large patient cohorts.
Cavallari M, Moscufo N, Meier D, Skudlarski P, Pearlson GD, White WB, Wolfson L, Guttmann CRG. Thalamic fractional anisotropy predicts accrual of cerebral white matter damage in older subjects with small-vessel disease. J Cereb Blood Flow Metab. 2014;34 (8) :1321-7.Abstract
White matter hyperintensities (WMHs) and lacunes are magnetic resonance imaging hallmarks of cerebral small-vessel disease, which increase the risk of stroke, cognitive, and mobility impairment. Although most studies of cerebral small-vessel disease have focused on white matter abnormalities, the gray matter (GM) is also affected, as evidenced by frequently observed lacunes in subcortical GM. Diffusion tensor imaging (DTI) is sensitive to subtle neurodegenerative changes in deep GM structures. We explored the relationship between baseline DTI characteristics of the thalamus, caudate, and putamen, and the volume and subsequent accrual of WMHs over a 4-year period in 56 community-dwelling older (⩾75 years) individuals. Baseline thalamic fractional anisotropy (FA) was an independent predictor of WMH accrual. WMH accrual also correlated with baseline lacune count and baseline WMH volume, the latter showing the strongest predictive power, explaining 27.3% of the variance. The addition of baseline thalamic FA in multivariate modeling increased this value by 70%, which explains 46.5% of the variance in WMH accrual rate. Thalamic FA might serve as a novel predictor of cerebral small-vessel disease progression in clinical settings and trials. Furthermore, our findings point to the possibility of a causal relationship between thalamic damage and the accrual of WMHs.
Huang W, Li X, Chen Y, Li X, Chang M-C, Oborski MJ, Malyarenko DI, Muzi M, Jajamovich GH, Fedorov A, et al. Variations of dynamic contrast-enhanced magnetic resonance imaging in evaluation of breast cancer therapy response: a multicenter data analysis challenge. Transl Oncol. 2014;7 (1) :153-66.Abstract
Pharmacokinetic analysis of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) time-course data allows estimation of quantitative parameters such as K (trans) (rate constant for plasma/interstitium contrast agent transfer), v e (extravascular extracellular volume fraction), and v p (plasma volume fraction). A plethora of factors in DCE-MRI data acquisition and analysis can affect accuracy and precision of these parameters and, consequently, the utility of quantitative DCE-MRI for assessing therapy response. In this multicenter data analysis challenge, DCE-MRI data acquired at one center from 10 patients with breast cancer before and after the first cycle of neoadjuvant chemotherapy were shared and processed with 12 software tools based on the Tofts model (TM), extended TM, and Shutter-Speed model. Inputs of tumor region of interest definition, pre-contrast T1, and arterial input function were controlled to focus on the variations in parameter value and response prediction capability caused by differences in models and associated algorithms. Considerable parameter variations were observed with the within-subject coefficient of variation (wCV) values for K (trans) and v p being as high as 0.59 and 0.82, respectively. Parameter agreement improved when only algorithms based on the same model were compared, e.g., the K (trans) intraclass correlation coefficient increased to as high as 0.84. Agreement in parameter percentage change was much better than that in absolute parameter value, e.g., the pairwise concordance correlation coefficient improved from 0.047 (for K (trans)) to 0.92 (for K (trans) percentage change) in comparing two TM algorithms. Nearly all algorithms provided good to excellent (univariate logistic regression c-statistic value ranging from 0.8 to 1.0) early prediction of therapy response using the metrics of mean tumor K (trans) and k ep (=K (trans)/v e, intravasation rate constant) after the first therapy cycle and the corresponding percentage changes. The results suggest that the interalgorithm parameter variations are largely systematic, which are not likely to significantly affect the utility of DCE-MRI for assessment of therapy response.
Langs G, Sweet A, Lashkari D, Tie Y, Rigolo L, Golby AJ, Golland P. Decoupling Function and Anatomy in Atlases of Functional Connectivity Patterns: Language Mapping in Tumor Patients. Neuroimage. 2014;103 :462-75.Abstract
In this paper we construct an atlas that summarizes functional connectivity characteristics of a cognitive process from a population of individuals. The atlas encodes functional connectivity structure in a low-dimensional embedding space that is derived from a diffusion process on a graph that represents correlations of fMRI time courses. The functional atlas is decoupled from the anatomical space, and thus can represent functional networks with variable spatial distribution in a population. In practice the atlas is represented by a common prior distribution for the embedded fMRI signals of all subjects. We derive an algorithm for fitting this generative model to the observed data in a population. Our results in a language fMRI study demonstrate that the method identifies coherent and functionally equivalent regions across subjects. The method also successfully maps functional networks from a healthy population used as a training set to individuals whose language networks are affected by tumors.
Gao Y, Tannenbaum A, Bouix S. A Framework for Joint Image-and-Shape Analysis. Proc SPIE Int Soc Opt Eng. 2014;9034 :90340V.Abstract
Techniques in medical image analysis are many times used for the comparison or regression on the intensities of images. In general, the domain of the image is a given Cartesian grids. Shape analysis, on the other hand, studies the similarities and differences among spatial objects of arbitrary geometry and topology. Usually, there is no function defined on the domain of shapes. Recently, there has been a growing needs for defining and analyzing functions defined on the shape space, and a coupled analysis on both the shapes and the functions defined on them. Following this direction, in this work we present a coupled analysis for both images and shapes. As a result, the statistically significant discrepancies in both the image intensities as well as on the underlying shapes are detected. The method is applied on both brain images for the schizophrenia and heart images for atrial fibrillation patients.
Savadjiev P, Rathi Y, Bouix S, Smith AR, Schultz RT, Verma R, Westin C-F. Fusion of White and Gray Matter Geometry: A Framework for Investigating Brain Development. Med Image Anal. 2014;18 (8) :1349-60.Abstract
Current neuroimaging investigation of the white matter typically focuses on measurements derived from diffusion tensor imaging, such as fractional anisotropy (FA). In contrast, imaging studies of the gray matter oftentimes focus on morphological features such as cortical thickness, folding and surface curvature. As a result, it is not clear how to combine findings from these two types of approaches in order to obtain a consistent picture of morphological changes in both gray and white matter. In this paper, we propose a joint investigation of gray and white matter morphology by combining geometrical information from white and the gray matter. To achieve this, we first introduce a novel method for computing multi-scale white matter tract geometry. Its formulation is based on the differential geometry of curve sets and is easily incorporated into a continuous scale-space framework. We then incorporate this method into a novel framework for "fusing" white and gray matter geometrical information. Given a set of fiber tracts originating in a particular cortical region, the key idea is to compute two scalar fields that represent geometrical characteristics of the white matter and of the surface of the cortical region. A quantitative marker is created by combining the distributions of these scalar values using Mutual Information. This marker can be then used in the study of normal and pathological brain structure and development. We apply this framework to a study on autism spectrum disorder in children. Our preliminary results support the view that autism may be characterized by early brain overgrowth, followed by reduced or arrested growth (Courchesne, 2004).
Nakhmani A, Kikinis R, Tannenbaum A. MRI Brain Tumor Segmentation and Necrosis Detection Using Adaptive Sobolev Snakes. Proc SPIE Int Soc Opt Eng. 2014;9034 :903442.Abstract
Brain tumor segmentation in brain MRI volumes is used in neurosurgical planning and illness staging. It is important to explore the tumor shape and necrosis regions at different points of time to evaluate the disease progression. We propose an algorithm for semi-automatic tumor segmentation and necrosis detection. Our algorithm consists of three parts: conversion of MRI volume to a probability space based on the on-line learned model, tumor probability density estimation, and adaptive segmentation in the probability space. We use manually selected acceptance and rejection classes on a single MRI slice to learn the background and foreground statistical models. Then, we propagate this model to all MRI slices to compute the most probable regions of the tumor. Anisotropic 3D diffusion is used to estimate the probability density. Finally, the estimated density is segmented by the Sobolev active contour (snake) algorithm to select smoothed regions of the maximum tumor probability. The segmentation approach is robust to noise and not very sensitive to the manual initialization in the volumes tested. Also, it is appropriate for low contrast imagery. The irregular necrosis regions are detected by using the outliers of the probability distribution inside the segmented region. The necrosis regions of small width are removed due to a high probability of noisy measurements. The MRI volume segmentation results obtained by our algorithm are very similar to expert manual segmentation.
Echlin PS, Johnson AM, Holmes JD, Tichenoff A, Gray S, Gatavackas H, Walsh J, Middlebro T, Blignaut A, MacIntyre M, et al. The Sport Concussion Education Project. A brief report on an educational initiative: from concept to curriculum. J Neurosurg. 2014;121 (6) :1331-6.Abstract
Current research on concussion is primarily focused on injury identification and treatment. Prevention initiatives are, however, important for reducing the incidence of brain injury. This report examines the development and implementation of an interactive electronic teaching program (an e-module) that is designed specifically for concussion education within an adolescent population. This learning tool and the accompanying consolidation rubric demonstrate that significant engagement occurs in addition to the knowledge gained among participants when it is used in a school curriculum setting.
Huang S, Rossi S, Hämäläinen M, Ahveninen J. Auditory conflict resolution correlates with medial-lateral frontal theta/alpha phase synchrony. PLoS One. 2014;9 (10) :e110989.Abstract
When multiple persons speak simultaneously, it may be difficult for the listener to direct attention to correct sound objects among conflicting ones. This could occur, for example, in an emergency situation in which one hears conflicting instructions and the loudest, instead of the wisest, voice prevails. Here, we used cortically-constrained oscillatory MEG/EEG estimates to examine how different brain regions, including caudal anterior cingulate (cACC) and dorsolateral prefrontal cortices (DLPFC), work together to resolve these kinds of auditory conflicts. During an auditory flanker interference task, subjects were presented with sound patterns consisting of three different voices, from three different directions (45° left, straight ahead, 45° right), sounding out either the letters "A" or "O". They were asked to discriminate which sound was presented centrally and ignore the flanking distracters that were phonetically either congruent (50%) or incongruent (50%) with the target. Our cortical MEG/EEG oscillatory estimates demonstrated a direct relationship between performance and brain activity, showing that efficient conflict resolution, as measured with reduced conflict-induced RT lags, is predicted by theta/alpha phase coupling between cACC and right lateral frontal cortex regions intersecting the right frontal eye fields (FEF) and DLPFC, as well as by increased pre-stimulus gamma (60-110 Hz) power in the left inferior fontal cortex. Notably, cACC connectivity patterns that correlated with behavioral conflict-resolution measures were found during both the pre-stimulus and the pre-response periods. Our data provide evidence that, instead of being only transiently activated upon conflict detection, cACC is involved in sustained engagement of attentional resources required for effective sound object selection performance.
Knutsson H, Westin C-F. From Expected Propagator Distribution to Optimal Q-Space Sample Metric. Med Image Comput Comput Assist Interv. 2014;17 (Pt 3) :217-24.Abstract
We present a novel approach to determine a local q-space metric that is optimal from an information theoreticperspective with respect to the expected signal statistics. It should be noted that the approach does not attempt to optimize the quality of a pre-defined mathematical representation, the estimator. In contrast, our suggestion aims at obtaining the maximum amount of information without enforcing a particular feature representation. Results for three significantly different average propagator distributions are presented. The results show that the optimal q-space metric has a strong dependence on the assumed distribution in the targeted tissue. In many practical cases educated guesses can be made regarding the average propagator distribution present. In such cases the presented analysis can produce a metric that is optimal with respect to this distribution. The metric will be different at different q-space locations and is defined by the amount of additional information that is obtained when adding a second sample at a given offset from a first sample. The intention is to use the obtained metric as a guide for the generation of specific efficient q-space sample distributions for the targeted tissue.
Gao Y, Zhu L-J, Bouix S, Tannenbaum A. Interpolation of Longitudinal Shape and Image Data via Optimal Mass Transport. Proc SPIE Int Soc Opt Eng. 2014;9034 :90342X.Abstract
Longitudinal analysis of medical imaging data has become central to the study of many disorders. Unfortunately, various constraints (study design, patient availability, technological limitations) restrict the acquisition of data to only a few time points, limiting the study of continuous disease/treatment progression. Having the ability to produce a sensible time interpolation of the data can lead to improved analysis, such as intuitive visualizations of anatomical changes, or the creation of more samples to improve statistical analysis. In this work, we model interpolation of medical image data, in particular shape data, using the theory of optimal mass transport (OMT), which can construct a continuous transition from two time points while preserving "mass" (e.g., image intensity, shape volume) during the transition. The theory even allows a short extrapolation in time and may help predict short-term treatment impact or disease progression on anatomical structure. We apply the proposed method to the hippocampus-amygdala complex in schizophrenia, the heart in atrial fibrillation, and full head MR images in traumatic brain injury.
Westin C-F, Szczepankiewicz F, Pasternak O, Ozarslan E, Topgaard D, Knutsson H, Nilsson M. Measurement Tensors in Diffusion MRI: Generalizing the Concept of Diffusion Encoding. Med Image Comput Comput Assist Interv. 2014;17 (Pt 3) :209-16.Abstract
In traditional diffusion MRI, short pulsed field gradients (PFG) are used for the diffusion encoding. The standard Stejskal-Tanner sequence uses one single pair of such gradients, known as single-PFG (sPFG). In this work we describe how trajectories in q-space can be used for diffusion encoding. We discuss how such encoding enables the extension of the well-known scalar b-value to a tensor-valued entity we call the diffusion measurement tensor. The new measurements contain information about higher order diffusion propagator covariances not present in sPFG. As an example analysis, we use this new information to estimate a Gaussian distribution over diffusion tensors in each voxel, described by its mean (a diffusion tensor) and its covariance (a 4th order tensor).
Gao Y, Zhu L, Norton I, Agar NYR, Tannenbaum A. Reconstruction and Feature Selection for Desorption Electrospray Ionization Mass Spectroscopy Imagery. Proc SPIE Int Soc Opt Eng. 2014;9036 :90360D.Abstract
Desorption electrospray ionization mass spectrometry (DESI-MS) provides a highly sensitive imaging technique for differentiating normal and cancerous tissue at the molecular level. This can be very useful, especially under intra-operative conditions where the surgeon has to make crucial decision about the tumor boundary. In such situations, the time it takes for imaging and data analysis becomes a critical factor. Therefore, in this work we utilize compressive sensing to perform the sparse sampling of the tissue, which halves the scanning time. Furthermore, sparse feature selection is performed, which not only reduces the dimension of data from about 10(4) to less than 50, and thus significantly shortens the analysis time. This procedure also identifies biochemically important molecules for pathological analysis. The methods are validated on brain and breast tumor data sets.
Rathi Y, Ning L, Michailovich O, Liao HJ, Gagoski B, Grant EP, Shenton ME, Stern R, Westin C-F, Lin A. Maximum Entropy Estimation of Glutamate and Glutamine in MR Spectroscopic Imaging. Med Image Comput Comput Assist Interv. 2014;17 (Pt 2) :749-56.Abstract
Magnetic resonance spectroscopic imaging (MRSI) is often used to estimate the concentration of several brain metabolites. Abnormalities in these concentrations can indicate specific pathology, which can be quite useful in understanding the disease mechanism underlying those changes. Due to higher concentration, metabolites such as N-acetylaspartate (NAA), Creatine (Cr) and Choline (Cho) can be readily estimated using standard Fourier transform techniques. However, metabolites such as Glutamate (Glu) and Glutamine (Gln) occur in significantly lower concentrations and their resonance peaks are very close to each other making it difficult to accurately estimate their concentrations (separately). In this work, we propose to use the theory of 'Spectral Zooming' or high-resolution spectral analysis to separate the Glutamate and Glutamine peaks and accurately estimate their concentrations. The method works by estimating a unique power spectral density, which corresponds to the maximum entropy solution of a zero-mean stationary Gaussian process. We demonstrate our estimation technique on several physical phantom data sets as well as on in-vivo brain spectroscopic imaging data. The proposed technique is quite general and can be used to estimate the concentration of any other metabolite of interest.
Dalca AV, Sridharan R, Cloonan L, Fitzpatrick KM, Kanakis A, Furie KL, Rosand J, Wu O, Sabuncu M, Rost NS, et al. Segmentation 0f Cerebrovascular Pathologies in Stroke Patients with Spatial and Shape Priors. Med Image Comput Comput Assist Interv. 2014;17 (Pt 2) :773-80.Abstract
We propose and demonstrate an inference algorithm for the automatic segmentation of cerebrovascular pathologies in clinical MR images of the brain. Identifying and differentiating pathologies is important for understanding the underlying mechanisms and clinical outcomes of cerebral ischemia. Manual delineation of separate pathologies is infeasible in large studies of stroke that include thousands of patients. Unlike normal brain tissues and structures, the location and shape of the lesions vary across patients, presenting serious challenges for prior-driven segmentation. Our generative model captures spatial patterns and intensity properties associated with different cerebrovascular pathologies in stroke patients. We demonstrate the resulting segmentation algorithm on clinical images of a stroke patient cohort.
Batmanghelich KN, Cho M, Jose RS, Golland P. Spherical Topic Models for Imaging Phenotype Discovery in Genetic Studies. Bayesian Graph Models Biomed Imaging. 2014;8677 :107-17.Abstract
In this paper, we use Spherical Topic Models to discover the latent structure of lung disease. This method can be widely employed when a measurement for each subject is provided as a normalized histogram of relevant features. In this paper, the resulting descriptors are used as phenotypes to identify genetic markers associated with the Chronic Obstructive Pulmonary Disease (COPD). Features extracted from images capture the heterogeneity of the disease and therefore promise to improve detection of relevant genetic variants in Genome Wide Association Studies (GWAS). Our generative model is based on normalized histograms of image intensity of each subject and it can be readily extended to other forms of features as long as they are provided as normalized histograms. The resulting algorithm represents the intensity distribution as a combination of meaningful latent factors and mixing co-efficients that can be used for genetic association analysis. This approach is motivated by a clinical hypothesis that COPD symptoms are caused by multiple coexisting disease processes. Our experiments show that the new features enhance the previously detected signal on chromosome 15 with respect to standard respiratory and imaging measurements.
Horky LL, Gerbaudo VH, Zaitsev A, Plesniak W, Hainer J, Govindarajulu U, Kikinis R, Dietrich J. Systemic chemotherapy decreases brain glucose metabolism. Ann Clin Transl Neurol. 2014;1 (10) :788-98.Abstract
OBJECTIVE: Cancer patients may experience neurologic adverse effects, such as alterations in neurocognitive function, as a consequence of chemotherapy. The mechanisms underlying such neurotoxic syndromes remain poorly understood. We here describe the temporal and regional effects of systemically administered platinum-based chemotherapy on glucose metabolism in the brain of cancer patients. METHODS: Using sequential FDG-PET/CT imaging prior to and after administration of chemotherapy, we retrospectively characterized the effects of intravenously administered chemotherapy on brain glucose metabolism in a total of 24 brain regions in a homogenous cohort of 10 patients with newly diagnosed non-small-cell lung cancer. RESULTS: Significant alterations of glucose metabolism were found in response to chemotherapy in all gray matter structures, including cortical structures, deep nuclei, hippocampi, and cerebellum. Metabolic changes were also notable in frontotemporal white matter (WM) network systems, including the corpus callosum, subcortical, and periventricular WM tracts. INTERPRETATION: Our data demonstrate a decrease in glucose metabolism in both gray and white matter structures associated with chemotherapy. Among the affected regions are those relevant to the maintenance of brain plasticity and global neurologic function. This study potentially offers novel insights into the spatial and temporal effects of systemic chemotherapy on brain metabolism in cancer patients.
Wachinger C, Golland P. Atlas-based Under-segmentation. Med Image Comput Comput Assist Interv. 2014;17 (Pt 1) :315-22.Abstract

We study the widespread, but rarely discussed, tendency of atlas-based segmentation to under-segment the organs of interest. Commonly used error measures do not distinguish between under- and over-segmentation, contributing to the problem. We explicitly quantify over- and under-segmentation in several typical examples and present a new hypothesis for the cause. We provide evidence that segmenting only one organ of interest and merging all surrounding structures into one label creates bias towards background in the label estimates suggested by the atlas. We propose a generative model that corrects for this effect by learning the background structures from the data. Inference in the model separates the background into distinct structures and consequently improves the segmentation accuracy. Our experiments demonstrate a clear improvement in several applications.

Wachinger C, Golland P, Reuter M. BrainPrint: Identifying Subjects by Their Brain. Med Image Comput Comput Assist Interv. 2014;17 (Pt 3) :41-8.Abstract

Introducing BrainPrint, a compact and discriminative representation of anatomical structures in the brain. BrainPrint captures shape information of an ensemble of cortical and subcortical structures by solving the 2D and 3D Laplace-Beltrami operator on triangular (boundary) and tetrahedral (volumetric) meshes. We derive a robust classifier for this representation that identifies the subject in a new scan, based on a database of brain scans. In an example dataset containing over 3000 MRI scans, we show that BrainPrint captures unique information about the subject's anatomy and permits to correctly classify a scan with an accuracy of over 99.8%. All processing steps for obtaining the compact representation are fully automated making this processing framework particularly attractive for handling large datasets.

Wachinger C, Golland P, Reuter M, Wells III WM. Gaussian Process Interpolation for Uncertainty Estimation in Image Registration. Med Image Comput Comput Assist Interv. 2014;17 (Pt 1) :267-74.Abstract

Intensity-based image registration requires resampling images on a common grid to evaluate the similarity function. The uncertainty of interpolation varies across the image, depending on the location of resampled points relative to the base grid. We propose to perform Bayesian inference with Gaussian processes, where the covariance matrix of the Gaussian process posterior distribution estimates the uncertainty in interpolation. The Gaussian process replaces a single image with a distribution over images that we integrate into a generative model for registration. Marginalization over resampled images leads to a new similarity measure that includes the uncertainty of the interpolation. We demonstrate that our approach increases the registration accuracy and propose an efficient approximation scheme that enables seamless integration with existing registration methods.

Pages