Georg Langs

Fast Active Appearance Model Search Using Canonical Correlation Analysis

A fast AAM search algorithm based on canonical correlation analysis (CCA-AAM) is introduced. It efficiently models the dependency between texture residuals and model parameters during search. Experiments show that CCA-AAMs, while requiring similar implementation effort, consistently outperform standard search with regard to convergence speed by a factor of four

Parcellating cortical functional networks in individuals

The capacity to identify the unique functional architecture of an individuals brain is a crucial step toward personalized medicine and understanding the neural basis of variation in human cognition and behavior. Here we developed a cortical parcellation approach to accurately map functional organization at the individual level using resting-state functional magnetic resonance imaging (fMRI). A population-based functional atlas and a map of inter-individual variability were employed to guide the iterative search for functional networks in individual subjects. Functional networks mapped by this approach were highly reproducible within subjects and effectively captured the variability across subjects, including individual differences in brain lateralization. The algorithm performed well across different subject populations and data types, including task fMRI data. The approach was then validated by invasive cortical stimulation mapping in surgical patients, suggesting potential for use in clinical applications.

Situating the default-mode network along a principal gradient of macroscale cortical organization

Significance We describe an overarching organization of large-scale connectivity that situates the default-mode network at the opposite end of a spectrum from primary sensory and motor regions. This topography, based on the differentiation of connectivity patterns, is also embedded in the spatial distance along the cortical surface between these respective systems. In addition, this connectivity gradient accounts for the respective positions of canonical networks and captures a functional spectrum from perception and action to more abstract cognitive functions. These results suggest that the default-mode network consists of regions at the top of a representational hierarchy that describe the current cognitive landscape in the most abstract terms. Understanding how the structure of cognition arises from the topographical organization of the cortex is a primary goal in neuroscience. Previous work has described local functional gradients extending from perceptual and motor regions to cortical areas representing more abstract functions, but an overarching framework for the association between structure and function is still lacking. Here, we show that the principal gradient revealed by the decomposition of connectivity data in humans and the macaque monkey is anchored by, at one end, regions serving primary sensory/motor functions and at the other end, transmodal regions that, in humans, are known as the default-mode network (DMN). These DMN regions exhibit the greatest geodesic distance along the cortical surface—and are precisely equidistant—from primary sensory/motor morphological landmarks. The principal gradient also provides an organizing spatial framework for multiple large-scale networks and characterizes a spectrum from unimodal to heteromodal activity in a functional metaanalysis. Together, these observations provide a characterization of the topographical organization of cortex and indicate that the role of the DMN in cognition might arise from its position at one extreme of a hierarchy, allowing it to process transmodal information that is unrelated to immediate sensory input.

The Prenatal Origin of Hemispheric Asymmetry: An In Utero Neuroimaging Study

Anatomical and functional hemispheric lateralization originates from differential gene expression and leads to asymmetric structural brain development, which initially appears in the perisylvian regions by 26 gestational weeks (GWs). In this in vivo neuroimaging study, we demonstrated a predominant pattern of temporal lobe (TL) asymmetry in a large cohort of human fetuses between 18 and 37 GWs. Over two-thirds of fetuses showed a larger, left-sided TL, combined with the earlier appearance of the right superior temporal sulcus by 23 GWs (vs. 25 GWs on the left side), which was also deeper than its left counterpart in the majority of cases (94.2%). Shape analysis detected highly significant differences in the contour of the right and left TLs by 20 GWs. Thus, fetal hemispheric asymmetry can be detected in utero, opening new diagnostic possibilities for the assessment of diseases that are believed to be linked to atypical hemispheric lateralization.

Global localization of 3D anatomical structures by pre-filtered Hough Forests and discrete optimization

Graphical abstract Highlights ► Automatic localization of landmarks in complex, repetitive anatomical structures. ► Random Forest classifiers for every landmark as a pre-filtering stage. ► Hough regression model for refining the landmark candidate positions. ► Parts-based model of global landmark topology to select the final landmark positions. ► Results on three challenging data sets, median residuals of 0.80 mm, 1.19 mm, 2.71 mm.

VISCERAL: towards large data in medical imaging -- challenges and directions

The increasing amount of medical imaging data acquired in clinical practice holds a tremendous body of diagnostically relevant information. Only a small portion of these data are accessible during clinical routine or research due to the complexity, richness, high dimensionality and size of the data. There is consensus in the community that leaps in this regard are hampered by the lack of large bodies of data shared across research groups and an associated definition of joint challenges on which development can focus. In this paper we describe the objectives of the project VISCERAL. It will provide the means to jump---start this process by providing access to unprecedented amounts of real world imaging data annotated through experts and by using a community effort to generate a large corpus of automatically generated standard annotations. To this end, Visceral will conduct two competitions that tackle large scale medical image data analysis in the fields of anatomy detection, and content---based image retrieval, in this case the retrieval of similar medical cases using visual data and textual radiology reports.

3D and Infrared Face Reconstruction from RGB data using Canonical Correlation Analysis

In this paper, we apply a multiple regression method based on canonical correlation analysis (CCA) to face data modelling. CCA is a factor analysis method which exploits the correlation between two high dimensional signals. We first use CCA to perform 3D face reconstruction and in a separate application we predict near-infrared (NIR) face texture. In both cases, the input data are color (RGB) face images. Experiments show, that due to the correlation between input and output signal, only a small number of canonical factors are needed to describe the functional relation of RGB images to the respective output (NIR images and 3D depth maps) with reasonable accuracy

Vision pyramids that do not grow too high

In irregular pyramids, their vertical structure is not determined beforehand as in regular pyramids. We present three methods, all based on maximal independent sets from graph theory, with the aim to simulate the major sampling properties of the regular counterparts: good coverage of the higher resolution level, not too large sampling gaps and, most importantly, the resulting height, e.g. the number of levels to reach the apex. We show both theoretically and experimentally that the number of vertices can be reduced by a factor of 2.0 at each level. The plausibility of log (diameter) pyramids is supported by psychological and psychophysical considerations. Their technical relevance is demonstrated by enhancing appearance-based object recognition. An irregular pyramid hypothesis generation for robust PCA through top-down attention mechanisms achieves higher speed and quality than regular pyramids and non-pyramidal approaches.

Shape priors and discrete MRFs for knowledge-based segmentation

In this paper we introduce a new approach to knowledge-based segmentation. Our method consists of a novel representation to model shape variations as well as an efficient inference procedure to fit the model to new data. The considered shape model is similarity-invariant and refers to an incomplete graph that consists of intra and intercluster connections representing the inter-dependencies of control points. The clusters are determined according to the co-dependencies of the deformations of the control points within the training set. The connections between the components of a cluster represent the local structure while the connections between the clusters account for the global structure. The distributions of the normalized distances between the connected control points encode the prior model. During search, this model is used together with a discrete Markov random field (MRF) based segmentation, where the unknown variables are the positions of the control points in the image domain. To encode the image support, a Voronoi decomposition of the domain is considered and regional based statistics are used. The resulting model is computationally efficient, can encode complex statistical models of shape variations and benefits from the image support of the entire spatial domain.

Detecting stable distributed patterns of brain activation using Gini contrast

The relationship between spatially distributed fMRI patterns and experimental stimuli or tasks offers insights into cognitive processes beyond those traceable from individual local activations. The multivariate properties of the fMRI signals allow us to infer interactions among individual regions and to detect distributed activations of multiple areas. Detection of task-specific multivariate activity in fMRI data is an important open problem that has drawn much interest recently. In this paper, we study and demonstrate the benefits of random forest classifiers and the associated Gini importance measure for selecting voxel subsets that form a multivariate neural response. The Gini importance measure quantifies the predictive power of a particular feature when considered as part of the entire pattern. The measure is based on a random sampling of fMRI time points and voxels. As a consequence the resulting voxel score, or Gini contrast, is highly reproducible and reliably includes all informative features. The method does not rely on a priori assumptions about the signal distribution, a specific statistical or functional model or regularization. Instead, it uses the predictive power of features to characterize their relevance for encoding task information. The Gini contrast offers an additional advantage of directly quantifying the task-relevant information in a multiclass setting, rather than reducing the problem to several binary classification subproblems. In a multicategory visual fMRI study, the proposed method identified informative regions not detected by the univariate criteria, such as the t-test or the F-test. Including these additional regions in the feature set improves the accuracy of multicategory classification. Moreover, we demonstrate higher classification accuracy and stability of the detected spatial patterns across runs than the traditional methods such as the recursive feature elimination used in conjunction with support vector machines.