nips nips2010 nips2010-97 knowledge-graph by maker-knowledge-mining

97 nips-2010-Functional Geometry Alignment and Localization of Brain Areas

Source: pdf

Author: Georg Langs, Yanmei Tie, Laura Rigolo, Alexandra Golby, Polina Golland

Abstract: Matching functional brain regions across individuals is a challenging task, largely due to the variability in their location and extent. It is particularly difﬁcult, but highly relevant, for patients with pathologies such as brain tumors, which can cause substantial reorganization of functional systems. In such cases spatial registration based on anatomical data is only of limited value if the goal is to establish correspondences of functional areas among different individuals, or to localize potentially displaced active regions. Rather than rely on spatial alignment, we propose to perform registration in an alternative space whose geometry is governed by the functional interaction patterns in the brain. We ﬁrst embed each brain into a functional map that reﬂects connectivity patterns during a fMRI experiment. The resulting functional maps are then registered, and the obtained correspondences are propagated back to the two brains. In application to a language fMRI experiment, our preliminary results suggest that the proposed method yields improved functional correspondences across subjects. This advantage is pronounced for subjects with tumors that affect the language areas and thus cause spatial reorganization of the functional regions. 1

Reference: text

Summary: the most important sentenses genereted by tfidf model

sentIndex sentText sentNum sentScore

1 edu Abstract Matching functional brain regions across individuals is a challenging task, largely due to the variability in their location and extent. [sent-12, score-0.751]

2 It is particularly difﬁcult, but highly relevant, for patients with pathologies such as brain tumors, which can cause substantial reorganization of functional systems. [sent-13, score-0.668]

3 In such cases spatial registration based on anatomical data is only of limited value if the goal is to establish correspondences of functional areas among different individuals, or to localize potentially displaced active regions. [sent-14, score-1.317]

4 Rather than rely on spatial alignment, we propose to perform registration in an alternative space whose geometry is governed by the functional interaction patterns in the brain. [sent-15, score-1.082]

5 We ﬁrst embed each brain into a functional map that reﬂects connectivity patterns during a fMRI experiment. [sent-16, score-0.82]

6 The resulting functional maps are then registered, and the obtained correspondences are propagated back to the two brains. [sent-17, score-0.606]

7 In application to a language fMRI experiment, our preliminary results suggest that the proposed method yields improved functional correspondences across subjects. [sent-18, score-0.612]

8 This advantage is pronounced for subjects with tumors that affect the language areas and thus cause spatial reorganization of the functional regions. [sent-19, score-0.806]

9 1 Introduction Alignment of functional neuroanatomy across individuals forms the basis for the study of the functional organization of the brain. [sent-20, score-0.916]

10 It is important for localization of speciﬁc functional regions and characterization of functional systems in a population. [sent-21, score-1.064]

11 Furthermore, the characterization of variability in location of speciﬁc functional areas is itself informative of the mechanisms of brain formation and reorganization. [sent-22, score-0.618]

12 In this paper we propose to align neuroanatomy based on the functional geometry of fMRI signals during speciﬁc cognitive processes. [sent-23, score-0.71]

13 For each subject, we construct a map based on spectral embedding of the functional connectivity of the fMRI signals and register those maps to establish correspondence between functional areas in different subjects. [sent-24, score-1.423]

14 Standard registration methods that match brain anatomy, such as the Talairach normalization [21] or non-rigid registration techniques like [10, 20], accurately match the anatomical structures across individuals. [sent-25, score-1.209]

15 However the variability of the functional locations relative to anatomy can be substantial [8, 22, 23], which limits the usefulness of such alignment in functional experiments. [sent-26, score-1.169]

16 1 Registration based on anatomical data brain 1 registration brain 2 Registration based on the functional geometry brain 1 embedding registration embedding brain 2 Figure 1: Standard anatomical registration and the proposed functional geometry alignment. [sent-28, score-3.655]

17 Functional geometry alignment matches the diffusion maps of fMRI signals of two subjects. [sent-29, score-0.665]

18 Integrating functional features into the registration process promises to alleviate this challenge. [sent-30, score-0.835]

19 In [7] registration of a population of subjects is accomplished by using the functional connectivity pattern of cortical points as a descriptor of the cortical surface. [sent-33, score-1.265]

20 All the methods described above rely on a spatial reference frame for registration, and use the functional characteristics as a feature vector of individual cortical surface points or the entire surface. [sent-35, score-0.571]

21 This might have limitations in the case of severe pathological changes that cause a substantial reorganization of the functional structures. [sent-36, score-0.505]

22 Examples include the migration to the other hemisphere, changes in topology of the functional maps, or substitution of functional roles played by one damaged region with another area. [sent-37, score-0.906]

23 In contrast, our approach to functional registration does not rely on spatial consistency. [sent-38, score-0.871]

24 Previously we used spectral methods to map voxels of a fMRI sequence into a space that captures joint functional characteristics of brain regions [14]. [sent-40, score-0.874]

25 Here we propose and demonstrate a functional registration method that operates in a space that reﬂects functional connectivity patterns of the brain. [sent-45, score-1.469]

26 In this space, the connectivity structure is captured by a structured distribution of points, or functional geometry. [sent-46, score-0.602]

27 To register functional regions among two individuals, we ﬁrst embed both fMRI volumes independently, and then obtain correspondences by matching the two point distributions in the functional geometry. [sent-50, score-1.192]

28 We argue that such a representation offers a more natural view of the co-activation patterns than the spatial structure augmented with functional feature vectors. [sent-51, score-0.492]

29 The functional geometry can handle long-range reorganizations and topological variability in the functional organization of different individuals. [sent-52, score-1.055]

30 Furthermore, by translating connectivity strength to distances we are able to regularize the registration effectively. [sent-53, score-0.589]

31 Strong connections are preserved during registration in the map by penalizing high-frequencies in the map deformation ﬁeld. [sent-54, score-0.568]

32 The functional connectivity pattern for a speciﬁc area provides a reﬁned representation of its activity that can augment the individual activation pattern. [sent-56, score-0.678]

33 Our approach is to utilize connectivity information to improve localization of the functional areas in tumor patients. [sent-57, score-0.927]

34 Our method transfers the connectivity patterns from healthy subjects to tumor patients. [sent-58, score-0.6]

35 The functional geometry we use is largely independent of the underlying anatomical organization. [sent-60, score-0.871]

36 As a consequence, our method handles substantial changes in spatial arrangement of the functional areas that typically present sig2 niﬁcant challenges for anatomical registration methods. [sent-61, score-1.212]

37 Such functional priors promise to improve detection accuracy in the challenging case of language area localization. [sent-62, score-0.507]

38 While standard detection identiﬁes the regions whose activation is correlated with the experimental protocol, we seek a more detailed description of the functional roles of the detected regions, based on the functional connectivity patterns. [sent-68, score-1.252]

39 We evaluate the method on healthy control subjects and brain tumor patients who perform language mapping tasks. [sent-69, score-0.661]

40 Our initial experimental results indicate that the proposed functional alignment outperforms anatomical registration in predicting activation in target subjects (both healthy controls and patients). [sent-72, score-1.701]

41 Furthermore functional alignment can handle substantial reorganizations and is much less affected by the tumor presence than anatomical registration. [sent-73, score-1.235]

42 2 Embedding the brain in a functional geometry We ﬁrst review the representation of the functional geometry that captures the co-activation patterns in a diffusion map deﬁned on the fMRI voxels [6, 14]. [sent-74, score-1.587]

43 The global structure of the functional connectivity is reﬂected in the point distribution Ψt . [sent-97, score-0.602]

44 This functional geometry is governed by the diffusion distance Dt on the graph: Dt (k, l) is deﬁned through the probability of traveling between two vertices k and l by taking all paths of at most t steps 3 a. [sent-99, score-0.709]

45 The two central columns show plots of the ﬁrst three dimensions of the embedding in the functional geometry after coarse rotational alignment. [sent-102, score-0.705]

46 The transition probabilities are based on the functional connectivity of pairs of nodes. [sent-106, score-0.602]

47 Thus the diffusion distance integrates the connectivity values over possible paths that connect two points and deﬁnes a geometry that captures the entirety of the connectivity structure. [sent-107, score-0.648]

48 The functional relations between fMRI signals are translated into spatial distances in the functional geometry [14]. [sent-114, score-1.133]

49 The resulting maps are the basis for the functional registration of the fMRI volumes. [sent-117, score-0.912]

50 3 Functional geometry alignment Let Ψ0 , and Ψ1 be the functional maps of two subjects. [sent-118, score-0.936]

51 The points in the maps correspond to voxels and registration of the maps establishes correspondences between brain regions of the subjects. [sent-120, score-1.075]

52 Our goal is to estimate correspondences of points in the two maps based on the structure in the two distributions determined by the functional connectivity structure in the data. [sent-121, score-0.814]

53 We perform registration in the functional space by non-rigidly deforming the distributions until their overlap is maximized. [sent-122, score-0.883]

54 However, for successful alignment it is essential that the embedding is consistent between the subjects, and we have to match the nuisance parameters of the embedding during alignment. [sent-125, score-0.46]

55 We initialise the registration using Procrustes analysis [4] so that the distance between a randomly chosen subset of vertices from the same anatomical part of the brain is minimised in functional space. [sent-140, score-1.245]

56 This typically resolves ambiguity in the embedding with respect to rotation and the order of eigenvectors in the functional space. [sent-141, score-0.526]

57 We employ the Coherent Point Drift algorithm for the subsequent non-linear registration of the functional maps [16]. [sent-142, score-0.912]

58 The ﬁrst term is a Gaussian kernel, that generates a continuous distribution for the entire map Ψ0 in the functional space Rw . [sent-145, score-0.465]

59 The regularization term induces a high penalty on changing strong functional connectivity relationships among voxels (which correspond to small distances or clusters in the map). [sent-153, score-0.708]

60 Once the registration of the two distributions in the functional geometry is completed, we assign correspondences between points in Ψ0 and Ψ1 by a simple matching algorithm that for any point in one map chooses the closest point in the other map. [sent-156, score-1.228]

61 4 Validation of Alignment To validate the functional registration quantitatively we align pairs of subjects via (i) the proposed functional geometry alignment, and (ii) the anatomical non-rigid demons registration [25, 28]. [sent-157, score-2.255]

62 After alignment we evaluate the quality of the ﬁt by (1) the accuracy of predicting the location of the active areas in the target subject and (2) the inter-subject correlation of BOLD signals after alignment. [sent-161, score-0.632]

63 The green region in the healthy subject is mapped to the red region by the proposed functional registration and to the yellow region by anatomical registration. [sent-166, score-1.455]

64 Note that the functional alignment places the region narrowly around the tumor location, while the anatomical registration result intersects with the tumor. [sent-167, score-1.653]

65 The slice of the anatomical scan with the tumor and the zoomed visualization of the registration results (fourth column) are also shown. [sent-168, score-0.89]

66 That is, can we transfer evidence for the activation of speciﬁc regions between subjects, for example between healthy controls and tumor patients? [sent-170, score-0.506]

67 We validate the accuracy of localizing activated regions in a target volume by measuring the average correlation of the t-maps (based on the standard GLM) between the source and the corresponding target regions after registration. [sent-173, score-0.706]

68 Additionally, we measure the overlap between regions in the target image to which the above-threshold source regions are mapped, and the above-threshold regions in the target image. [sent-178, score-0.721]

69 Note that for the registration itself neither the inter-subject correlation of fMRI signals, nor the correlation of t-maps is used. [sent-179, score-0.569]

70 Across-subject correlation of the fMRI signals indicates a relationship between the underlying functional processes. [sent-183, score-0.573]

71 We are interested in two speciﬁc scenarios: (i) above-threshold regions in the target image that were matched to above-threshold regions in the source image, and (ii) below-threshold regions in the target image that were matched to abovethreshold regions in the source image. [sent-184, score-1.008]

72 5 Experimental Results We demonstrate the method on a set of 6 control subjects and 3 patients with low-grade tumors in one of the regions associated with language processing. [sent-187, score-0.461]

73 1 Above-threshold region in source subject Above-threshold region in target subject Region corresponding to abovethreshold region in source subject after alignment A. [sent-199, score-0.888]

74 Correlation distribution of corresponding t-values after functional geometry alignment (FGA) and anatomical registration (AR) for control-control and control-tumor matches. [sent-212, score-1.538]

75 correlation of the BOLD signals for activated regions mapped to activated regions (left) and activated regions mapped to sub-threshold regions (right). [sent-214, score-1.074]

76 For each subject, anatomical T1 MRI data was acquired and registered to the functional data. [sent-219, score-0.737]

77 3 illustrates the effect of a tumor in a language region, and the corresponding registration results. [sent-222, score-0.705]

78 An area of the brain associated with language is registered from a control subject to a tumor patient. [sent-223, score-0.548]

79 The location of the tumor is shown in blue; the regions resulting from functional and anatomical registration are indicated in red (FGA), and yellow (AR), respectively. [sent-224, score-1.491]

80 While anatomical registration creates a large overlap between the mapped region and the tumor, functional geometry alignment maps the region to a plausible area narrowly surrounding the tumor. [sent-225, score-1.823]

81 Functional geometry alignment achieves signiﬁcantly higher correlation of t-values than anatomical registration (0. [sent-229, score-1.193]

82 Anatomical registration performance drops signiﬁcantly when registering a control subject and a tumor patient, compared to a pair of control subjects (0. [sent-233, score-0.872]

83 For functional geometry alignment this drop is not signiﬁcant (0. [sent-238, score-0.859]

84 Functional geometry alignment predicts 50% of the above-threshold in the target brain, while anatomical registration predicts 29% (Fig. [sent-243, score-1.201]

85 These ﬁndings indicate that the functional alignment of language regions among source and target subjects is less affected by the presence of a tumor and the associated reorganization than the matching of functional regions by anatomical registration. [sent-245, score-2.354]

86 Furthermore the functional alignment has better predictive power for the activated regions in the target subject for both control-control and control-patient pairs. [sent-246, score-1.086]

87 In contrast and as expected, the matching of functional regions by anatomical alignment is affected by the tumor. [sent-248, score-1.159]

88 If both source region and corresponding target region are above-threshold the average correlation between the source and target signals is signiﬁcantly higher for functional geometry alignment (0. [sent-250, score-1.446]

89 This signiﬁcant difference between functional geometry alignment and anatomical registration vanishes for regions mapped from below-threshold regions in the source subject. [sent-260, score-1.956]

90 The fMRI signal correlation in the source and the target region is higher for functional alignment if the source region is activated. [sent-263, score-1.137]

91 The functional connectivity 7 structure is sufﬁciently consistent to support an alignment of the functional geometry between subjects. [sent-265, score-1.461]

92 We demonstrate that our alignment improves inter-subject correlation for activated source regions and their target regions, but not for the non-active source regions. [sent-267, score-0.799]

93 6 Conclusion In this paper we propose and demonstrate a method for registering neuroanatomy based on the functional geometry of fMRI signals. [sent-269, score-0.665]

94 The method offers an alternative to anatomical registration; it relies on matching a spectral embedding of the functional connectivity patterns of two fMRI volumes. [sent-270, score-1.076]

95 Initial results indicate that the structure in the diffusion map that reﬂects functional connectivity enables accurate matching of functional regions. [sent-271, score-1.188]

96 When used to predict the activation in a target fMRI volume the proposed functional registration exhibits higher predictive power than the anatomical registration. [sent-272, score-1.291]

97 Moreover it is more robust to pathologies and the associated changes in the spatial organization of functional areas. [sent-273, score-0.46]

98 Further research is necessary to evaluate the predictive power of the method for localization of speciﬁc functional areas. [sent-276, score-0.515]

99 Functional topography: multidimensional scaling and functional connectivity in the brain. [sent-356, score-0.602]

100 Statistical parametric maps in functional imaging: a general linear approach. [sent-359, score-0.501]

similar papers computed by tfidf model

tfidf for this paper:

wordName wordTfidf (topN-words)

[('functional', 0.424), ('registration', 0.411), ('fmri', 0.343), ('anatomical', 0.268), ('alignment', 0.256), ('tumor', 0.211), ('geometry', 0.179), ('connectivity', 0.178), ('regions', 0.15), ('brain', 0.119), ('subjects', 0.11), ('voxels', 0.106), ('correspondences', 0.105), ('embedding', 0.102), ('target', 0.087), ('fga', 0.084), ('language', 0.083), ('diffusion', 0.083), ('correlation', 0.079), ('activated', 0.079), ('maps', 0.077), ('activation', 0.076), ('source', 0.074), ('signals', 0.07), ('healthy', 0.069), ('localization', 0.066), ('subject', 0.065), ('region', 0.058), ('reorganization', 0.056), ('cortical', 0.056), ('deformation', 0.05), ('tumors', 0.049), ('areas', 0.048), ('registered', 0.045), ('patients', 0.044), ('mapped', 0.044), ('ar', 0.043), ('langs', 0.042), ('map', 0.041), ('anatomy', 0.04), ('matching', 0.038), ('neuroanatomy', 0.037), ('spatial', 0.036), ('nih', 0.035), ('spectral', 0.034), ('thirion', 0.034), ('rw', 0.034), ('bold', 0.033), ('patterns', 0.032), ('voxel', 0.032), ('patient', 0.031), ('individuals', 0.031), ('graph', 0.031), ('points', 0.03), ('matched', 0.029), ('ects', 0.029), ('abovethreshold', 0.028), ('demons', 0.028), ('fischl', 0.028), ('georg', 0.028), ('intersubject', 0.028), ('myronenko', 0.028), ('pinel', 0.028), ('polina', 0.028), ('procrustes', 0.028), ('reorganizations', 0.028), ('roche', 0.028), ('rsj', 0.028), ('sereno', 0.028), ('talairach', 0.028), ('glm', 0.028), ('neuroimage', 0.028), ('location', 0.027), ('signal', 0.027), ('xk', 0.026), ('kj', 0.026), ('xl', 0.026), ('embed', 0.026), ('reference', 0.025), ('substantial', 0.025), ('control', 0.025), ('predictive', 0.025), ('cerebral', 0.025), ('penalizing', 0.025), ('epilepsy', 0.025), ('displaced', 0.025), ('conroy', 0.025), ('deforming', 0.025), ('frith', 0.025), ('narrowly', 0.025), ('register', 0.025), ('registering', 0.025), ('exhibit', 0.024), ('vertices', 0.023), ('cortex', 0.023), ('affected', 0.023), ('dt', 0.023), ('overlap', 0.023), ('coordinate', 0.023), ('bryan', 0.023)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.99999911 97 nips-2010-Functional Geometry Alignment and Localization of Brain Areas

Author: Georg Langs, Yanmei Tie, Laura Rigolo, Alexandra Golby, Polina Golland

2 0.3900249 44 nips-2010-Brain covariance selection: better individual functional connectivity models using population prior

Author: Gael Varoquaux, Alexandre Gramfort, Jean-baptiste Poline, Bertrand Thirion

Abstract: Spontaneous brain activity, as observed in functional neuroimaging, has been shown to display reproducible structure that expresses brain architecture and carries markers of brain pathologies. An important view of modern neuroscience is that such large-scale structure of coherent activity reﬂects modularity properties of brain connectivity graphs. However, to date, there has been no demonstration that the limited and noisy data available in spontaneous activity observations could be used to learn full-brain probabilistic models that generalize to new data. Learning such models entails two main challenges: i) modeling full brain connectivity is a difﬁcult estimation problem that faces the curse of dimensionality and ii) variability between subjects, coupled with the variability of functional signals between experimental runs, makes the use of multiple datasets challenging. We describe subject-level brain functional connectivity structure as a multivariate Gaussian process and introduce a new strategy to estimate it from group data, by imposing a common structure on the graphical model in the population. We show that individual models learned from functional Magnetic Resonance Imaging (fMRI) data using this population prior generalize better to unseen data than models based on alternative regularization schemes. To our knowledge, this is the ﬁrst report of a cross-validated model of spontaneous brain activity. Finally, we use the estimated graphical model to explore the large-scale characteristics of functional architecture and show for the ﬁrst time that known cognitive networks appear as the integrated communities of functional connectivity graph. 1

3 0.38688532 128 nips-2010-Infinite Relational Modeling of Functional Connectivity in Resting State fMRI

Author: Morten Mørup, Kristoffer Madsen, Anne-marie Dogonowski, Hartwig Siebner, Lars K. Hansen

Abstract: Functional magnetic resonance imaging (fMRI) can be applied to study the functional connectivity of the neural elements which form complex network at a whole brain level. Most analyses of functional resting state networks (RSN) have been based on the analysis of correlation between the temporal dynamics of various regions of the brain. While these models can identify coherently behaving groups in terms of correlation they give little insight into how these groups interact. In this paper we take a different view on the analysis of functional resting state networks. Starting from the deﬁnition of resting state as functional coherent groups we search for functional units of the brain that communicate with other parts of the brain in a coherent manner as measured by mutual information. We use the inﬁnite relational model (IRM) to quantify functional coherent groups of resting state networks and demonstrate how the extracted component interactions can be used to discriminate between functional resting state activity in multiple sclerosis and normal subjects. 1

4 0.32879704 123 nips-2010-Individualized ROI Optimization via Maximization of Group-wise Consistency of Structural and Functional Profiles

Author: Kaiming Li, Lei Guo, Carlos Faraco, Dajiang Zhu, Fan Deng, Tuo Zhang, Xi Jiang, Degang Zhang, Hanbo Chen, Xintao Hu, Steve Miller, Tianming Liu

Abstract: Functional segregation and integration are fundamental characteristics of the human brain. Studying the connectivity among segregated regions and the dynamics of integrated brain networks has drawn increasing interest. A very controversial, yet fundamental issue in these studies is how to determine the best functional brain regions or ROIs (regions of interests) for individuals. Essentially, the computed connectivity patterns and dynamics of brain networks are very sensitive to the locations, sizes, and shapes of the ROIs. This paper presents a novel methodology to optimize the locations of an individual's ROIs in the working memory system. Our strategy is to formulate the individual ROI optimization as a group variance minimization problem, in which group-wise functional and structural connectivity patterns, and anatomic profiles are defined as optimization constraints. The optimization problem is solved via the simulated annealing approach. Our experimental results show that the optimized ROIs have significantly improved consistency in structural and functional profiles across subjects, and have more reasonable localizations and more consistent morphological and anatomic profiles. 1 Int ro ducti o n The human brainâ€™s function is segregated into distinct regions and integrated via axonal fibers [1]. Studying the connectivity among these regions and modeling their dynamics and interactions has drawn increasing interest and effort from the brain imaging and neuroscience communities [2-6]. For example, recently, the Human Connectome Project [7] and the 1000 Functional Connectomes Project [8] have embarked to elucidate large-scale connectivity patterns in the human brain. For traditional connectivity analysis, a variety of models including DCM (dynamics causal modeling), GCM (Granger causality modeling) and MVA (multivariate autoregressive modeling) are proposed [6, 9-10] to model the interactions of the ROIs. A fundamental issue in these studies is how to accurately identify the ROIs, which are the structural substrates for measuring connectivity. Currently, this is still an open, urgent, yet challenging problem in many brain imaging applications. From our perspective, the major challenges come from uncertainties in ROI boundary definition, the tremendous variability across individuals, and high nonlinearities within and around ROIs. Current approaches for identifying brain ROIs can be broadly classified into four categories. The first is manual labeling by experts using their domain knowledge. The second is a data-driven clustering of ROIs from the brain image itself. For instance, the ReHo (regional homogeneity) algorithm [11] has been used to identify regional homogeneous regions as ROIs. The third is to predefine ROIs in a template brain, and warp them back to the individual space using image registration [12]. Lastly, ROIs can be defined from the activated regions observed during a task-based fMRI paradigm. While fruitful results have been achieved using these approaches, there are various limitations. For instance, manual labeling is difficult to implement for large datasets and may be vulnerable to inter-subject and intra-subject variation; it is difficult to build correspondence across subjects using data-driven clustering methods; warping template ROIs back to individual space is subject to the accuracy of warping techniques and the anatomical variability across subjects. Even identifying ROIs using task-based fMRI paradigms, which is regarded as the standard approach for ROI identification, is still an open question. It was reported in [13] that many imaging-related variables including scanner vender, RF coil characteristics (phase array vs. volume coil), k-space acquisition trajectory, reconstruction algorithms, susceptibility -induced signal dropout, as well as field strength differences, contribute to variations in ROI identification. Other researchers reported that spatial smoothing, a common preprocessing technique in fMRI analysis to enhance SNR, may introduce artificial localization shift s (up to 12.1mm for Gaussian kernel volumetric smoothing) [14] or generate overly smoothed activation maps that may obscure important details [15]. For example, as shown in Fig.1a, the local maximum of the ROI was shifted by 4mm due to the spatial smoothing process. Additionally, its structural profile (Fig.1b) was significantly altered. Furthermore, group-based activation maps may show different patterns from an individual's activation map; Fig.1c depicts such differences. The top panel is the group activation map from a working memory study, while the bottom panel is the activation map of one subject in the study. As we can see from the highlighted boxes, the subject has less activated regions than the group analysis result. In conclusion, standard analysis of task-based fMRI paradigm data is inadequate to accurately localize ROIs for each individual. Fig.1. (a): Local activation map maxima (marked by the cross) shift of one ROI due to spatial volumetric smoothing. The top one was detected using unsmoothed data while the bottom one used smoothed data (FWHM: 6.875mm). (b): The corresponding fibers for the ROIs in (a). The ROIs are presented using a sphere (radius: 5mm). (c): Activation map differences between the group (top) and one subject (bottom). The highlighted boxes show two of the missing activated ROIs found from the group analysis. Without accurate and reliable individualized ROIs, the validity of brain connectivity analysis, and computational modeling of dynamics and interactions among brain networks , would be questionable. In response to this fundamental issue, this paper presents a novel computational methodology to optimize the locations of an individual's ROIs initialized from task-based fMRI. We use the ROIs identified in a block-based working memory paradigm as a test bed application to develop and evaluate our methodology. The optimization of ROI locations was formulated as an energy minimization problem, with the goal of jointly maximizing the group-wise consistency of functional and structural connectivity patterns and anatomic profiles. The optimization problem is solved via the well-established simulated annealing approach. Our experimental results show that the optimized ROIs achieved our optimization objectives and demonstrated promising results. 2 Mat eria l s a nd Metho ds 2.1 Data acquisition and preprocessing Twenty-five university students were recruited to participate in this study. Each participant performed an fMRI modified version of the OSPAN task (3 block types: OSPAN, Arithmetic, and Baseline) while fMRI data was acquired. DTI scans were also acquired for each participant. FMRI and DTI scans were acquired on a 3T GE Signa scanner. Acquisition parameters were as follows : fMRI: 64x64 matrix, 4mm slice thickness, 220mm FOV, 30 slices, TR=1.5s, TE=25ms, ASSET=2; DTI: 128x128 matrix, 2mm slice thickness, 256mm FOV, 60 slices, TR=15100ms, TE= variable, ASSET=2, 3 B0 images, 30 optimized gradient directions, b-value=1000). Each participantâ€™s fMRI data was analyzed using FSL. Individual activation map Fig.2. working memory reflecting the OSPAN (OSPAN > Baseline) contrast was used. In ROIs mapped on a total, we identified the 16 highest activated ROIs, including left WM/GM surface and right insula, left and right medial frontal gyrus, left and right precentral gyrus, left and right paracingulate gyrus, left and right dorsolateral prefrontal cortex, left and right inferior parietal lobule, left occipital pole, right frontal pole, right lateral occipital gyrus, and left and right precuneus. Fig.2 shows the 16 ROIs mapped onto a WM(white matter)/GM(gray matter) cortical surface. For some individuals, there may be missing ROIs on their activation maps. Under such condition, we adapted the group activation map as a guide to find these ROIs using linear registration. DTI pre-processing consisted of skull removal, motion correction, and eddy current correction. After the pre-processing, fiber tracking was performed using MEDINRIA (FA threshold: 0.2; minimum fiber length: 20). Fibers were extended along their tangent directions to reach into the gray matter when necessary. Brain tissue segmentation was conducted on DTI data by the method in [16] and the cortical surface was reconstructed from the tissue maps using the marching cubes algorithm. The cortical surface was parcellated into anatomical regions using the HAMMER tool [17]. DTI space was used as the standard space from which to generate the GM (gray matter) segmentation and from which to report the ROI locations on the cortical surface. Since the fMRI and DTI sequences are both EPI (echo planar imaging) sequences, their distortions tend to be similar and the misalignment between DTI and fMRI images is much less than that between T1 and fMRI images [18]. Co-registration between DTI and fMRI data was performed using FSL FLIRT [12]. The activated ROIs and tracked fibers were then mapped onto the cortical surface for joint modeling. 2.2 Joint modeling of anatomical, structural and functional profiles Despite the high degree of variability across subjects, there are several aspects of regularity on which we base the proposed solution. Firstly, across subjects, the functional ROIs should have similar anatomical locations, e.g., similar locations in the atlas space. Secondly, these ROIs should have similar structural connectivity profiles across subjects. In other words, fibers penetrating the same functional ROIs should have at least similar target regions across subjects. Lastly, individual networks identified by task-based paradigms, like the working memory network we adapted as a test bed in this paper, should have similar functional connectivity pattern across subjects. The neuroscience bases of the above premises include: 1) structural and functional brain connectivity are closely related [19], and cortical gyrification and axongenesis processes are closely coupled [20]; Hence, it is reasonable to put these three types of information in a joint modeling framework. 2) Extensive studies have already demonstrated the existence of a common structural and functional architecture of the human brain [21, 22], and it makes sense to assume that the working memory network has similar structural and functional connectivity patterns across individuals. Based on these premises, we proposed to optimize the locations of individual functional ROIs by jointly modeling anatomic profiles, structural connectivity patterns, and functional connectivity patterns, as illustrated in Fig 3. The Fig.3. ROIs optimization scheme. goal was to minimize the group-wise variance (or maximize group-wise consistency) of these jointly modeled profiles. Mathematically, we modeled the group-wise variance as energy E as follows. A ROI from fMRI analysis was mapped onto the surface, and is represented by a center vertex and its neighborhood. Suppose đ?‘… đ?‘–đ?‘— is the ROI region j on the cortical surface of subject i identified in Section 2.1; we find a corresponding surface ROI region đ?‘† đ?‘–đ?‘— so that the energy E (contains energy from n subjects, each with m ROIs) is minimized: đ??¸ = đ??¸ đ?‘Ž (đ?œ† đ??¸ đ?‘? âˆ’đ?‘€ đ??¸ đ?‘? đ?œŽ đ??¸đ?‘? + (1 âˆ’ đ?œ†) đ??¸ đ?‘“ âˆ’đ?‘€ đ??¸ đ?‘“ đ?œŽđ??¸đ?‘“ ) (1) where Ea is the anatomical constraint; Ec is the structural connectivity constraint, M Ec and ď ł E are the mean and standard deviation of Ec in the searching space; E f is the functional c connectivity constraint, M E f and ď ł E f are the mean and standard deviation of E f respectively; and ď Ź is a weighting parameter between 0 and 1. If not specified, and m is the number of ROIs in this paper. The details of these energy terms are provided in the following sections. 2.2.1 n is the number of subjects, Anatomical constraint energy Anatomical constraint energy Ea is defined to ensure that the optimized ROIs have similar anatomical locations in the atlas space (Fig.4 shows an example of ROIs of 15 randomly selected subjects in the atlas space). We model the locations for all ROIs in the atlas space using a Gaussian model (mean: đ?‘€ đ?‘‹ đ?‘— ,and standard deviation: ď ł X j for ROI j ). The model parameters were estimated using the initial locations obtained from Section 2.1. Let X ij be the center coordinate of region Sij in the atlas space, then Ea is expressed as đ??¸đ?‘Ž = { 1 đ?‘’ đ?‘‘đ?‘šđ?‘Žđ?‘Ľâˆ’1 Fig.4. ROI distributions in Atlas space. (đ?‘‘đ?‘šđ?‘Žđ?‘Ľâ‰¤1) (đ?‘‘đ?‘šđ?‘Žđ?‘Ľ>1) (2) â€– , 1 â‰¤ đ?‘– â‰¤ đ?‘›; 1 â‰¤ đ?‘— â‰¤ đ?‘š. } (3) where đ?‘‘đ?‘šđ?‘Žđ?‘Ľ = đ?‘€đ?‘Žđ?‘Ľ { â€– đ?‘‹ đ?‘–đ?‘— âˆ’đ?‘€ đ?‘‹ đ?‘— 3đ?œŽ đ?‘‹ đ?‘— Under the above definition, if any X ij is within the range of 3s X from the distribution model j center M X , the anatomical constraint energy will always be one; if not, there will be an j exponential increase of the energy which punishes the possible involvement of outliers. In other words, this energy factor will ensure the optimized ROIs will not significantly deviate away from the original ROIs. 2.2.2 Structural connectivity constraint energy Structural connectivity constraint energy Ec is defined to ensure the group has similar structural connectivity profiles for each functional ROI, since similar functional regions should have the similar structural connectivity patterns [19], n m Ec ď€˝ ďƒĽďƒĽ (Cij ď€ M C j )Covc ď€1 (Ci j ď€ M C j )T (4) i ď€˝1 j ď€˝1 where Cij is the connectivity pattern vector for ROI j of subject i , M C j is the group mean ď€1 for ROI j , and Covc is the inverse of the covariance matrix. The connectivity pattern vector Cij is a fiber target region distribution histogram. To obtain this histogram, we first parcellate all the cortical surfaces into nine regions ( as shown in Fig.5a, four lobes for each hemisphere, and the subcortical region) using the HAMMER algorithm [17]. A finer parcellation is available but not used due to the relatively lower parcellation accuracy, which might render the histogram too sensitive to the parcellation result. Then, we extract fibers penetrating region Sij , and calculate the distribution of the fibersâ€™ target cortical regions. Fig.5 illustrates the ideas. Fig.5. Structural connectivity pattern descriptor. (a): Cortical surface parcellation using HAMMER [17]; (b): Joint visualization of the cortical surface, two ROIs (blue and green spheres), and fibers penetrating the ROIs (in red and yellow, respectively); (c): Corresponding target region distribution histogram of ROIs in Fig.5b. There are nine bins corresponding to the nine cortical regions. Each bin contains the number of fibers that penetrate the ROI and are connected to the corresponding cortical region. Fiber numbers are normalized across subjects. 2.2.3 Functional connectivity constraint energy Functional connectivity constraint energy E f is defined to ensure each individual has similar functional connectivity patterns for the working memory system, assuming the human brain has similar functional architecture across individuals [21]. đ?‘› đ??¸ đ?‘“ = âˆ‘ đ?‘–=1â€–đ??šđ?‘– âˆ’ đ?‘€ đ??š â€– (5) Here, Fi is the functional connectivity matrix for subject i , and M F is the group mean of the dataset. The connectivity between each pair of ROIs is defined using the Pearson correlation. The matrix distance used here is the Frobenius norm. 2.3 Energy minimization solution The minimization of the energy defined in Section 2.2 is known as a combinatorial optimization problem. Traditional optimization methods may not fit this problem, since there are two noticeable characteristics in this application. First, we do not know how the energy changes with the varying locations of ROIs. Therefore, techniques like Newtonâ€™s method cannot be used. Second, the structure of search space is not smooth, which may lead to multiple local minima during optimization. To address this problem, we adopt the simulated annealing (SA) algorithm [23] for the energy minimization. The idea of the SA algorithm is based on random walk through the space for lower energies. In these random walks, the probability of taking a step is determined by the Boltzmann distribution, - (E - E )/ ( KT ) p = e i+ 1 i (6) if Ei ď€Ť1 ď€ž Ei , and p ď€˝ 1 when Ei ď€Ť1 ď‚Ł Ei . Here, đ??¸ đ?‘– and đ??¸ đ?‘–+1 are the system energies at solution configuration đ?‘– and đ?‘– + 1 respectively; đ??ž is the Boltzmann constant; and đ?‘‡ is the system temperature. In other words, a step will be taken when a lower energy is found. A step will also be taken with probability p if a higher energy is found. This helps avoid the local minima in the search space. 3 R esult s Compared to structural and functional connectivity patterns, anatomical profiles are more easily affected by variability across individuals. Therefore, the anatomical constraint energy is designed to provide constraint only to ROIs that are obviously far away from reasonableness. The reasonable range was statistically modeled by the localizations of ROIs warped into the atlas space in Section 2.2.1. Our focus in this paper is the structural and functional profiles. 3.1 Optimization using anatomical and structural connectivity profile s In this section, we use only anatomical and structural connectivity profiles to optimize the locations of ROIs. The goal is to check whether the structural constraint energy Ec works as expected. Fig.6 shows the fibers penetrating the right precuneus for eight subjects before (top panel) and after optimization (bottom panel). The ROI is highlighted in a red sphere for each subject. As we can see from the figure (please refer to the highlighted yellow arrows), after optimization, the third and sixth subjects have significantly improved consistency with the rest of the group than before optimization, which proves the validity of the energy function Eq.(4). Fig.6. Comparison of structural profiles before and after optimization. Each column shows the corresponding before-optimization (top) and after-optimization (bottom) fibers of one subject. The ROI (right precuneus) is presented by the red sphere. 3.2 Optimization using anatomical and functional connectivity profiles In this section, we optimize the locations of ROIs using anatomical and functional profiles, aiming to validate the definition of functional connectivity constraint energy E f . If this energy constraint worked well, the functional connectivity variance of the working memory system across subjects would decrease. Fig.7 shows the comparison of the standard derivation for functional connectivity before (left) and after (right) optimization. As we can see, the variance is significantly reduced after optimization. This demonstrated the effectiveness of the defined functional connectivity constraint energy. Fig.7. Comparison of the standard derivation for functional connectivity before and after the optimization. Lower values mean more consistent connectivity pattern cross subjects. 3.3 Consistency between optimization of functional profiles and structural profiles Fig.8. Optimization consistency between functional and structural profiles. Top: Functional profile energy drop along with structural profile optimization; Bottom: Structural profile energy drop along with functional profile optimization. Each experiment was repeated 15 times with random initial ROI locations that met the anatomical constraint. The relationship between structure and function has been extensively studied [24], and it is widely believed that they are closely related. In this section, we study the relationship between functional profiles and structural profiles by looking at how the energy for one of them changes while the energy of the other decreases. The optimization processes in Section 3.1 and 3.2 were repeated 15 times respectively with random initial ROI locations that met the anatomical constraint. As shown in Fig.8, in general, the functional profile energies and structural profile energies are closely related in such a way that the functional profile energies tend to decrease along with the structural profile optimization process, while the structural profile energies also tend to decrease as the functional profile is optimized. This positively correlated decrease of functional profile energy and structural profile energy not only proves the close relationship between functional and structural profiles, but also demonstrates the consistency between functional and structural optimization, laying down the foundation of the joint optimiza tion, whose results are detailed in the following section. 3.4 Optimization connectivity profiles using anatomical, structural and functional In this section, we used all the constraints in Eq. (1) to optimize the individual locations of all ROIs in the working memory system. Ten runs of the optimization were performed using random initial ROI locations that met the anatomical constraint. Weighting parameter ď Ź equaled 0.5 for all these runs. Starting and ending temperatures for the simulated annealing algorithm are 8 and 0.05; Boltzmann constant K ď€˝ 1 . As we can see from Fig.9, most runs started to converge at step 24, and the convergence energy is quite close for all runs. This indicates that the simulated annealing algorithm provides a valid solution to our problem. By visual inspection, most of the ROIs move to more reasonable and consistent locations after the joint optimization. As an example, Fig.10 depicts the location movements of the ROI in Fig. 6 for eight subjects. As we can see, the ROIs for these subjects share a similar anatomical landmark, which appears to be the tip of the upper bank of the parieto-occipital sulcus. If the initial ROI was not at this landmark, it moved to the landmark after the optimization, which was the case for subjects 1, 4 and 7. The structural profiles of these ROIs are very similar to Fig.6. The results in Fig. 10 indicate the significant improvement of ROI locations achieved by the joint optimization procedure. Fig.9. Convergence performance of the simulated annealing . Each run has 28 temperature conditions. Fig.10. The movement of right precuneus before (in red sphere) and after (in green sphere) optimization for eight subjects. The

5 0.24629711 249 nips-2010-Spatial and anatomical regularization of SVM for brain image analysis

Author: Remi Cuingnet, Marie Chupin, Habib Benali, Olivier Colliot

Abstract: Support vector machines (SVM) are increasingly used in brain image analyses since they allow capturing complex multivariate relationships in the data. Moreover, when the kernel is linear, SVMs can be used to localize spatial patterns of discrimination between two groups of subjects. However, the features’ spatial distribution is not taken into account. As a consequence, the optimal margin hyperplane is often scattered and lacks spatial coherence, making its anatomical interpretation difﬁcult. This paper introduces a framework to spatially regularize SVM for brain image analysis. We show that Laplacian regularization provides a ﬂexible framework to integrate various types of constraints and can be applied to both cortical surfaces and 3D brain images. The proposed framework is applied to the classiﬁcation of MR images based on gray matter concentration maps and cortical thickness measures from 30 patients with Alzheimer’s disease and 30 elderly controls. The results demonstrate that the proposed method enables natural spatial and anatomical regularization of the classiﬁer. 1

6 0.10652796 283 nips-2010-Variational Inference over Combinatorial Spaces

7 0.10433774 77 nips-2010-Epitome driven 3-D Diffusion Tensor image segmentation: on extracting specific structures

8 0.076944157 57 nips-2010-Decoding Ipsilateral Finger Movements from ECoG Signals in Humans

9 0.065403357 162 nips-2010-Link Discovery using Graph Feature Tracking

10 0.056311518 161 nips-2010-Linear readout from a neural population with partial correlation data

11 0.055838685 167 nips-2010-Mixture of time-warped trajectory models for movement decoding

12 0.055735614 116 nips-2010-Identifying Patients at Risk of Major Adverse Cardiovascular Events Using Symbolic Mismatch

13 0.0554098 98 nips-2010-Functional form of motion priors in human motion perception

14 0.055278216 251 nips-2010-Sphere Embedding: An Application to Part-of-Speech Induction

15 0.055258609 94 nips-2010-Feature Set Embedding for Incomplete Data

16 0.053703319 135 nips-2010-Label Embedding Trees for Large Multi-Class Tasks

17 0.050943621 86 nips-2010-Exploiting weakly-labeled Web images to improve object classification: a domain adaptation approach

18 0.049457315 200 nips-2010-Over-complete representations on recurrent neural networks can support persistent percepts

19 0.046983834 61 nips-2010-Direct Loss Minimization for Structured Prediction

20 0.046840277 127 nips-2010-Inferring Stimulus Selectivity from the Spatial Structure of Neural Network Dynamics

similar papers computed by lsi model

lsi for this paper:

topicId topicWeight

[(0, 0.154), (1, 0.083), (2, -0.201), (3, 0.174), (4, -0.002), (5, -0.197), (6, 0.031), (7, -0.548), (8, -0.002), (9, 0.044), (10, 0.062), (11, 0.093), (12, 0.032), (13, 0.023), (14, -0.115), (15, 0.054), (16, 0.028), (17, 0.093), (18, 0.048), (19, -0.105), (20, 0.027), (21, 0.017), (22, -0.032), (23, -0.054), (24, -0.036), (25, -0.023), (26, -0.043), (27, -0.06), (28, 0.003), (29, -0.032), (30, 0.031), (31, -0.0), (32, -0.039), (33, 0.006), (34, 0.089), (35, 0.003), (36, 0.028), (37, -0.019), (38, 0.009), (39, 0.002), (40, 0.015), (41, 0.006), (42, 0.009), (43, -0.024), (44, 0.06), (45, -0.032), (46, -0.04), (47, -0.024), (48, 0.012), (49, -0.037)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.99055946 97 nips-2010-Functional Geometry Alignment and Localization of Brain Areas

Author: Georg Langs, Yanmei Tie, Laura Rigolo, Alexandra Golby, Polina Golland

2 0.96766132 123 nips-2010-Individualized ROI Optimization via Maximization of Group-wise Consistency of Structural and Functional Profiles

Author: Kaiming Li, Lei Guo, Carlos Faraco, Dajiang Zhu, Fan Deng, Tuo Zhang, Xi Jiang, Degang Zhang, Hanbo Chen, Xintao Hu, Steve Miller, Tianming Liu

3 0.87728 128 nips-2010-Infinite Relational Modeling of Functional Connectivity in Resting State fMRI

Author: Morten Mørup, Kristoffer Madsen, Anne-marie Dogonowski, Hartwig Siebner, Lars K. Hansen

4 0.86366975 44 nips-2010-Brain covariance selection: better individual functional connectivity models using population prior

Author: Gael Varoquaux, Alexandre Gramfort, Jean-baptiste Poline, Bertrand Thirion

5 0.71161145 249 nips-2010-Spatial and anatomical regularization of SVM for brain image analysis

Author: Remi Cuingnet, Marie Chupin, Habib Benali, Olivier Colliot

6 0.44715127 57 nips-2010-Decoding Ipsilateral Finger Movements from ECoG Signals in Humans

7 0.42658553 77 nips-2010-Epitome driven 3-D Diffusion Tensor image segmentation: on extracting specific structures

8 0.24501865 111 nips-2010-Hallucinations in Charles Bonnet Syndrome Induced by Homeostasis: a Deep Boltzmann Machine Model

9 0.23523216 167 nips-2010-Mixture of time-warped trajectory models for movement decoding

10 0.22395986 283 nips-2010-Variational Inference over Combinatorial Spaces

11 0.21253416 200 nips-2010-Over-complete representations on recurrent neural networks can support persistent percepts

12 0.20623997 127 nips-2010-Inferring Stimulus Selectivity from the Spatial Structure of Neural Network Dynamics

13 0.19714281 251 nips-2010-Sphere Embedding: An Application to Part-of-Speech Induction

14 0.19621661 259 nips-2010-Subgraph Detection Using Eigenvector L1 Norms

15 0.18496278 162 nips-2010-Link Discovery using Graph Feature Tracking

16 0.1833394 116 nips-2010-Identifying Patients at Risk of Major Adverse Cardiovascular Events Using Symbolic Mismatch

17 0.17565209 256 nips-2010-Structural epitome: a way to summarize one’s visual experience

18 0.17353185 21 nips-2010-Accounting for network effects in neuronal responses using L1 regularized point process models

19 0.16693477 238 nips-2010-Short-term memory in neuronal networks through dynamical compressed sensing

20 0.16691229 56 nips-2010-Deciphering subsampled data: adaptive compressive sampling as a principle of brain communication

similar papers computed by lda model

lda for this paper:

topicId topicWeight

[(13, 0.042), (17, 0.012), (27, 0.179), (30, 0.068), (35, 0.328), (45, 0.123), (50, 0.035), (52, 0.029), (60, 0.022), (77, 0.038), (90, 0.019)]

similar papers list:

simIndex simValue paperId paperTitle

same-paper 1 0.86552805 97 nips-2010-Functional Geometry Alignment and Localization of Brain Areas

Author: Georg Langs, Yanmei Tie, Laura Rigolo, Alexandra Golby, Polina Golland

2 0.80062664 170 nips-2010-Moreau-Yosida Regularization for Grouped Tree Structure Learning

Author: Jun Liu, Jieping Ye

Abstract: We consider the tree structured group Lasso where the structure over the features can be represented as a tree with leaf nodes as features and internal nodes as clusters of the features. The structured regularization with a pre-deﬁned tree structure is based on a group-Lasso penalty, where one group is deﬁned for each node in the tree. Such a regularization can help uncover the structured sparsity, which is desirable for applications with some meaningful tree structures on the features. However, the tree structured group Lasso is challenging to solve due to the complex regularization. In this paper, we develop an efﬁcient algorithm for the tree structured group Lasso. One of the key steps in the proposed algorithm is to solve the Moreau-Yosida regularization associated with the grouped tree structure. The main technical contributions of this paper include (1) we show that the associated Moreau-Yosida regularization admits an analytical solution, and (2) we develop an efﬁcient algorithm for determining the effective interval for the regularization parameter. Our experimental results on the AR and JAFFE face data sets demonstrate the efﬁciency and effectiveness of the proposed algorithm.

3 0.72002697 59 nips-2010-Deep Coding Network

Author: Yuanqing Lin, Zhang Tong, Shenghuo Zhu, Kai Yu

Abstract: This paper proposes a principled extension of the traditional single-layer ﬂat sparse coding scheme, where a two-layer coding scheme is derived based on theoretical analysis of nonlinear functional approximation that extends recent results for local coordinate coding. The two-layer approach can be easily generalized to deeper structures in a hierarchical multiple-layer manner. Empirically, it is shown that the deep coding approach yields improved performance in benchmark datasets.

4 0.70683497 73 nips-2010-Efficient and Robust Feature Selection via Joint ℓ2,1-Norms Minimization

Author: Feiping Nie, Heng Huang, Xiao Cai, Chris H. Ding

Abstract: Feature selection is an important component of many machine learning applications. Especially in many bioinformatics tasks, efﬁcient and robust feature selection methods are desired to extract meaningful features and eliminate noisy ones. In this paper, we propose a new robust feature selection method with emphasizing joint 2,1 -norm minimization on both loss function and regularization. The 2,1 -norm based loss function is robust to outliers in data points and the 2,1 norm regularization selects features across all data points with joint sparsity. An efﬁcient algorithm is introduced with proved convergence. Our regression based objective makes the feature selection process more efﬁcient. Our method has been applied into both genomic and proteomic biomarkers discovery. Extensive empirical studies are performed on six data sets to demonstrate the performance of our feature selection method. 1

5 0.64202315 149 nips-2010-Learning To Count Objects in Images

Author: Victor Lempitsky, Andrew Zisserman

Abstract: We propose a new supervised learning framework for visual object counting tasks, such as estimating the number of cells in a microscopic image or the number of humans in surveillance video frames. We focus on the practically-attractive case when the training images are annotated with dots (one dot per object). Our goal is to accurately estimate the count. However, we evade the hard task of learning to detect and localize individual object instances. Instead, we cast the problem as that of estimating an image density whose integral over any image region gives the count of objects within that region. Learning to infer such density can be formulated as a minimization of a regularized risk quadratic cost function. We introduce a new loss function, which is well-suited for such learning, and at the same time can be computed efﬁciently via a maximum subarray algorithm. The learning can then be posed as a convex quadratic program solvable with cutting-plane optimization. The proposed framework is very ﬂexible as it can accept any domain-speciﬁc visual features. Once trained, our system provides accurate object counts and requires a very small time overhead over the feature extraction step, making it a good candidate for applications involving real-time processing or dealing with huge amount of visual data. 1

6 0.63762897 260 nips-2010-Sufficient Conditions for Generating Group Level Sparsity in a Robust Minimax Framework

7 0.628842 81 nips-2010-Evaluating neuronal codes for inference using Fisher information

8 0.62473518 109 nips-2010-Group Sparse Coding with a Laplacian Scale Mixture Prior

9 0.62258184 123 nips-2010-Individualized ROI Optimization via Maximization of Group-wise Consistency of Structural and Functional Profiles

10 0.62107354 200 nips-2010-Over-complete representations on recurrent neural networks can support persistent percepts

11 0.60567069 161 nips-2010-Linear readout from a neural population with partial correlation data

12 0.60361296 128 nips-2010-Infinite Relational Modeling of Functional Connectivity in Resting State fMRI

13 0.60324258 21 nips-2010-Accounting for network effects in neuronal responses using L1 regularized point process models

14 0.59931558 121 nips-2010-Improving Human Judgments by Decontaminating Sequential Dependencies

15 0.59522665 249 nips-2010-Spatial and anatomical regularization of SVM for brain image analysis

16 0.59390754 39 nips-2010-Bayesian Action-Graph Games

17 0.59036887 55 nips-2010-Cross Species Expression Analysis using a Dirichlet Process Mixture Model with Latent Matchings

18 0.58656722 60 nips-2010-Deterministic Single-Pass Algorithm for LDA

19 0.58241904 44 nips-2010-Brain covariance selection: better individual functional connectivity models using population prior

20 0.58207864 26 nips-2010-Adaptive Multi-Task Lasso: with Application to eQTL Detection