Search

Psychiatric disorders show high rates of co-morbidity and non-specificity of presenting clinical symptoms, while at the same time demonstrating substantial heterogeneity within diagnostic categories. Notably, many of these psychiatric disorders first manifest in youth. Here we review progress and next steps in efforts to parse heterogeneity in psychiatric symptoms in youth by identifying abnormalities within neural circuits. To address this fundamental challenge in psychiatry, a number of methods have been proposed. We provide an overview of these methods, broadly organized into dimensional vs. categorical approaches and single-view vs. multi-view approaches. Dimensional approaches including factor analysis and canonical correlation analysis aim to capture dimensional associations between psychopathology and brain measures across a continuous spectrum from health to disease. In contrast, categorical approaches such as clustering and community detection aim to identify subtypes of individuals within a class of symptoms or brain features. We highlight several studies that apply these methods to samples of youth, and discuss issues to consider when using these approaches. Finally, we end by highlighting avenues for future research.

Major depressive disorder with psychotic features (psychotic depression) is a severe disorder. Compared with other psychotic disorders such as schizophrenia, relatively few studies on the neurobiology of psychotic depression have been pursued. Neuroimaging studies investigating psychotic depression have provided evidence for distributed structural brain abnormalities implicating the insular cortex and limbic system. We examined structural brain networks in participants (N = 245) using magnetic resonance imaging. This sample included healthy controls (n = 159) and the largest cross-sectional sample of patients with remitted psychotic depression (n = 86) collected to date. All patients participated in the Study of Pharmacotherapy of Psychotic Depression II randomized controlled trial. We used a novel, whole-brain, data-driven parcellation technique-non-negative matrix factorization-and applied it to cortical thickness data to derive structural covariance networks. We compared patients with remitted psychotic depression to healthy controls and found that patients had significantly thinner cortex in five structural covariance networks (insular-limbic, occipito-temporal, temporal, parahippocampal-limbic, and inferior fronto-temporal), confirming our hypothesis that affected brain networks would incorporate cortico-limbic regions. We also found that cross-sectional depression and severity scores at the time of scanning were associated with the insular-limbic network. Furthermore, the insular-limbic network predicted future severity scores that were collected at the time of recurrence of psychotic depression or sustained remission. Overall, decreased cortical thickness was found in five structural brain networks in patients with remitted psychotic depression and brain-behavior relationships were observed, particularly between the insular-limbic network and illness severity.

Introduction Relationships between brain atrophy patterns of typical aging and Alzheimer's disease (AD), white matter disease, cognition, and AD neuropathology were investigated via machine learning in a large harmonized magnetic resonance imaging database (11 studies; 10,216 subjects). Methods Three brain signatures were calculated: Brain-age, AD-like neurodegeneration, and white matter hyperintensities (WMHs). Brain Charts measured and displayed the relationships of these signatures to cognition and molecular biomarkers of AD. Results WMHs were associated with advanced brain aging, AD-like atrophy, poorer cognition, and AD neuropathology in mild cognitive impairment (MCI)/AD and cognitively normal (CN) subjects. High WMH volume was associated with brain aging and cognitive decline occurring in an ≈10-year period in CN subjects. WMHs were associated with doubling the likelihood of amyloid beta (Aβ) positivity after age 65. Brain aging, AD-like atrophy, and WMHs were better predictors of cognition than chronological age in MCI/AD. Discussion A Brain Chart quantifying brain-aging trajectories was established, enabling the systematic evaluation of individuals' brain-aging patterns relative to this large consortium.

Depression is a common psychiatric illness that often begins in youth, and is sometimes associated with cognitive deficits. However, there is significant variability in cognitive dysfunction, likely reflecting biological heterogeneity. We sought to identify neurocognitive subtypes and their neurofunctional signatures in a large cross-sectional sample of depressed youth. Participants were drawn from the Philadelphia Neurodevelopmental Cohort, including 712 youth with a lifetime history of a major depressive episode and 712 typically developing (TD) youth matched on age and sex. A subset (MDD n = 368, TD n = 200) also completed neuroimaging. Cognition was assessed with the Penn Computerized Neurocognitive Battery. A recently developed semi-supervised machine learning algorithm was used to delineate neurocognitive subtypes. Subtypes were evaluated for differences in both clinical psychopathology and brain activation during an n-back working memory fMRI task. We identified three neurocognitive subtypes in the depressed group. Subtype 1 was high-performing (high accuracy, moderate speed), Subtype 2 was cognitively impaired (low accuracy, slow speed), and Subtype 3 was impulsive (low accuracy, fast speed). While subtypes did not differ in clinical psychopathology, they diverged in their activation profiles in regions critical for executive function, which mirrored differences in cognition. Taken together, these data suggest disparate mechanisms of cognitive vulnerability and resilience in depressed youth, which may inform the identification of biomarkers for prognosis and treatment response.

There is a growing amount of clinical, anatomical and functional evidence for the heterogeneous presentation of neuropsychiatric and neurodegenerative diseases such as schizophrenia and Alzheimer’s Disease (AD). Elucidating distinct subtypes of diseases allows a better understanding of neuropathogenesis and enables the possibility of developing targeted treatment programs. Recent semi-supervised clustering techniques have provided a data-driven way to understand disease heterogeneity. However, existing methods do not take into account that subtypes of the disease might present themselves at different spatial scales across the brain. Here, we introduce a novel method, MAGIC, to uncover disease heterogeneity by leveraging multi-scale clustering. We first extract multi-scale patterns of structural covariance (PSCs) followed by a semi-supervised clustering with double cyclic block-wise optimization across different scales of PSCs. We validate MAGIC using simulated heterogeneous neuroanatomical data and demonstrate its clinical potential by exploring the heterogeneity of AD using T1 MRI scans of 228 cognitively normal (CN) and 191 patients. Our results indicate two main subtypes of AD with distinct atrophy patterns that consist of both fine-scale atrophy in the hippocampus as well as large-scale atrophy in cortical regions. The evidence for the heterogeneity is further corroborated by the clinical evaluation of two subtypes, which indicates that there is a subpopulation of AD patients that tend to be younger and decline faster in cognitive performance relative to the other subpopulation, which tends to be older and maintains a relatively steady decline in cognitive abilities.

ObjectivesTo investigate spatial heterogeneity of white matter lesions or hyperintensities (WMH).MethodsMRI scans of 1,836 participants (median age 52.2 ± 13.16 years) encompassing a wide age range (22–84 years) from the cross-sectional Study of Health in Pomerania (Germany) were included as discovery set identifying spatially distinct components of WMH using a structural covariance approach. Scans of 307 participants (median age 73.8 ± 10.2 years, with 747 observations) from the Baltimore Longitudinal Study of Aging (United States) were included to examine differences in longitudinal progression of these components. The associations of these components with vascular risk factors, cortical atrophy, Alzheimer disease (AD) genetics, and cognition were then investigated using linear regression.ResultsWMH were found to occur nonuniformly, with higher frequency within spatially heterogeneous patterns encoded by 4 components, which were consistent with common categorizations of deep and periventricular WMH, while further dividing the latter into posterior, frontal, and dorsal components. Temporal trends of the components differed both cross-sectionally and longitudinally. Frontal periventricular WMH were most distinctive as they appeared in the fifth decade of life, whereas the other components appeared later in life during the sixth decade. Furthermore, frontal WMH were associated with systolic blood pressure and with pronounced atrophy including AD-related regions. AD polygenic risk score was associated with the dorsal periventricular component in the elderly. Cognitive decline was associated with the dorsal component.ConclusionsThese results support the hypothesis that the appearance of WMH follows age and disease-dependent regional distribution patterns, potentially influenced by differential underlying pathophysiologic mechanisms, and possibly with a differential link to vascular and neurodegenerative changes.

Prematurity is associated with diverse developmental abnormalities, yet few studies relate cognitive and neurostructural deficits to a dimensional measure of prematurity. Leveraging a large sample of children, adolescents, and young adults (age 8–22 years) studied as part of the Philadelphia Neurodevelopmental Cohort, we examined how variation in gestational age impacted cognition and brain structure later in development. Participants included 72 preterm youth born before 37 weeks’ gestation and 206 youth who were born at term (37 weeks or later). Using a previously-validated factor analysis, cognitive performance was assessed in three domains: (1) executive function and complex reasoning, (2) social cognition, and (3) episodic memory. All participants completed T1-weighted neuroimaging at 3 T to measure brain volume. Structural covariance networks were delineated using non-negative matrix factorization, an advanced multivariate analysis technique. Lower gestational age was associated with both deficits in executive function and reduced volume within 11 of 26 structural covariance networks, which included orbitofrontal, temporal, and parietal cortices as well as subcortical regions including the hippocampus. Notably, the relationship between lower gestational age and executive dysfunction was accounted for in part by structural network deficits. Together, these findings emphasize the durable impact of prematurity on cognition and brain structure, which persists across development.

Adolescence is characterized by both maturation of brain structure and increased risk of negative outcomes from behaviors associated with impulsive decision-making. One important index of impulsive choice is delay discounting (DD), which measures the tendency to prefer smaller rewards available soon over larger rewards delivered after a delay. However, it remains largely unknown how individual differences in structural brain development may be associated with impulsive choice during adolescence. Leveraging a unique large sample of 427 human youths (208 males and 219 females) imaged as part of the Philadelphia Neurodevelopmental Cohort, we examined associations between delay discounting and cortical thickness within structural covariance networks. These structural networks were derived using non-negative matrix factorization, an advanced multivariate technique for dimensionality reduction, and analyzed using generalized additive models with penalized splines to capture both linear and nonlinear developmental effects. We found that impulsive choice, as measured by greater discounting, was most strongly associated with diminished cortical thickness in structural brain networks that encompassed the ventromedial prefrontal cortex, orbitofrontal cortex, temporal pole, and temporoparietal junction. Furthermore, structural brain networks predicted DD above and beyond cognitive performance. Taken together, these results suggest that reduced cortical thickness in regions known to be involved in value-based decision-making is a marker of impulsive choice during the critical period of adolescence.SIGNIFICANCERisky behaviors during adolescence, such as initiation of substance use or reckless driving, are a major source of morbidity and mortality. In this study, we present evidence from a large sample of youths that diminished cortical thickness in specific structural brain networks is associated with impulsive choice. Notably, the strongest association between impulsive choice and brain structure was seen in regions implicated in value-based decision-making; namely, the ventromedial prefrontal and orbitofrontal cortices. Moving forward, such neuroanatomical markers of impulsivity may aid in the development of personalized interventions targeted to reduce risk of negative outcomes resulting from impulsivity during adolescence.

During adolescence, the human cortex undergoes substantial remodeling to support a rapid expansion of behavioral repertoire. Accurately quantifying these changes is a prerequisite for understanding normal brain development, as well as the neuropsychiatric disorders that emerge in this vulnerable period. Past accounts have demonstrated substantial regional heterogeneity in patterns of brain development, but frequently have been limited by small samples and analytics that do not evaluate complex multivariate imaging patterns. Capitalizing on recent advances in multivariate analysis methods, we used nonnegative matrix factorization (NMF) to uncover coordinated patterns of cortical development in a sample of 934 youths ages 8-20, who completed structural neuroimaging as part of the Philadelphia Neurodevelopmental Cohort. Patterns of structural covariance (PSCs) derived by NMF were highly reproducible over a range of resolutions, and differed markedly from common gyral-based structural atlases. Moreover, PSCs were largely symmetric and showed correspondence to specific large-scale functional networks. The level of correspondence was ordered according to their functional role and position in the evolutionary hierarchy, being high in lower-order visual and somatomotor networks and diminishing in higher-order association cortex. Furthermore, PSCs showed divergent developmental associations, with PSCs in higher-order association cortex networks showing greater changes with age than primary somatomotor and visual networks. Critically, such developmental changes within PSCs were significantly associated with the degree of evolutionary cortical expansion. Together, our findings delineate a set of structural brain networks that undergo coordinated cortical thinning during adolescence, which is in part governed by evolutionary novelty and functional specialization.

Purpose: Glioblastoma, the most common and aggressive adult brain tumor, is considered noncurative at diagnosis, with 14 to 16 months median survival following treatment. There is increasing evidence that noninvasive integrative analysis of radiomic features can predict overall and progression-free survival, using advanced multiparametric magnetic resonance imaging (Adv-mpMRI). If successfully applicable, such noninvasive markers can considerably influence patient management. However, most patients prior to initiation of therapy typically undergo only basic structural mpMRI (Bas-mpMRI, i.e., T1, T1-Gd, T2, and T2-fluid-attenuated inversion recovery) preoperatively, rather than Adv-mpMRI that provides additional vascularization (dynamic susceptibility contrast-MRI) and cell-density (diffusion tensor imaging) related information. Approach: We assess a retrospective cohort of 101 glioblastoma patients with available Adv-mpMRI from a previous study, which has shown that an initial feature panel (IFP, i.e., intensity, volume, location, and growth model parameters) extracted from Adv-mpMRI can yield accurate overall survival stratification. We focus on demonstrating that equally accurate prediction models can be constructed using augmented radiomic feature panels (ARFPs, i.e., integrating morphology and textural descriptors) extracted solely from widely available Bas-mpMRI, obviating the need for using Adv-mpMRI. We extracted 1612 radiomic features from distinct tumor subregions to build multivariate models that stratified patients as long-, intermediate-, or short-survivors. Results: The classification accuracy of the model utilizing Adv-mpMRI protocols and the IFP was 72.77% and degraded to 60.89% when using only Bas-mpMRI. However, utilizing the ARFP on Bas-mpMRI improved the accuracy to 74.26%. Furthermore, Kaplan-Meier analysis demonstrated superior classification of subjects into short-, intermediate-, and long-survivor classes when using ARFP extracted from Bas-mpMRI. Conclusions: This quantitative evaluation indicates that accurate survival prediction in glioblastoma patients is feasible using solely Bas-mpMRI and integrative advanced radiomic features, which can compensate for the lack of Adv-mpMRI. Our finding holds promise for generalization across multiple institutions that may not have access to Adv-mpMRI and to better inform clinical decision-making about aggressive interventions and clinical trials.

Neurobiological heterogeneity in schizophrenia is poorly understood and confounds current analyses. We investigated neuroanatomical subtypes in a multi-institutional multi-ethnic cohort, using novel semi-supervised machine learning methods designed to discover patterns associated with disease rather than normal anatomical variation. Structural MRI and clinical measures in established schizophrenia (n = 307) and healthy controls (n = 364) were analysed across three sites of PHENOM (Psychosis Heterogeneity Evaluated via Dimensional Neuroimaging) consortium. Regional volumetric measures of grey matter, white matter, and CSF were used to identify distinct and reproducible neuroanatomical subtypes of schizophrenia. Two distinct neuroanatomical subtypes were found. Subtype 1 showed widespread lower grey matter volumes, most prominent in thalamus, nucleus accumbens, medial temporal, medial prefrontal/frontal and insular cortices. Subtype 2 showed increased volume in the basal ganglia and internal capsule, and otherwise normal brain volumes. Grey matter volume correlated negatively with illness duration in Subtype 1 (r = −0.201, P = 0.016) but not in Subtype 2 (r = −0.045, P = 0.652), potentially indicating different underlying neuropathological processes. The subtypes did not differ in age (t = −1.603, df = 305, P = 0.109), sex (chi-square = 0.013, df = 1, P = 0.910), illness duration (t = −0.167, df = 277, P = 0.868), antipsychotic dose (t = −0.439, df = 210, P = 0.521), age of illness onset (t = −1.355, df = 277, P = 0.177), positive symptoms (t = 0.249, df = 289, P = 0.803), negative symptoms (t = 0.151, df = 289, P = 0.879), or antipsychotic type (chi-square = 6.670, df = 3, P = 0.083). Subtype 1 had lower educational attainment than Subtype 2 (chi-square = 6.389, df = 2, P = 0.041). In conclusion, we discovered two distinct and highly reproducible neuroanatomical subtypes. Subtype 1 displayed widespread volume reduction correlating with illness duration, and worse premorbid functioning. Subtype 2 had normal and stable anatomy, except for larger basal ganglia and internal capsule, not explained by antipsychotic dose. These subtypes challenge the notion that brain volume loss is a general feature of schizophrenia and suggest differential aetiologies. They can facilitate strategies for clinical trial enrichment and stratification, and precision diagnostics.

OBJECTIVEDepression is a common psychiatric illness that often begins in youth, and is associated with cognitive symptoms. However, there is significant variability in the cognitive burden, likely reflecting biological heterogeneity. This study sought to identify neurocognitive subtypes in a large sample of depressed youth, and evaluated the neural signatures of these subtypes.METHODSParticipants were drawn from the Philadelphia Neurodevelopmental Cohort, including 712 youth with a lifetime history of a major depressive episode and 712 typically developing (TD) youth matched on age and sex. A subset (n=368, TD=200) also completed neuroimaging. Cognition was assessed with the Penn Computerized Neurocognitive Battery. A semi-supervised machine-learning algorithm, HYDRA (Heterogeneity through Discriminative Analysis), was used to delineate neurocognitive subtypes. Subtypes were evaluated for differences in both clinical psychopathology and brain activation during ann-back working memory fMRI task.RESULTSHYDRA identified three neurocognitive subtypes in the depressed group. Overall, Subtype 1 had better performance than TD comparators across many cognitive tasks (high accuracy, moderate speed), Subtype 2 was cognitively impaired (low accuracy, slow speed), whereas Subtype 3 was impulsive (low accuracy, fast speed). While subtypes did not differ in clinical psychopathology, they diverged in their activation profiles in regions critical for executive function, which mirrored differences in cognition.CONCLUSIONSUsing a data-driven approach, three neurocognitive subtypes of depression were identified that differed in neural signatures despite similar clinical psychopathology. These data suggest disparate mechanisms of cognitive vulnerability and resilience in depression, which may inform the identification of biomarkers for prognosis and treatment response.

High comorbidity among psychiatric disorders suggests that they may share underlying neurobiological deficits. Abnormalities in cortical thickness and volume have been demonstrated in clinical samples of adults, but less is known when these structural differences emerge in youths. The purpose of this study was to examine the association between dimensions of psychopathology and brain structure.The authors studied 1,394 youths who underwent brain imaging as part of the Philadelphia Neurodevelopmental Cohort. Dimensions of psychopathology were constructed using a bifactor model of symptoms. Cortical thickness and volume were quantified using high-resolution 3-T MRI. Structural covariance networks were derived using nonnegative matrix factorization and analyzed using generalized additive models with penalized splines to capture both linear and nonlinear age-related effects.Fear symptoms were associated with reduced cortical thickness in most networks, and overall psychopathology was associated with globally reduced gray matter volume across all networks. Structural covariance networks predicted psychopathology symptoms above and beyond demographic characteristics and cognitive performance.The results suggest a dissociable relationship whereby fear is most strongly linked to reduced cortical thickness and overall psychopathology is most strongly linked to global reductions in gray matter volume. Such results have implications for understanding how abnormalities of brain development may be associated with divergent dimensions of psychopathology.

BackgroundIrritability is an important dimension of psychopathology that spans multiple clinical diagnostic categories, yet its relationship to patterns of brain development remains sparsely explored. Here, we examined how trans-diagnostic symptoms of irritability relate to the development of structural brain networks.MethodsAll participants (n=144, 87 females) completed structural brain imaging with 3 Tesla MRI at two timepoints (mean age at follow-up: 20.9 years, mean inter-scan interval: 5.1 years). Irritability at follow-up was assessed using the Affective Reactivity Index, and cortical thickness was quantified using Advanced Normalization Tools software. Structural covariance networks were delineated using non-negative matrix factorization, a multivariate analysis technique. Both cross-sectional and longitudinal associations with irritability at follow-up were evaluated using generalized additive models with penalized splines. The False Discovery Rate (qResultsCross-sectional analysis of follow-up data revealed that 11 of the 24 covariance networks were associated with irritability, with higher levels of irritability being associated with thinner cortex. Longitudinal analyses further revealed that accelerated cortical thinning within 9 networks was related to irritability at follow-up. Effects were particularly prominent in brain regions implicated in emotion regulation, including the orbitofrontal, lateral temporal, and medial temporal cortex.ConclusionsCollectively, these findings suggest that irritability is associated with widespread cortical thickness reductions and accelerated cortical thinning, particularly within frontal and temporal cortex. Aberrant structural maturation of regions important for emotional regulation may in part underlie symptoms of irritability.

The complexity of modern multi-parametric MRI has increasingly challenged conventional interpretations of such images. Machine learning has emerged as a powerful approach to integrating diverse and complex imaging data into signatures of diagnostic and predictive value. It has also allowed us to progress from group comparisons to imaging biomarkers that offer value on an individual basis. We review several directions of research around this topic, emphasizing the use of machine learning in personalized predictions of clinical outcome, in breaking down broad umbrella diagnostic categories into more detailed and precise subtypes, and in non-invasively estimating cancer molecular characteristics. These methods and studies contribute to the field of precision medicine, by introducing more specific diagnostic and predictive biomarkers of clinical outcome, therefore pointing to better matching of treatments to patients.

Internalizing disorders such as anxiety and depression are the most common psychiatric disorders, frequently begin in youth, and exhibit marked heterogeneity in treatment response and clinical course. It is increasingly recognized that symptom-based classification approaches to internalizing disorders do not align with underlying neurobiology. An alternative to classifying psychopathology based on clinical symptoms is to identify neurobiologically-informed subtypes based on brain imaging data. We used a recently developed semi-supervised machine learning method (HYDRA) to delineate patterns of neurobiological heterogeneity within youth with internalizing symptoms using structural imaging data collected at 3T from a large community-based sample of 1,141 youth. Using volume and cortical thickness, cross-validation methods indicated a highly stable solution (ARI=.66; permutation-basedpfdr< .001) and identified two subtypes of internalizing youth. Subtype 1, defined by smaller brain volumes and reduced cortical thickness, was marked by impaired cognitive performance and higher levels of psychopathology than both Subtype 2 and typically developing youth. Using resting-state fMRI and diffusion images not considered during clustering, we found that Subtype 1 also showed reduced amplitudes of low-frequency fluctuations in fronto-limbic regions at rest, as well as reduced fractional anisotropy in white matter tracts such as the parahippocampal cingulum bundle and the uncinate fasciculus. In contrast, Subtype 2 showed intact cognitive performance, greater volume, cortical thickness, and amplitudes during rest compared to Subtype 1 and typically developing youth, despite still showing clinically significant levels of psychopathology. Identification of biologically-grounded subtypes of internalizing disorders may assist in targeting early interventions and assessing longitudinal prognosis.

Significance Delineating cortical microstructure differentiation is important for understanding complicated yet precisely organized patterns in early developing brain. Knowledge of cortical differentiation predominantly from histological studies is limited in localized and discrete cortical regions. We quantified the preterm brain cerebral cortical profile with microstructural complexity [indexed by mean kurtosis (MK)] and microstructural organization [indexed by fractional anisotropy (FA)] from advanced diffusion MRI. Cortical MK and FA maps revealed a heterogeneous maturation signature. Spatiotemporally distinctive disruption of radial glia and decrease of neuronal density among cortical regions were inferred by FA and MK decreases, respectively. These findings suggest that diffusion kurtosis metrics are significant imaging markers for microstructural differentiation of the developmental brain in health and disease., During the third trimester, the human brain undergoes rapid cellular and molecular processes that reshape the structural architecture of the cerebral cortex. Knowledge of cortical differentiation obtained predominantly from histological studies is limited in localized and small cortical regions. How cortical microstructure is differentiated across cortical regions in this critical period is unknown. In this study, the cortical microstructural architecture across the entire cortex was delineated with non-Gaussian diffusion kurtosis imaging as well as conventional diffusion tensor imaging of 89 preterm neonates aged 31–42 postmenstrual weeks. The temporal changes of cortical mean kurtosis (MK) or fractional anisotropy (FA) were heterogeneous across the cortical regions. Cortical MK decreases were observed throughout the studied age period, while cortical FA decrease reached its plateau around 37 weeks. More rapid decreases in MK were found in the primary visual region, while faster FA declines were observed in the prefrontal cortex. We found that distinctive cortical microstructural changes were coupled with microstructural maturation of associated white matter tracts. Both cortical MK and FA measurements predicted the postmenstrual age of preterm infants accurately. This study revealed a differential 4D spatiotemporal cytoarchitectural signature inferred by non-Gaussian diffusion barriers inside the cortical plate during the third trimester. The cytoarchitectural processes, including dendritic arborization and neuronal density decreases, were inferred by regional cortical FA and MK measurements. The presented findings suggest that cortical MK and FA measurements could be used as effective imaging markers for cortical microstructural changes in typical and potentially atypical brain development.

There are conflicting results regarding how APOE genotype, the strongest genetic risk factor for Alzheimer's disease (AD), influences spatial and longitudinal amyloid-beta (A beta) deposition and its impact on the selection of biomarker cut-points. In our study, we sought to determine the impact of APOE genotype on cross-sectional and longitudinal florbetapir positron emission tomography (PET) amyloid measures and its impact in classification of patients and interpretation of clinical cohort results. We included 1,019 and 1,072 Alzheimer's Disease Neuroimaging Initiative participants with cerebrospinal fluid A beta 1 - 42 and florbetapir PET values, respectively. 623 of these subjects had a second florbetapir PET scans two years after the baseline visit. We evaluated the effect of APOE genotype on A beta distribution pattern, pathological biomarker cut-points, cross-sectional clinical associations with A beta load, and longitudinal A beta deposition rate measured using florbetapir PET scans. 1) APOE epsilon 4 genotype influences brain amyloid deposition pattern; 2) APOE epsilon 4 genotype does not modify A beta biomarker cut-points estimated using unsupervised mixture modeling methods if white matter and brainstem references are used (but not when cerebellum is used as a reference); 3) findings of large differences in A beta biomarker value differences based on APOE genotype are due to increased probability of having AD neuropathology and are most significant in mild cognitive impairment subjects; and 4) APOE genotype and age (but not gender) were associated with increased A beta deposition rate. APOE epsilon 4 carrier status affects rate and location of brain A beta deposition but does not affect choice of biomarker cut-points if adequate references are selected for florbetapir PET processing.

We present a generic method for automatic detection of abnormal regions in medical images as deviations from a normative data base. The algorithm decomposes an image, or more broadly a function defined on the image grid, into the superposition of a normal part and a residual term. A statistical model is constructed with regional sparse learning to represent normative anatomical variations among a reference population (e.g., healthy controls), in conjunction with a Markov random field regularization that ensures mutual consistency of the regional learning among partially overlapping image blocks. The decomposition is performed in a principled way so that the normal part fits well with the learned normative model, while the residual term absorbs pathological patterns, which may then be detected through a statistical significance test. The decomposition is applied to multiple image features from an individual scan, detecting abnormalities using both intensity and shape information. We form an iterative scheme that interleaves abnormality detection with deformable registration, gradually improving robustness of the spatial normalization and precision of the detection. The algorithm is evaluated with simulated images and clinical data of brain lesions, and is shown to achieve robust deformable registration and localize pathological regions simultaneously. The algorithm is also applied on images from Alzheimer’s disease patients to demonstrate the generality of the method.

Accurate subject-to-template alignment requires deformation models with high degrees of freedom to account for the high anatomical variability. Without proper regularization, such models tend to match the images aggressively, often producing unrealistic transformations, especially in the presence of noise, or pathologies such as various types of lesions. To improve the robustness of deformable registration, we propose a novel framework, which makes use of statistical deformation models (SDMs) for diffeomorphisms. We present a general approach to constructing such SDMs, and detail how to use them for regularizing a given transformation. To preserve the diffeomorphic property, while making use of linear statistical models, we convert the deformation field into a stationary velocity field through the logarithm operator. To account for learning in a high-dimensional, low-sample size setting, we model the high-dimensional velocity field as a collection of mutually constrained local velocity fields. For each local field, a low-dimensional representation is learned using principal component analysis. To capture possible dependencies across local transformations, canonical correlation analysis is performed on each pair of local velocities in the learned low-dimensional space. Experiments on healthy brain images show that the model can capture the normative variation of subject-to-template deformation fields with sub-millimeter accuracy. The method is validated on simulated brain lesion images and is tested on real brain images with pathologies, producing significantly smoother and more robust results than its non-statistical counterpart.

Statistical mapping of normative or pathological changes in the brain is of utmost importance for our understanding of its structure and function. Mass-univariate as well as multivariate pattern analysis techniques have been proposed to map group differences in neuroimaging studies. However, these methods often suffer from low sensitivity and specificity, as well as high computational cost. To address these limitations, we introduce a novel multivariate statistical framework, termed MIDAS, aiming to efficiently produce highly sensitive and specific statistical brain maps. MIDAS utilizes localized discriminative learning to produce a statistic whose significance can be assessed by analytic approximation of permutation testing. Discriminative learning allows for finding the optimal adaptive filtering of the image for group analysis. The null distribution of the resulting statistic is analytically approximated, which provides computational efficiency. MIDAS is extensively validated using simulated atrophy on structural magnetic resonance images of 200 healthy subjects. Furthermore, the applicability of MIDAS to clinical studies is confirmed by applying it to an Alzheimer's disease (AD) dataset (ADNI) comprising 199 AD patients and 230 controls.

The relationship between grey matter volume (GMV) patterns and age can be captured by multivariate pattern analysis, allowing prediction of individuals’ age based on structural imaging. Raw data, voxel-wise GMV and non-sparse factorization (with Principal Component Analysis, PCA) show good performance but do not promote relatively localized brain components for post-hoc examinations. Here we evaluated a non-negative matrix factorization (NNMF) approach to provide a reduced, but also interpretable representation of GMV data in age prediction frameworks in healthy and clinical populations. This examination was performed using three datasets: a multi-site cohort of life-span healthy adults, a single site cohort of older adults and clinical samples from the ADNI dataset with healthy subjects, participants with Mild Cognitive Impairment and patients with Alzheimer’s disease (AD) subsamples. T1-weighted images were preprocessed with VBM8 standard settings to compute GMV values after normalization, segmentation and modulation for non-linear transformations only. Non-negative matrix factorization was computed on the GM voxel-wise values for a range of granularities (50 to 690 components) and LASSO (Least Absolute Shrinkage and Selection Operator) regression were used for age prediction. First, we compared the performance of our data compression procedure (i.e., NNMF) to various other approaches (i.e., uncompressed VBM data, PCA-based factorization and parcellation-based compression). We then investigated the impact of the granularity on the accuracy of age prediction, as well as the transferability of the factorization and model generalization across datasets. We finally validated our framework by examining age prediction in ADNI samples. Our results showed that our framework favorably compares with other approaches. They also demonstrated that the NNMF based factorization derived from one dataset could be efficiently applied to compress VBM data of another dataset and that granularities between 300 and 500 components give an optimal representation for age prediction. In addition to the good performance in healthy subjects our framework provided relatively localized brain regions as the features contributing to the prediction, thereby offering further insights into structural changes due to brain aging. Finally, our validation in clinical populations showed that our framework is sensitive to deviance from normal structural variations in pathological aging.

This paper presents a general framework for obtaining interpretable multivariate discriminative models that allow efficient statistical inference for neuroimage analysis. The framework, termed generative discriminative machine (GDM), augments discriminative models with a generative regularization term. We demonstrate that the proposed formulation can be optimized in closed form and in dual space, allowing efficient computation for high dimensional neuroimaging datasets. Furthermore, we provide an analytic estimation of the null distribution of the model parameters, which enables efficient statistical inference and p-value computation without the need for permutation testing. We compared the proposed method with both purely generative and discriminative learning methods in two large structural magnetic resonance imaging (sMRI) datasets of Alzheimer’s disease (AD) (n = 415) and Schizophrenia (n = 853). Using the AD dataset, we demonstrated the ability of GDM to robustly handle confounding variations. Using Schizophrenia dataset, we demonstrated the ability of GDM to handle multi-site studies. Taken together, the results underline the potential of the proposed approach for neuroimaging analyses.

The growth of multiparametric imaging protocols has paved the way for quantitative imaging phenotypes that predict treatment response and clinical outcome, reflect underlying cancer molecular characteristics and spatiotemporal heterogeneity, and can guide personalized treatment planning. This growth has underlined the need for efficient quantitative analytics to derive high-dimensional imaging signatures of diagnostic and predictive value in this emerging era of integrated precision diagnostics. This paper presents cancer imaging phenomics toolkit (CaPTk), a new and dynamically growing software platform for analysis of radiographic images of cancer, currently focusing on brain, breast, and lung cancer. CaPTk leverages the value of quantitative imaging analytics along with machine learning to derive phenotypic imaging signatures, based on two-level functionality. First, image analysis algorithms are used to extract comprehensive panels of diverse and complementary features, such as multiparametric intensity histogram distributions, texture, shape, kinetics, connectomics, and spatial patterns. At the second level, these quantitative imaging signatures are fed into multivariate machine learning models to produce diagnostic, prognostic, and predictive biomarkers. Results from clinical studies in three areas are shown: (i) computational neuro-oncology of brain gliomas for precision diagnostics, prediction of outcome, and treatment planning; (ii) prediction of treatment response for breast and lung cancer, and (iii) risk assessment for breast cancer.

Statistical parametric maps formed via voxel-wise mass-univariate tests, such as the general linear model, are commonly used to test hypotheses about regionally specific effects in neuroimaging cross-sectional studies where each subject is represented by a single image. Despite being informative, these techniques remain limited as they ignore multivariate relationships in the data. Most importantly, the commonly employed local Gaussian smoothing, which is important for accounting for registration errors and making the data follow Gaussian distributions, is usually chosen in an ad hoc fashion. Thus, it is often suboptimal for the task of detecting group differences and correlations with non-imaging variables. Information mapping techniques, such as searchlight, which use pattern classifiers to exploit multivariate information and obtain more powerful statistical maps, have become increasingly popular in recent years. However, existing methods may lead to important interpretation errors in practice (i.e., misidentifying a cluster as informative, or failing to detect truly informative voxels), while often being computationally expensive. To address these issues, we introduce a novel efficient multivariate statistical framework for cross-sectional studies, termed MIDAS, seeking highly sensitive and specific voxel-wise brain maps, while leveraging the power of regional discriminant analysis. In MIDAS, locally linear discriminative learning is applied to estimate the pattern that best discriminates between two groups, or predicts a variable of interest. This pattern is equivalent to local filtering by an optimal kernel whose coefficients are the weights of the linear discriminant. By composing information from all neighborhoods that contain a given voxel, MIDAS produces a statistic that collectively reflects the contribution of the voxel to the regional classifiers as well as the discriminative power of the classifiers. Critically, MIDAS efficiently assesses the statistical significance of the derived statistic by analytically approximating its null distribution without the need for computationally expensive permutation tests. The proposed framework was extensively validated using simulated atrophy in structural magnetic resonance imaging (MRI) and further tested using data from a task-based functional MRI study as well as a structural MRI study of cognitive performance. The performance of the proposed framework was evaluated against standard voxel-wise general linear models and other information mapping methods. The experimental results showed that MIDAS achieves relatively higher sensitivity and specificity in detecting group differences. Together, our results demonstrate the potential of the proposed approach to efficiently map effects of interest in both structural and functional data.

Gliomas belong to a group of central nervous system tumors, and consist of various sub-regions. Gold standard labeling of these sub-regions in radiographic imaging is essential for both clinical and computational studies, including radiomic and radiogenomic analyses. Towards this end, we release segmentation labels and radiomic features for all pre-operative multimodal magnetic resonance imaging (MRI) (n=243) of the multi-institutional glioma collections of The Cancer Genome Atlas (TCGA), publicly available in The Cancer Imaging Archive (TCIA). Pre-operative scans were identified in both glioblastoma (TCGA-GBM, n=135) and low-grade-glioma (TCGA-LGG, n=108) collections via radiological assessment. The glioma sub-region labels were produced by an automated state-of-the-art method and manually revised by an expert board-certified neuroradiologist. An extensive panel of radiomic features was extracted based on the manually-revised labels. This set of labels and features should enable i) direct utilization of the TCGA/TCIA glioma collections towards repeatable, reproducible and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments, as well as ii) performance evaluation of computer-aided segmentation methods, and comparison to our state-of-the-art method.

International audience; Multi-atlas segmentation has emerged in recent years as a simple yet powerful approach in medical image segmentation. It commonly comprises two steps: i) a series of pairwise registrations that establish correspondences between a query image and a number of atlases, and ii) the fusion of the available seg-mentation hypotheses towards labeling objects of interest. In this paper, we introduce a novel approach that solves simultaneously for the underlying segmentation labels and the multi-atlas registration. The proposed approach is formulated as a pairwise Markov Random Field, where registration and segmentation nodes are coupled towards simultaneously recovering all atlas deformations and labeling the query image. The coupling is achieved by promoting the consistency between selected deformed atlas segmentations and the estimated query segmentation. Additional membership fields are estimated, determining the participation of each atlas in labeling each voxel. Inference is performed by using a sequential relaxation scheme. The proposed approach is validated on the IBSR dataset and is compared against standard post-registration label fusion strategies. Promising results demonstrate the potential of our method.

Computer assisted imaging aims to characterize disease processes by contrasting healthy and pathological populations. The sensitivity of these analyses is hindered by the variability in the neuroanatomy of the normal population. To alleviate this shortcoming, it is necessary to define a normative range of controls. Moreover, elucidating the structure in outliers may be important in understanding diverging individuals and characterizing prodromal disease states. To address these issues, we propose a novel geometric concept called minimal convex polytope (MCP). The proposed approach is used to simultaneously capture high probability regions in datasets consisting of normal subjects, and delineate outliers, thus characterizing the main directions of deviation from the normative range. We validated our method using simulated datasets before applying it to an imaging study of elderly subjects consisting of 177 controls, 123 Alzheimer’s disease (AD) and 285 mild cognitive impairment (MCI) patients. We show that cerebellar degeneration is a major type of deviation among the controls. Furthermore, our findings suggest that a subset of AD patients may be following an accelerated type of deviation that is observed among the normal population.

Multivariate pattern analysis techniques have been increasingly used over the past decade to derive highly sensitive and specific biomarkers of diseases on an individual basis. The driving assumption behind the vast majority of the existing methodologies is that a single imaging pattern can distinguish between healthy and diseased populations, or between two subgroups of patients (e.g., progressors vs. non-progressors). This assumption effectively ignores the ample evidence for the heterogeneous nature of brain diseases. Neurodegenerative, neuropsychiatric and neurodevelopmental disorders are largely characterized by high clinical heterogeneity, which likely stems in part from underlying neuroanatomical heterogeneity of various pathologies. Detecting and characterizing heterogeneity may deepen our understanding of disease mechanisms and lead to patient-specific treatments. However, few approaches tackle disease subtype discovery in a principled machine learning framework. To address this challenge, we present a novel non-linear learning algorithm for simultaneous binary classification and subtype identification, termed HYDRA (Heterogeneity through Discriminative Analysis). Neuroanatomical subtypes are effectively captured by multiple linear hyperplanes, which form a convex polytope that separates two groups (e.g., healthy controls from pathologic samples); each face of this polytope effectively defines a disease subtype. We validated HYDRA on simulated and clinical data. In the latter case, we applied the proposed method independently to the imaging and genetic datasets of the Alzheimer's Disease Neuroimaging Initiative (ADNI 1) study. The imaging dataset consisted of T1-weighted volumetric magnetic resonance images of 123 AD patients and 177 controls. The genetic dataset consisted of single nucleotide polymorphism information of 103 AD patients and 139 controls. We identified 3 reproducible subtypes of atrophy in AD relative to controls: (1) diffuse and extensive atrophy, (2) precuneus and extensive temporal lobe atrophy, as well some prefrontal atrophy, (3) atrophy pattern very much confined to the hippocampus and the medial temporal lobe. The genetics dataset yielded two subtypes of AD characterized mainly by the presence/absence of the apolipoprotein E (APOE) e4 genotype, but also involving differential presence of risk alleles of CD2AP, SPON1 and LOC39095 SNPs that were associated with differences in the respective patterns of brain atrophy, especially in the precuneus. The results demonstrate the potential of the proposed approach to map disease heterogeneity in neuroimaging and genetic studies.

We present an approach for segmenting both low- and high-grade gliomas in multimodal magnetic resonance imaging volumes. The proposed framework is an extension of our previous work [6,7], with an additional component for segmenting post-operative scans. The proposed approach is based on a hybrid generative-discriminative model. Firstly, a generative model based on a joint segmentation-registration framework is used to segment the brain scans into cancerous and healthy tissues. Secondly, a gradient boosting classification scheme is used to refine tumor segmentation based on information from multiple patients. We evaluated our approach in 218 cases during the training phase of the BRAin Tumor Segmentation (BRATS) 2016 challenge and report promising results. During the testing phase, the proposed approach was ranked among the top performing methods, after being additionally evaluated in 191 unseen cases.

Identifying accurate biomarkers of cognitive decline is essential for advancing early diagnosis and prevention therapies in Alzheimer's disease. The Alzheimer's disease DREAM Challenge was designed as a computational crowdsourced project to benchmark the current state-of-the-art in predicting cognitive outcomes in Alzheimer's disease based on high dimensional, publicly available genetic and structural imaging data. This meta-analysis failed to identify a meaningful predictor developed from either data modality, suggesting that alternate approaches should be considered for prediction of cognitive performance.

This review introduces a novel deformable image registration paradigm that exploits Markov random field formulation and powerful discrete optimization algorithms. We express deformable registration as a minimal cost graph problem, where nodes correspond to the deformation grid, a node's connectivity corresponds to regularization constraints, and labels correspond to 3D deformations. To cope with both iconic and geometric (landmark-based) registration, we introduce two graphical models, one for each subproblem. The two graphs share interconnected variables, leading to a modular, powerful, and flexible formulation that can account for arbitrary image-matching criteria, various local deformation models, and regularization constraints. To cope with the corresponding optimization problem, we adopt two optimization strategies: a computationally efficient one and a tight relaxation alternative. Promising results demonstrate the potential of this approach. Discrete methods are an important new trend in medical image registration, as they provide several improvements over the more traditional continuous methods. This is illustrated with several key examples where the presented framework outperforms existing general-purpose registration methods in terms of both performance and computational complexity. Our methods become of particular interest in applications where computation time is a critical issue, as in intraoperative imaging, or where the huge variation in data demands complex and application-specific matching criteria, as in large-scale multimodal population studies. The proposed registration framework, along with a graphical interface and corresponding publications, is available for download for research purposes (for Windows and Linux platforms) from http://www.mrf-registration.net.

Irritability is an important dimension of psychopathology that spans multiple clinical diagnostic categories, yet its relationship to patterns of brain development remains sparsely explored. Here, we examined how transdiagnostic symptoms of irritability relate to the development of structural brain networks. All participants (n = 137, 83 females) completed structural brain imaging with 3 Tesla MRI at two timepoints (mean age at follow-up: 21.1 years, mean inter-scan interval: 5.2 years). Irritability at follow-up was assessed using the Affective Reactivity Index, and cortical thickness was quantified using Advanced Normalization Tools software. Structural covariance networks were delineated using non-negative matrix factorization, a multivariate analysis technique. Both cross-sectional and longitudinal associations with irritability at follow-up were evaluated using generalized additive models with penalized splines. The False Discovery Rate (q

International audience; Carotid plaque segmentation in ultrasound images is a crucial step for carotid atherosclerosis. However, image quality, important deformations and lack of texture are prohibiting factors towards manual or accurate carotid segmentation. We propose a novel fully automated methodology to identify the plaque region by exploiting kinematic dependencies between the atherosclerotic and the normal arterial wall. The proposed methodology exploits group-wise image registration towards recovering the deformation field, on which information theory criteria are used to determine dominant motion classes and a map reflecting kinematic dependencies , which is then segmented using Markov random fields. The algorithm was evaluated on 120 cases, for which manually-traced plaque contours by an experienced physician were available. Promising evaluation results showed the enhanced performance of the algorithm in automatically segmenting the plaque region, while future experiments on additional datasets are expected to further elucidate its potential.

See Coulthard and Knight (doi:10.1093/aww335) for a scientific commentary on this article.Individuals with mild cognitive impairment and Alzheimer's disease clinical diagnoses can display significant phenotypic heterogeneity. This variability likely reflects underlying genetic, environmental and neuropathological differences. Characterizing this heterogeneity is important for precision diagnostics, personalized predictions, and recruitment of relatively homogeneous sets of patients into clinical trials. In this study, we apply state-of-the-art semi-supervised machine learning methods to the Alzheimer's disease Neuroimaging cohort (ADNI) to elucidate the heterogeneity of neuroanatomical differences between subjects with mild cognitive impairment (n = 530) and Alzheimer's disease (n = 314) and cognitively normal individuals (n = 399), thereby adding to an increasing literature aiming to establish neuroanatomical and neuropathological (e.g. amyloid and tau deposition) dimensions in Alzheimer's disease and its prodromal stages. These dimensional approaches aim to provide surrogate measures of heterogeneous underlying pathologic processes leading to cognitive impairment. We relate these neuroimaging patterns to cerebrospinal fluid biomarkers, white matter hyperintensities, cognitive and clinical measures, and longitudinal trajectories. We identified four such atrophy patterns: (i) individuals with largely normal neuroanatomical profiles, who also turned out to have the least abnormal cognitive and cerebrospinal fluid biomarker profiles and the slowest clinical progression during follow-up; (ii) individuals with classical Alzheimer's disease neuroanatomical, cognitive, cerebrospinal fluid biomarkers and clinical profile, who presented the fastest clinical progression; (iii) individuals with a diffuse pattern of atrophy with relatively less pronounced involvement of the medial temporal lobe, abnormal cerebrospinal fluid amyloid-β1-42 values, and proportionally greater executive impairment; and (iv) individuals with notably focal involvement of the medial temporal lobe and a slow steady progression, likely representing in early Alzheimer's disease stages. These four atrophy patterns effectively define a 4-dimensional categorization of neuroanatomical alterations in mild cognitive impairment and Alzheimer's disease that can complement existing dimensional approaches for staging Alzheimer's disease using a variety of biomarkers, which offer the potential for enabling precision diagnostics and prognostics, as well as targeted patient recruitment of relatively homogeneous subgroups of subjects for clinical trials.

International audience; In this paper, we present a novel method for disease classification between two patient populations based on features extracted from Magnetic Resonance Imaging (MRI) data. Anatomically meaningful features are extracted from structural data (T1- and T2-weighted MR images) and Diffusion Tensor Imaging (DTI) data, and used to train a new machine learning algorithm, the k-support SVM (ksup-SVM). The k-support regularized SVM has an inherent feature selection property, and thus it eliminates the requirement for a separate feature selection step. Our dataset consists of patients that suffer from facioscapulohumeral muscular dystrophy (FSH) and Myotonic muscular dystrophy type 1 (DM1) and our proposed method achieves a high performance. More specifically, it achieves a mean Area Under the Curve (AUC) of 0.7141 and mean accuracy 77% ± 0.013. Moreover, we provide a sparsity visualization of the features in order to indentify their discriminative value. The results suggest the potential of the combined use of MR markers to diagnose myopathies, and the general utility of the ksup-SVM. Source code is also available at https://gitorious.org/ksup-svm.

International audience; Image registration is in principle a symmetric problem. Nonetheless, most intensity-based non-rigid algorithms are asymmetric. In this paper, we propose a novel symmetric deformable registration algorithm formulated in a Markov Random Fields framework where both images are let to deform towards a common domain that lies halfway between two image domains. A grid-based deformation model is employed and the latent variables correspond to the displacements of the grid-nodes towards both image domains. First-order interactions between the unknown variables model standard smoothness priors. Efficient linear programming is consider to recover the optimal solution. The discrete nature of our algorithm allows the handling of both mono- and multi-modal registration problems. Promising experimental results demonstrate the potentials of our approach.

International audience; First order Markov Random Fields (MRFs) have become a predominant tool in Computer Vision over the past decade. Such a success was mostly due to the development of efficient optimization algorithms both in terms of speed as well as in terms of optimality properties. Message passing algorithms are among the most popular methods due to their good performance for a wide range of pairwise potential functions (PPFs). Their main bottleneck is computational complexity. In this paper, we revisit message computation as a distance transformation using a more formal setting than [8] to generalize it to arbitrary PPFs. The method is based on [20] yielding accurate results for a specific class of PPFs and in most other cases a close approximation. The proposed algorithm is parallel and thus enables us to fully take advantage of the computational power of parallel processing architectures. The proposed scheme coupled with an efficient belief propagation algorithm [8] and implemented on a massively parallel coprocessor provides results as accurate as state of the art inference methods, though is in general one order of magnitude faster in terms of speed.

International audience; A general-purpose deformable registration algorithm referred to as "DRAMMS" is presented in this paper. DRAMMS bridges the gap between the traditional voxel-wise methods and landmark/feature-based methods with primarily two contributions. First, DRAMMS renders each voxel relatively distinctively identifiable by a rich set of attributes, therefore largely reducing matching ambiguities. In particular, a set of multi-scale and multi-orientation Gabor attributes are extracted and the optimal components are selected, so that they form a highly distinctive morphological signature reflecting the anatomical and geometric context around each voxel. Moreover, the way in which the optimal Gabor attributes are constructed is independent of the underlying image modalities or contents, which renders DRAMMS generally applicable to diverse registration tasks. A second contribution of DRAMMS is that it modulates the registration by assigning higher weights to those voxels having higher ability to establish unique (hence reliable) correspondences across images, therefore reducing the negative impact of those regions that are less capable of finding correspondences (such as outlier regions). A continuously-valued weighting function named "mutual-saliency" is developed to reflect the matching uniqueness between a pair of voxels implied by the tentative transformation. As a result, voxels do not contribute equally as in most voxel-wise methods, nor in isolation as in landmark/feature-based methods. Instead, they contribute according to the continuously-valued mutual-saliency map, which dynamically evolves during the registration process. Experiments in simulated images, inter-subject images, single-/multi-modality images, from brain, heart, and prostate have demonstrated the general applicability and the accuracy of DRAMMS.

International audience; In this paper, we introduce a novel approach to bridge the gap between the landmark-based and the iconic-based voxel-wise registration methods. The registration problem is formulated with the use of Markov Random Field theory resulting in a discrete objective function consisting of thee parts. The first part of the energy accounts for the iconic-based volumetric registration problem while the second one for establishing geometrically meaningful correspondences by optimizing over a set of automatically generated mutually salient candidate pairs of points. The last part of the energy penalizes locally the difference between the dense deformation field due to the iconic-based registration and the implied displacements due to the obtained correspondences. Promising results in real MR brain data demonstrate the potentials of our approach.

International audience; Optical imaging is an efficient mean to measure biological signal. However, it can suffer from low spatial and temporal resolution while animal deformable displacements could also degrade significantly the localization of the measurements. In this paper, we propose a novel approach to perform fusion of cinematic flow and optical imaging towards enhancement of the biological signal. To this end, fusion is reformulated as a population (all vs. all) registration problem where the two (being spatially aligned) signals are registered in time using the same deformation field. Implicit silhouette and landmark matching are considered for the cinematic images and are combined with global statistical congealing-type measurements of the optical one. The problem is reformulated using a discrete MRF, where optical imaging costs are expressed in singleton (global) potentials, while smoothness constraints as well as cinematic measurements through pair-wise potentials. Promising experimental results demonstrate the potentials of our approach.

In this paper, we propose a novel method for the spatial normalization of diffusion tensor images. The proposed method takes advantage of both the diffusion information and the spatial location of tensor in order to define an appropriate metric in a probabilistic framework. A registration energy is defined in a Reproducing Kernel Hilbert Space (RKHS), encoding the image dissimilarity and the regularity of the deformation field in both the translation and the rotation space. The problem is reformulated as a graphical model where the latent variables are the rotation and the translation that should be applied to every tensor and the observed variables are the tensors themselves. Efficient linear programming is used to minimize the resulting energy. Quantitative and qualitative results on a manually annotated dataset of diffusion tensor images demonstrate the potential of the proposed method.