Abstract: High-dimensional pattern classification was applied to baseline and multiple follow-up MRI scans of the Alzheimer's Disease Neuroimaging Initiative (ADNI) participants with mild cognitive impairment (MCI), in order to investigate the potential of predicting short-term conversion to Alzheimer's Disease (AD) on an individual basis. MCI participants that converted to AD (average follow-up 15 months) displayed significantly lower volumes in a number of grey matter (GM) regions, as well as in the white matter (WM). They also displayed more pronounced periventricular small-vessel pathology, as well as an increased rate of increase of such pathology. Individual person analysis was performed using a pattern classifier previously constructed from AD patients and cognitively normal (CN) individuals to yield an abnormality score that is positive for AD-like brains and negative otherwise. The abnormality scores measured from MCI non-converters (MCI-NC) followed a bimodal distribution, reflecting the heterogeneity of this group, whereas they were positive in almost all MCI converters (MCI-C), indicating extensive patterns of AD-like brain atrophy in almost all MCI-C. Both MCI subgroups had similar MMSE scores at baseline. A more specialized classifier constructed to differentiate converters from non-converters based on their baseline scans provided good classification accuracy reaching 81.5%, evaluated via cross-validation. These pattern classification schemes, which distill spatial patterns of atrophy to a single abnormality score, offer promise as biomarkers of AD and as predictors of subsequent clinical progression, on an individual patient basis.

Abstract: A brain image registration algorithm, referred to as RABBIT, is proposed to achieve fast and accurate image registration with the help of an intermediate template generated by a statistical deformation model. The statistical deformation model is built by principal component analysis (PCA) on a set of training samples of brain deformation fields that warp a selected template image to the individual brain samples. The statistical deformation model is capable of characterizing individual brain deformations by a small number of parameters, which is used to rapidly estimate the brain deformation between the template and a new individual brain image. The estimated deformation is then used to warp the template, thus generating an intermediate template close to the individual brain image. Finally, the shape difference between the intermediate template and the individual brain is estimated by an image registration algorithm, e.g., HAMMER. The overall registration between the template and the individual brain image can be achieved by directly combining the deformation fields that warp the template to the intermediate template, and the intermediate template to the individual brain image. The algorithm has been validated for spatial normalization of both simulated and real magnetic resonance imaging (MRI) brain images. Compared with HAMMER, the experimental results demonstrate that the proposed algorithm can achieve over five times speedup, with similar registration accuracy and statistical power in detecting brain atrophy.

Abstract: A challenge in developing informative neuroimaging biomarkers for early diagnosis of Alzheimer's disease is the need to identify biomarkers that are evident before the onset of clinical symptoms, and which have sufficient sensitivity and specificity on an individual patient basis. Recent literature suggests that spatial patterns of brain atrophy discriminate amongst Alzheimer's disease, mild cognitive impairment (MCI) and cognitively normal (CN) older adults with high accuracy on an individual basis, thereby offering promise that subtle brain changes can be detected during prodromal Alzheimer's disease stages. Here, we investigate whether these spatial patterns of brain atrophy can be detected in CN and MCI individuals and whether they are associated with cognitive decline. Images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) were used to construct a pattern classifier that recognizes spatial patterns of brain atrophy which best distinguish Alzheimer's disease patients from CN on an individual person basis. This classifier was subsequently applied to longitudinal magnetic resonance imaging scans of CN and MCI participants in the Baltimore Longitudinal Study of Aging (BLSA) neuroimaging study. The degree to which Alzheimer's disease-like patterns were present in CN and MCI subjects was evaluated longitudinally in relation to cognitive performance. The oldest BLSA CN individuals showed progressively increasing Alzheimer's disease-like patterns of atrophy, and individuals with these patterns had reduced cognitive performance. MCI was associated with steeper longitudinal increases of Alzheimer's disease-like patterns of atrophy, which separated them from CN (receiver operating characteristic area under the curve equal to 0.89). Our results suggest that imaging-based spatial patterns of brain atrophy of Alzheimer's disease, evaluated with sophisticated pattern analysis and recognition methods, may be useful in discriminating among CN individuals who are likely to be stable versus those who will show cognitive decline. Future prospective studies will elucidate the temporal dynamics of spatial atrophy patterns and the emergence of clinical symptoms.

Abstract: BACKGROUND: A number of studies have provided evidence for genetic modulation of brain structure in unaffected family members (FM) of schizophrenia patients using conventional volumetric analysis. High-dimensional pattern classification methods have been reported to have the capacity to determine subtle and spatially complex structural patterns that distinguish schizophrenia patients from healthy control subjects using standard magnetic resonance imaging. This study investigates whether such endophenotypic patterns are found in FM via similar image analysis approaches. METHODS: A high-dimensional pattern classifier was constructed from a group of 69 patients and 79 control subjects, via an analysis that identified a subtle and spatially complex pattern of reduced brain volumes. The constructed classifier was applied to examine brain structure of 30 FM. RESULTS: The classifier indicated that FM had highly overlapping structural profiles with those of patients. Moreover, an orbitofrontal region of relatively increased white matter was found to contribute significantly to the classification, indicating that white matter alterations, along with reductions of gray matter volumes, might be present in patients and unaffected FM. CONCLUSIONS: These findings provide evidence that high-dimensional pattern classification can identify complex and subtle structural endophenotypes that are shared by probands and their unaffected FM.

Abstract: This work builds upon previous studies that reported high sensitivity and specificity in classifying individuals with mild cognitive impairment (MCI), which is often a prodromal phase of Alzheimer's disease (AD), via pattern classification of MRI scans. The current study integrates MRI and PET (15)O water scans from 30 participants in the Baltimore Longitudinal Study of Aging, and tests the hypothesis that joint evaluation of structure and function can yield higher classification accuracy than either alone. Classification rates of up to 100% accuracy were achieved via leave-one-out cross-validation, whereas conservative estimates of generalization performance in new scans, evaluated via bagging cross-validation, yielded an area under the receiver operating characteristic (ROC) curve equal to 0.978 (97.8%), indicating excellent diagnostic accuracy. Spatial maps of regions determined to contribute the most to the classification implicated many temporal, prefrontal, orbitofrontal, and parietal regions. Detecting complex patterns of brain abnormality in early stages of cognitive impairment has pivotal importance for the detection and management of AD.

Abstract: We report evidence that computer-based high-dimensional pattern classification of magnetic resonance imaging (MRI) detects patterns of brain structure characterizing mild cognitive impairment (MCI), often a prodromal phase of Alzheimer's disease (AD). Ninety percent diagnostic accuracy was achieved, using cross-validation, for 30 participants in the Baltimore Longitudinal Study of Aging. Retrospective evaluation of serial scans obtained during prior years revealed gradual increases in structural abnormality for the MCI group, often before clinical symptoms, but slower increase for individuals remaining cognitively normal. Detecting complex patterns of brain abnormality in very early stages of cognitive impairment has pivotal importance for the detection and management of AD.

Abstract: Spatial patterns of brain atrophy in mild cognitive impairment (MCI) and Alzheimer's disease (AD) were measured via methods of computational neuroanatomy. These patterns were spatially complex and involved many brain regions. In addition to the hippocampus and the medial temporal lobe gray matter, a number of other regions displayed significant atrophy, including orbitofrontal and medial-prefrontal grey matter, cingulate (mainly posterior), insula, uncus, and temporal lobe white matter. Approximately 2/3 of the MCI group presented patterns of atrophy that overlapped with AD, whereas the remaining 1/3 overlapped with cognitively normal individuals, thereby indicating that some, but not all, MCI patients have significant and extensive brain atrophy in this cohort of MCI patients. Importantly, the group with AD-like patterns presented much higher rate of MMSE decline in follow-up visits; conversely, pattern classification provided relatively high classification accuracy (87%) of the individuals that presented relatively higher MMSE decline within a year from baseline. High-dimensional pattern classification, a nonlinear multivariate analysis, provided measures of structural abnormality that can potentially be useful for individual patient classification, as well as for predicting progression and examining multivariate relationships in group analyses.

Abstract: This paper presents a method for classification of structural brain magnetic resonance (MR) images, by using a combination of deformation-based morphometry and machine learning methods. A morphological representation of the anatomy of interest is first obtained using a high-dimensional mass-preserving template warping method, which results in tissue density maps that constitute local tissue volumetric measurements. Regions that display strong correlations between tissue volume and classification (clinical) variables are extracted using a watershed segmentation algorithm, taking into account the regional smoothness of the correlation map which is estimated by a cross-validation strategy to achieve robustness to outliers. A volume increment algorithm is then applied to these regions to extract regional volumetric features, from which a feature selection technique using support vector machine (SVM)-based criteria is used to select the most discriminative features, according to their effect on the upper bound of the leave-one-out generalization error. Finally, SVM-based classification is applied using the best set of features, and it is tested using a leave-one-out cross-validation strategy. The results on MR brain images of healthy controls and schizophrenia patients demonstrate not only high classification accuracy (91.8% for female subjects and 90.8% for male subjects), but also good stability with respect to the number of features selected and the size of SVM kernel used.

Abstract: A multivariate classification approach has been presented to examine the brain abnormalities, i.e., due to prenatal cocaine exposure, using both structural and functional brain images. First, a regional statistical feature extraction scheme was adopted to capture discriminative features from voxel-wise morphometric and functional representations of brain images, in order to reduce the dimensionality of the features used for classification, as well as to achieve the robustness to registration error and inter-subject variations. Then, this feature extraction method was used in conjunction with a hybrid feature selection method and a nonlinear support vector machine for the classification of brain abnormalities. This brain classification approach has been applied to detecting the brain abnormality associated with prenatal cocaine exposure in adolescents. A promising classification performance was achieved on a data set of 49 subjects (24 normal and 25 prenatally cocaine-exposed teenagers), with a leave-one-out cross-validation. Experimental results demonstrated the efficacy of our method, as well as the importance of incorporating both structural and functional images for brain classification. Moreover, spatial patterns of group difference derived from the constructed classifier were mostly consistent with the results of the conventional statistical analysis method. Therefore, the proposed approach provided not only a multivariate classification method for detecting brain abnormalities, but also an alternative way for group analysis of multimodality images.

Abstract: Gender is an important biological determinant of vulnerability to psychosocial stress. We used perfusion based functional magnetic resonance imaging (fMRI) to measure cerebral blood flow (CBF) responses to mild to moderate stress in 32 healthy people (16 males and 16 females). Psychological stress was elicited using mental arithmetic tasks under varying pressure. Stress in men was associated with CBF increase in the right prefrontal cortex (RPFC) and CBF reduction in the left orbitofrontal cortex (LOrF), a robust response that persisted beyond the stress task period. In contrast, stress in women primarily activated the limbic system, including the ventral striatum, putamen, insula and cingulate cortex. The asymmetric prefrontal activity in males was associated with a physiological index of stress responses-salivary cortisol, whereas the female limbic activation showed a lower degree of correlations with cortisol. Conjunction analyses indicated only a small degree of overlap between the stress networks in men and women at the threshold level of P < 0.01. Increased overlap of stress networks between the two genders was revealed when the threshold for conjunction analyses was relaxed to P < 0.05. Further, machine classification was used to differentiate the central stress responses between the two genders with over 94% accuracy. Our study may represent an initial step in uncovering the neurobiological basis underlying the contrasting health consequences of psychosocial stress in men and women.

Abstract: A number of neurological diseases are associated with structural and functional alterations in the brain. This paper presents a method of using both structural and functional MR images for brain disease diagnosis, by machine learning and high-dimensional template warping. First, a high-dimensional template warping technique is used to complete morphological and functional representation for each individual brain in a template space, within a mass preserving framework. Then, statistical regional features are extracted to reduce the dimensionality of morphological and functional representation , as well as to achieve the robustness to registration errors and inter-subject variations. Finally, the most discriminative regional features are selected by a hybrid feature method for brain classification, using a nonlinear support vector machine. The proposed method has been applied to classifying the brain images of prenatally cocaine-exposed young adults from those of socioeconomically matched controls, resulting in 91.8% correct classification rate using a leave-one-out cross-validation. Comparison results show the effectiveness of our method and also the importance of simultaneously using both structural and functional images for brain classification.

Abstract: A number of neurological diseases are associated with structural and functional alterations in the brain. This paper presents a method of using both structural and functional MR images for brain disease diagnosis, by machine learning and high-dimensional template warping. First, a high-dimensional template warping technique is used to compute morphological and functional representations for each individual brain in a template space, within a mass preserving framework. Then, statistical regional features are extracted to reduce the dimensionality of morphological and functional representations, as well as to achieve the robustness to registration errors and inter-subject variations. Finally, the most discriminative regional features are selected by a hybrid feature selection method for brain classification, using a nonlinear support vector machine. The proposed method has been applied to classifying the brain images of prenatally cocaine-exposed young adults from those of socioeconomically matched controls, resulting in 91.8% correct classification rate using a leave-one-out cross-validation. Comparison results show the effectiveness of our method and also the importance of simultaneously using both structural and functional images for brain classification.

Abstract: A 4D image registration method is proposed for consistent estimation of cardiac motion from MR image sequences. Under this 4D registration framework, all 3D cardiac images taken at different time-points are registered simultaneously, and motion estimated is enforced to be spatiotemporally smooth, thereby overcoming potential limitations of some methods that typically estimate cardiac deformation sequentially from one frame to another, instead of treating the entire set of images as a 4D volume. To facilitate our image matching process, an attribute vector is designed for each point in the image to include intensity, boundary and geometric moment invariants (GMIs). Hierarchical registration of two image sequences is achieved by using the most distinctive points for initial registration of two sequences and gradually adding less-distinctive points for refinement of registration. Experimental results on real data demonstrate good performance of the proposed method in registering cardiac images and estimating motions from cardiac image sequences.

Abstract: Patterns of brain activity during deception have recently been characterized with fMRI on the multi-subject average group level. The clinical value of fMRI in lie detection will be determined by the ability to detect deception in individual subjects, rather than group averages. High-dimensional non-linear pattern classification methods applied to functional magnetic resonance (fMRI) images were used to discriminate between the spatial patterns of brain activity associated with lie and truth. In 22 participants performing a forced-choice deception task, 99% of the true and false responses were discriminated correctly. Predictive accuracy, assessed by cross-validation in participants not included in training, was 88%. The results demonstrate the potential of non-linear machine learning techniques in lie detection and other possible clinical applications of fMRI in individual subjects, and indicate that accurate clinical tests could be based on measurements of brain function with fMRI.

Abstract: This paper presents a method for classification of medical images, using machine learning and deformation-based morphometry. A morphological representation of the anatomy of interest is first obtained using high-dimensional template warping, from which regions that display strong correlations between morphological measurements and the classification (clinical) variable are extracted using a watershed segmentation, taking into account the regional smoothness of the correlation map which is estimated by a cross-validation strategy in order to achieve robustness to outliers. A Support Vector Machine-Recursive Feature Elimination (SVM-RFE) technique is then used to rank computed features from the extracted regions, according to their effect on the leave-one-out error bound. Finally, SVM classification is applied using the best set of features, and it is tested using leave-one-out. The results from a group of 61 brain images of female normal controls and schizophrenia patients demonstrate not only high classification accuracy (91.8%) and steep ROC curves, but also exceptional stability with respect to the number of selected features and the SVM kernel size.

Abstract: CONTEXT: Neuroanatomic abnormalities in schizophrenia may underlie behavioral manifestations. Characterization of such abnormalities is required for interpreting functional data. Frontotemporal abnormalities have been documented by using predetermined region-of-interest approaches, but deformation-based morphometry permits examination of the entire brain. OBJECTIVES: To perform whole-brain analyses of structural differences between patients with schizophrenia and controls, to examine sex and medication effects, and to apply a high-dimensional nonlinear pattern classification technique to quantify the degree of separation between patients and controls, thereby testing the potential of this new technique as an aid to diagnostic procedures. DESIGN: Whole-brain morphologic analysis using high-dimensional shape transformations. SETTING: Schizophrenia Research Center, University of Pennsylvania Medical Center. PARTICIPANTS: Neuroleptic-naïve and previously treated patients with DSM-IV schizophrenia (n = 69) and sociodemographically matched controls (n = 79). MAIN OUTCOME MEASURES: Gray matter, white matter, and ventricular cerebrospinal fluid volumes in the brain. RESULTS: Magnetic resonance images showed reduced gray matter and increased ventricular cerebrospinal fluid volumes in patients with schizophrenia in the whole brain and in specific foci: the hippocampus and adjacent white matter, the cingulate and orbitofrontal cortex, the frontotemporal and parietotemporal areas, and the occipital areas near the lingual gyrus. The classifier had a mean classification accuracy of 81.1% for men and women combined (82% for women and 85% for men, when each group was treated separately), determined via cross-validation. CONCLUSIONS: This study confirms previous findings of reduced frontotemporal volumes and suggests new hypotheses, especially involving occipital association and speech production areas. It also suggests finer localization of volume reduction in the hippocampus and other limbic structures and in the frontal lobe. Pattern classification showed high sensitivity and specificity for the diagnosis of schizophrenia, suggesting the potential utility of magnetic resonance imaging as a diagnostic aid.