An Efficient Approach for Differentiating Alzheimer's Disease from Normal Elderly Based on Multicenter MRI Using Gray-Level Invariant Features

Machine learning techniques, along with imaging markers extracted from structural magnetic resonance images, have been shown to increase the accuracy to differentiate patients with Alzheimer''s disease (AD) from normal elderly controls. Several forms of anatomical features, such as cortical volume, shape, and thickness, have demonstrated discriminative capability. These approaches rely on accurate non-linear image transformation, which could invite several nuisance factors, such as dependency on transformation parameters and the degree of anatomical abnormality, and an unpredictable influence of residual registration errors. In this study, we tested a simple method to extract disease-related anatomical features, which is suitable for initial stratification of the heterogeneous patient populations often encountered in clinical data. The method employed gray-level invariant features, which were extracted from linearly transformed images, to characterize AD-specific anatomical features. The intensity information from a disease-specific spatial masking, which was linearly registered to each patient, was used to capture the anatomical features. We implemented a two-step feature selection for anatomic recognition. First, a statistic-based feature selection was implemented to extract AD-related anatomical features while excluding non-significant features. Then, seven knowledge-based ROIs were used to capture the local discriminative powers of selected voxels within areas that were sensitive to AD or mild cognitive impairment (MCI). The discriminative capability of the proposed feature was measured by its performance in differentiating AD or MCI from normal elderly controls (NC) using a support vector machine. The statistic-based feature selection, together with the knowledge-based masks, provided a promising solution for capturing anatomical features of the brain efficiently. For the analysis of clinical populations, which are inherently heterogeneous, this approach could stratify the large amount of data rapidly and could be combined with more detailed subsequent analyses based on non-linear transformation.     

The effect of feature selection on multivariate pattern analysis of structural brain MR images

Clinical predictions performed using structural magnetic resonance (MR) images are crucial in neuroimaging studies and can be used as a successful complementary method for clinical decision making. Multivariate pattern analysis (MVPA) is a significant tool that helps correct predictions by exhibiting a compound relationship between disease-related features. In this study, the effectiveness of determining the most relevant features for MVPA of the brain MR images are examined using ReliefF and minimum Redundancy Maximum Relevance (mRMR) algorithms to predict the Alzheimer’s disease (AD), schizophrenia, autism, and attention deficit and hyperactivity disorder (ADHD). Three state-of-the-art MVPA algorithms namely support vector machines (SVM), k-nearest neighbor (kNN) and backpropagation neural network (BP-NN) are employed to analyze the images from five different datasets that include 1390 subjects in total. Feature selection is performed on structural brain features such as volumes and thickness of anatomical structures and selected features are used to compare the effect of feature selection on different MVPA algorithms. Selecting the most relevant features for differentiating images of healthy controls from the diseased subjects using both ReliefF and mRMR methods significantly increased the performance. The most successful MVPA method was SVM for all classification tasks.     

Homology as a parsimony problem: a dynamic homology approach for morphological data

The primary data used to reconstruct phylogenies comes organized in the conceptual grid of homology correspondences, and the construction of this theory‐rich grid depends in part on knowledge of relationships. This situation is not satisfactory as a conceptual system, because the evidence is not clearly delimited from the results. I explore the testing of alternative hypotheses of morphological correspondences in a quantitative cladistic context. The varying homology assessments implied by classical criteria of homology (topological equivalence, or position and connections; composition of structures, or commonality in details of construction) can be expressed as regular characters in a cladistic analysis. Doing so provides adequate transformation costs for changes in schemas of correspondences. Correspondences imply evolutionary transformations, and multiple schemas of correspondences can be compared according to the evolutionary transformations that they imply. The method is used to test the correspondences in sclerites of the male copulatory organs of spiders of the subfamily Amaurobioidinae (Arachnida, Araneae, Anyphaenidae). The correspondences of three sclerites are tested, in a data set of 93 species having one, two or three sclerites, using a simultaneous analysis of all the morphological characters. Most parsimonious trees are identified together with the correspondences they imply. Once the correspondences are integrated in the phylogenetic analysis, it is easy to evaluate the robustness of trees or decay in optimality after changes in anatomical interpretations. A Bremer support for anatomical interpretations is proposed, calculated as the increase in tree length when the specific interpretation is not used. © The Willi Hennig Society 2007.     

A Spectral Graph Regression Model for Learning Brain Connectivity of Alzheimer’s Disease

Understanding network features of brain pathology is essential to reveal underpinnings of neurodegenerative diseases. In this paper, we introduce a novel graph regression model (GRM) for learning structural brain connectivity of Alzheimer''s disease (AD) measured by amyloid-β deposits. The proposed GRM regards ¹¹C-labeled Pittsburgh Compound-B (PiB) positron emission tomography (PET) imaging data as smooth signals defined on an unknown graph. This graph is then estimated through an optimization framework, which fits the graph to the data with an adjustable level of uniformity of the connection weights. Under the assumed data model, results based on simulated data illustrate that our approach can accurately reconstruct the underlying network, often with better reconstruction than those obtained by both sample correlation and ℓ1-regularized partial correlation estimation. Evaluations performed upon PiB-PET imaging data of 30 AD and 40 elderly normal control (NC) subjects demonstrate that the connectivity patterns revealed by the GRM are easy to interpret and consistent with known pathology. Moreover, the hubs of the reconstructed networks match the cortical hubs given by functional MRI. The discriminative network features including both global connectivity measurements and degree statistics of specific nodes discovered from the AD and NC amyloid-beta networks provide new potential biomarkers for preclinical and clinical AD.     

White Matter Changes in Patients with Amnestic Mild Cognitive Impairment Detected by Diffusion Tensor Imaging

Compared to normal aging adults, individuals with amnestic mild cognitive impairment (aMCI) have significantly increased risk for progressing into Alzheimer’s disease (AD). Autopsy studies found that most of the brains of aMCI cases showed anatomical features associated with AD pathology. The recent development of non-invasive neuroimaging technique, such as diffusion tensor imaging (DTI), makes it possible to investigate the microstructures of the cerebral white matter in vivo. We hypothesized that disrupted white matter (WM) integrity existed in aMCI. So we used DTI technique, by measuring fractional anisotropy (FA) and mean diffusivity (MD), to test the brain structures involved in patients with aMCI. DTI scans were collected from 40 patients with aMCI, and 28 normal controls (NC). Tract-based spatial statistics (TBSS) analyses of whole-brain FA and MD images in each individual and group comparisons were carried out. Compared to NC, aMCI patients showed significant FA reduction bilaterally, in the association and projection fibers of frontal, parietal, and temporal lobes, corpus callosum, bilateral corona radiation, right posterior thalamic radiation and right sagittal stratum. aMCI patients also showed significantly increased MD widespreadly in the association and projection fibers of frontal, parietal and temporal lobes, and corpus callosum. Assessment of the WM integrity of the frontal, parietal, temporal lobes, and corpus callosum by using DTI measures may aid early diagnosis of aMCI.     

A new method in computer-assisted imaging in neuroanatomy

A procedure is described yielding computed images of postmortem brains with high topographic accuracy. Structures of the brain are traced and registered by means of a digitizer capable of measuring coordinates three-dimensionally. The information corresponding to one brain model is stored on a flexible disk with a capacity of 256 Kbytes. According to the output desired, the resulting brain images are either completely or partially displayed on the computer screen as stereo pairs. The brain models possess a local fidelity of about 1 mm. The images are useful in simultaneously studying superficial and central parts of the brain, spatial relationships of the various structures and the projection of deep structures onto the surface of the brain. A RAM of about 100 Kbytes is necessary for a program enabling the user to perform stereo projections, three-dimensional transformations and other image manipulations. The special features of anatomical computer imaging as compared to computed tomography (CT) and nuclear magnetic resonance imaging (NMR) are outlined. A combination of these different techniques seems to improve clinical diagnosis.     

RootAnalyzer: A Cross-Section Image Analysis Tool for Automated Characterization of Root Cells and Tissues

The morphology of plant root anatomical features is a key factor in effective water and nutrient uptake. Existing techniques for phenotyping root anatomical traits are often based on manual or semi-automatic segmentation and annotation of microscopic images of root cross sections. In this article, we propose a fully automated tool, hereinafter referred to as RootAnalyzer, for efficiently extracting and analyzing anatomical traits from root-cross section images. Using a range of image processing techniques such as local thresholding and nearest neighbor identification, RootAnalyzer segments the plant root from the image’s background, classifies and characterizes the cortex, stele, endodermis and epidermis, and subsequently produces statistics about the morphological properties of the root cells and tissues. We use RootAnalyzer to analyze 15 images of wheat plants and one maize plant image and evaluate its performance against manually-obtained ground truth data. The comparison shows that RootAnalyzer can fully characterize most root tissue regions with over 90% accuracy.     

Structural Interactions within the Default Mode Network Identified by Bayesian Network Analysis in Alzheimer’s Disease

Alzheimer’s disease (AD) is a well-known neurodegenerative disease that is associated with dramatic morphological abnormalities. The default mode network (DMN) is one of the most frequently studied resting-state networks. However, less is known about specific structural dependency or interactions among brain regions within the DMN in AD. In this study, we performed a Bayesian network (BN) analysis based on regional grey matter volumes to identify differences in structural interactions among core DMN regions in structural MRI data from 80 AD patients and 101 normal controls (NC). Compared to NC, the structural interactions between the medial prefrontal cortex (mPFC) and other brain regions, including the left inferior parietal cortex (IPC), the left inferior temporal cortex (ITC) and the right hippocampus (HP), were significantly reduced in the AD group. In addition, the AD group showed prominent increases in structural interactions from the left ITC to the left HP, the left HP to the right ITC, the right HP to the right ITC, and the right IPC to the posterior cingulate cortex (PCC). The BN models significantly distinguished AD patients from NC with 87.12% specificity and 81.25% sensitivity. We then used the derived BN models to examine the replicability and stability of AD-associated BN models in an independent dataset and the results indicated discriminability with 83.64% specificity and 80.49% sensitivity. The results revealed that the BN analysis was effective for characterising regional structure interactions and the AD-related BN models could be considered as valid and predictive structural brain biomarker models for AD. Therefore, our study can assist in further understanding the pathological mechanism of AD, based on the view of the structural network, and may provide new insights into classification and clinical application in the study of AD in the future.     

Detecting and analyzing differentially activated pathways in brain regions of Alzheimer's disease patients

Alzheimer's disease (AD) generally results in neuronal loss due to protein dysfunction in various brain regions. Genome-wide data have provided new opportunities to analyze the underlying mechanisms of AD. Here, we present a novel network-based systems biology framework to identify and analyze differentially activated pathways by integrating human protein-protein interaction data and gene expression profile data in six brain regions. Specifically, we propose a new scoring system by ranking the edges associated with AD. Then, an edge expansion algorithm is designed to identify the dysfunctional pathways implicated in AD pathogenesis in six brain regions respectively. The analyses of the similarities and differences of these dysfunctional pathways provide insights into understanding the dynamics of AD progression in six brain regions from a network perspective, which will further shed light on the pathogenesis of AD.     

Patterns of differences in brain morphology in humans as compared to extant apes

Although human evolution is characterized by a vast increase in brain size, it is not clear whether or not certain regions of the brain are enlarged disproportionately in humans, or how this enlargement relates to differences in overall neural morphology. The aim of this study is to determine whether or not there are specific suites of features that distinguish the morphology of the human brain from that of apes. The study sample consists of whole brain, in vivo magnetic resonance images (MRIs) of anatomically modern humans (Homo sapiens sapiens) and five ape species (gibbons, orangutans, gorillas, chimpanzees, bonobos). Twenty-nine 3D landmarks, including surface and internal features of the brain were located on 3D MRI reconstructions of each individual using MEASURE software. Landmark coordinate data were scaled for differences in size and analyzed using Euclidean Distance Matrix Analysis (EDMA) to statistically compare the brains of each non-human ape species to the human sample. Results of analyses show both a pattern of brain morphology that is consistently different between all apes and humans, as well as patterns that differ among species. Further, both the consistent and species-specific patterns include cortical and subcortical features. The pattern that remains consistent across species indicates a morphological reorganization of 1) relationships between cortical and subcortical frontal structures, 2) expansion of the temporal lobe and location of the amygdala, and 3) expansion of the anterior parietal region. Additionally, results demonstrate that, although there is a pattern of morphology that uniquely defines the human brain, there are also patterns that uniquely differentiate human morphology from the morphology of each non-human ape species, indicating that reorganization of neural morphology occurred at the evolutionary divergence of each of these groups.     

Multiscale feature analysis of salivary gland branching morphogenesis

Pattern formation in developing tissues involves dynamic spatio-temporal changes in cellular organization and subsequent evolution of functional adult structures. Branching morphogenesis is a developmental mechanism by which patterns are generated in many developing organs, which is controlled by underlying molecular pathways. Understanding the relationship between molecular signaling, cellular behavior and resulting morphological change requires quantification and categorization of the cellular behavior. In this study, tissue-level and cellular changes in developing salivary gland in response to disruption of ROCK-mediated signaling by are modeled by building cell-graphs to compute mathematical features capturing structural properties at multiple scales. These features were used to generate multiscale cell-graph signatures of untreated and ROCK signaling disrupted salivary gland organ explants. From confocal images of mouse submandibular salivary gland organ explants in which epithelial and mesenchymal nuclei were marked, a multiscale feature set capturing global structural properties, local structural properties, spectral, and morphological properties of the tissues was derived. Six feature selection algorithms and multiway modeling of the data was performed to identify distinct subsets of cell graph features that can uniquely classify and differentiate between different cell populations. Multiscale cell-graph analysis was most effective in classification of the tissue state. Cellular and tissue organization, as defined by a multiscale subset of cell-graph features, are both quantitatively distinct in epithelial and mesenchymal cell types both in the presence and absence of ROCK inhibitors. Whereas tensor analysis demonstrate that epithelial tissue was affected the most by inhibition of ROCK signaling, significant multiscale changes in mesenchymal tissue organization were identified with this analysis that were not identified in previous biological studies. We here show how to define and calculate a multiscale feature set as an effective computational approach to identify and quantify changes at multiple biological scales and to distinguish between different states in developing tissues.     

Multi-method analysis of MRI images in early diagnostics of Alzheimer's disease

The role of structural brain magnetic resonance imaging (MRI) is becoming more and more emphasized in the early diagnostics of Alzheimer's disease (AD). This study aimed to assess the improvement in classification accuracy that can be achieved by combining features from different structural MRI analysis techniques. Automatically estimated MR features used are hippocampal volume, tensor-based morphometry, cortical thickness and a novel technique based on manifold learning. Baseline MRIs acquired from all 834 subjects (231 healthy controls (HC), 238 stable mild cognitive impairment (S-MCI), 167 MCI to AD progressors (P-MCI), 198 AD) from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database were used for evaluation. We compared the classification accuracy achieved with linear discriminant analysis (LDA) and support vector machines (SVM). The best results achieved with individual features are 90% sensitivity and 84% specificity (HC/AD classification), 64%/66% (S-MCI/P-MCI) and 82%/76% (HC/P-MCI) with the LDA classifier. The combination of all features improved these results to 93% sensitivity and 85% specificity (HC/AD), 67%/69% (S-MCI/P-MCI) and 86%/82% (HC/P-MCI). Compared with previously published results in the ADNI database using individual MR-based features, the presented results show that a comprehensive analysis of MRI images combining multiple features improves classification accuracy and predictive power in detecting early AD. The most stable and reliable classification was achieved when combining all available features.     

Identification of distinctive features in human intracranial tumors by label‐free nonlinear multimodal microscopy

Nonlinear multimodal microscopy offers a series of label‐free techniques with potential for intraoperative identification of tumor borders in situ using novel endoscopic devices. Here, we combined coherent anti‐Stokes Raman scattering, two‐photon excited fluorescence (TPEF) and second harmonic generation imaging to analyze biopsies of different human brain tumors, with the aim to understand whether the morphological information carried by single field of view images, similar to what delivered by present endoscopic systems, is sufficient for tumor recognition. We imaged 40 human biopsies of high and low grade glioma, meningioma, as well as brain metastases of melanoma, breast, lung and renal carcinoma, in comparison with normal brain parenchyma. Furthermore, five biopsies of schwannoma were analyzed and compared with nonpathological nerve tissue. Besides the high cellularity, the typical features of tumor, which were identified and quantified, are intracellular and extracellular lipid droplets, aberrant vessels, extracellular matrix collagen and diffuse TPEF. Each tumor type displayed a particular morphochemistry characterized by specific patterns of the above‐mentioned features. Nonlinear multimodal microscopy performed on fresh unprocessed biopsies confirmed that the technique has the ability to visualize tumor structures and discern normal from neoplastic tissue likewise in conditions close to in situ.      

Abnormal cortical networks in mild cognitive impairment and Alzheimer's disease

Recently, many researchers have used graph theory to study the aberrant brain structures in Alzheimer's disease (AD) and have made great progress. However, the characteristics of the cortical network in Mild Cognitive Impairment (MCI) are still largely unexplored. In this study, the gray matter volumes obtained from magnetic resonance imaging (MRI) for all brain regions except the cerebellum were parcellated into 90 areas using the automated anatomical labeling (AAL) template to construct cortical networks for 98 normal controls (NCs), 113 MCIs and 91 ADs. The measurements of the network properties were calculated for each of the three groups respectively. We found that all three cortical networks exhibited small-world properties and those strong interhemispheric correlations existed between bilaterally homologous regions. Among the three cortical networks, we found the greatest clustering coefficient and the longest absolute path length in AD, which might indicate that the organization of the cortical network was the least optimal in AD. The small-world measures of the MCI network exhibited intermediate values. This finding is logical given that MCI is considered to be the transitional stage between normal aging and AD. Out of all the between-group differences in the clustering coefficient and absolute path length, only the differences between the AD and normal control groups were statistically significant. Compared with the normal controls, the MCI and AD groups retained their hub regions in the frontal lobe but showed a loss of hub regions in the temporal lobe. In addition, altered interregional correlations were detected in the parahippocampus gyrus, medial temporal lobe, cingulum, fusiform, medial frontal lobe, and orbital frontal gyrus in groups with MCI and AD. Similar to previous studies of functional connectivity, we also revealed increased interregional correlations within the local brain lobes and disrupted long distance interregional correlations in groups with MCI and AD.     

Dense Neuron Clustering Explains Connectivity Statistics in Cortical Microcircuits

Local cortical circuits appear highly non-random, but the underlying connectivity rule remains elusive. Here, we analyze experimental data observed in layer 5 of rat neocortex and suggest a model for connectivity from which emerge essential observed non-random features of both wiring and weighting. These features include lognormal distributions of synaptic connection strength, anatomical clustering, and strong correlations between clustering and connection strength. Our model predicts that cortical microcircuits contain large groups of densely connected neurons which we call clusters. We show that such a cluster contains about one fifth of all excitatory neurons of a circuit which are very densely connected with stronger than average synapses. We demonstrate that such clustering plays an important role in the network dynamics, namely, it creates bistable neural spiking in small cortical circuits. Furthermore, introducing local clustering in large-scale networks leads to the emergence of various patterns of persistent local activity in an ongoing network activity. Thus, our results may bridge a gap between anatomical structure and persistent activity observed during working memory and other cognitive processes.     

Geometric Morphometrics of Rodent Sperm Head Shape

Mammalian spermatozoa, particularly those of rodent species, are extremely complex cells and differ greatly in form and dimensions. Thus, characterization of sperm size and, particularly, sperm shape represents a major challenge. No consensus exists on a method to objectively assess size and shape of spermatozoa. In this study we apply the principles of geometric morphometrics to analyze rodent sperm head morphology and compare them with two traditional morphometry methods, that is, measurements of linear dimensions and dimensions-derived parameters calculated using formulae employed in sperm morphometry assessments. Our results show that geometric morphometrics clearly identifies shape differences among rodent spermatozoa. It is also capable of discriminating between size and shape and to analyze these two variables separately. Thus, it provides an accurate method to assess sperm head shape. Furthermore, it can identify which sperm morphology traits differ between species, such as the protrusion or retraction of the base of the head, the orientation and relative position of the site of flagellum insertion, the degree of curvature of the hook, and other distinct anatomical features and appendices. We envisage that the use of geometric morphometrics may have a major impact on future studies focused on the characterization of sperm head formation, diversity of sperm head shape among species (and underlying evolutionary forces), the effects of reprotoxicants on changes in cell shape, and phenotyping of genetically-modified individuals.     

Influence of APOE Genotype on Hippocampal Atrophy over Time - An N=1925 Surface-Based ADNI Study

The apolipoprotein E (APOE) e4 genotype is a powerful risk factor for late-onset Alzheimer’s disease (AD). In the Alzheimer’s Disease Neuroimaging Initiative (ADNI) cohort, we previously reported significant baseline structural differences in APOE e4 carriers relative to non-carriers, involving the left hippocampus more than the right—a difference more pronounced in e4 homozygotes than heterozygotes. We now examine the longitudinal effects of APOE genotype on hippocampal morphometry at 6-, 12- and 24-months, in the ADNI cohort. We employed a new automated surface registration system based on conformal geometry and tensor-based morphometry. Among different hippocampal surfaces, we computed high-order correspondences, using a novel inverse-consistent surface-based fluid registration method and multivariate statistics consisting of multivariate tensor-based morphometry (mTBM) and radial distance. At each time point, using Hotelling’s T² test, we found significant morphological deformation in APOE e4 carriers relative to non-carriers in the full cohort as well as in the non-demented (pooled MCI and control) subjects at each follow-up interval. In the complete ADNI cohort, we found greater atrophy of the left hippocampus than the right, and this asymmetry was more pronounced in e4 homozygotes than heterozygotes. These findings, combined with our earlier investigations, demonstrate an e4 dose effect on accelerated hippocampal atrophy, and support the enrichment of prevention trial cohorts with e4 carriers.     

Searching for Sex Differences in the Vomeronasal Pathway

The sexual differentiation of brain and behavior is reviewed from the findings of sex differences in the vomeronasal pathway. A motivational approach to sex differences in reproductive behavior is stressed by taking into account that sex differences are present in neural networks: from the receptor organ (the vomeronasal organ) to effector nuclei. Sex differences in the brain appear in two morphological patterns. In one, the male presents greater morphological measurements than the female; in the other, the opposite occurs. These two morphological patterns are actively differentiated by gonadal steroids. The functional significance of these two morphological patterns is addressed. Moreover, since the GABA_Areceptor is involved in the organization of sex differences in vomeronasal structures such as the accessory olfactory bulb and in maternal behavior, the role of membrane mechanisms, 5α reduced hormones, and neurosteroids in the sexual differentiation process is discussed.