The hippocampus is involved at the onset of the neuropathological pathways leading to Alzheimer’s disease (AD). Individuals with Mild Cognitive Impairment (MCI) are at increased risk of AD. Hippocampal volume has been shown to predict which MCI subjects will convert to AD. Our aim in the present study was to produce a fully automated prognostic procedure, scalable to high throughput clinical and research applications, for the prediction of MCI conversion to AD using 3D hippocampal morphology. We used an automated analysis for the extraction and mapping of the hippocampus from structural magnetic resonance scans to extract 3D hippocampal shape morphology, and we then applied machine learning classification to predict conversion from MCI to AD. We investigated the accuracy of prediction in 103 MCI subjects (mean age 74.1 years) from the longitudinal AddNeuroMed study. Our model correctly predicted MCI conversion to dementia within a year at an accuracy of 80% (sensitivity 77%, specificity 80%), a performance which is competitive with previous predictive models dependent on manual measurements. Categorization of MCI subjects based on hippocampal morphology revealed more rapid cognitive deterioration in MMSE scores (p < 0.01) and CERAD verbal memory (p < 0.01) in those subjects who were predicted to develop dementia relative to those predicted to remain stable. The pattern of atrophy associated with increased risk of conversion demonstrated initial degeneration in the anterior part of the cornus ammonis 1 (CA1) hippocampal subregion. We conclude that automated shape analysis generates sensitive measurements of early neurodegeneration which predates the onset of dementia and thus provides a prognostic biomarker for conversion of MCI to AD.
Neuroimaging; Hippocampus; Prognosis; Automated methods; Alzheimer’s disease; Mild Cognitive Impairment
To create a sentiment classification system for the Fifth i2b2/VA Challenge Track 2, which can identify thirteen subjective categories and two objective categories.
We developed a hybrid system using Support Vector Machine (SVM) classifiers with augmented training data from the Internet. Our system consists of three types of classification-based systems: the first system uses spanning n-gram features for subjective categories, the second one uses bag-of-n-gram features for objective categories, and the third one uses pattern matching for infrequent or subtle emotion categories. The spanning n-gram features are selected by a feature selection algorithm that leverages emotional corpus from weblogs. Special normalization of objective sentences is generalized with shallow parsing and external web knowledge. We utilize three sources of web data: the weblog of LiveJournal which helps to improve the feature selection, the eBay List which assists in special normalization of information and instructions categories, and the suicide project web which provides unlabeled data with similar properties as suicide notes.
The performance is evaluated by the overall micro-averaged precision, recall and F-measure.
Our system achieved an overall micro-averaged F-measure of 0.59. Happiness_peacefulness had the highest F-measure of 0.81. We were ranked as the second best out of 26 competing teams.
Our results indicated that classifying fine-grained sentiments at sentence level is a non-trivial task. It is effective to divide categories into different groups according to their semantic properties. In addition, our system performance benefits from external knowledge extracted from publically available web data of other purposes; performance can be further enhanced when more training data is available.
sentiment analysis; suicide note; spanning n-gram; web data; supervised approach
In this paper, we study the classification problem in the situation where large volumes of training data become available sequentially (online learning). In medical imaging, this is typical, e.g., a 3D brain MRI dataset may be gradually collected from a patient population, and not all of the data is available when the analysis begins. First, we describe two common ensemble learning algorithms, AdaBoost and bagging, and their corresponding online learning versions. We then show why each is ineffective for segmenting a gradually increasing set of medical images. Instead, we introduce a new ensemble learning algorithm, termed Lossless Online Ensemble Learning (LOEL). This algorithm is lossless in the online case, compared to its batch mode. LOEL outperformed online-AdaBoost and online-bagging when validated on a standardized dataset; it also performed better when used to segment the hippocampus from brain MRI scans of patients with Alzheimer’s Disease and matched healthy subjects. Among those tested, LOEL largely outperformed the alternative online learning algorithms and gave excellent error metrics that were consistent between the online and offline case; it also accurately distinguished AD subjects from healthy controls based on automated measures of hippocampal volume.
We compared four automated methods for hippocampal segmentation using different machine learning algorithms (1) hierarchical AdaBoost, (2) Support Vector Machines (SVM) with manual feature selection, (3) hierarchical SVM with automated feature selection (Ada-SVM), and (4) a publicly available brain segmentation package (FreeSurfer). We trained our approaches using T1-weighted brain MRI’s from 30 subjects (10 normal elderly, 10 mild cognitive impairment (MCI), and 10 Alzheimer’s disease (AD)), and tested on an independent set of 40 subjects (20 normal, 20 AD). Manually segmented gold standard hippocampal tracings were available for all subjects (training and testing). We assessed each approach’s accuracy relative to manual segmentations, and its power to map AD effects. We then converted the segmentations into parametric surfaces to map disease effects on anatomy. After surface reconstruction, we computed significance maps, and overall corrected p-values, for the 3D profile of shape differences between AD and normal subjects. Our AdaBoost and Ada-SVM segmentations compared favorably with the manual segmentations and detected disease effects as well as FreeSurfer on the data tested. Cumulative p-value plots, in conjunction with the False Discovery Rate method, were used to examine the power of each method to detect correlations with diagnosis and cognitive scores. We also evaluated how segmentation accuracy depended on the size of the training set, providing practical information for future users of this technique.
AdaBoost; Alzheimer’s disease; hippocampal segmentation; support vector machines; surface modeling; Subcoritcal Segmentation; Hippocampus
We used a new method we developed for automated hippocampal segmentation, called the auto context model (ACM), to analyze brain MRI scans of 400 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). After training the classifier on 21 hand-labeled expert segmentations, we created binary maps of the hippocampus for three age- and sex-matched groups: 100 subjects with Alzheimer’s disease (AD), 200 with mild cognitive impairment (MCI) and 100 elderly controls (mean age: 75.84; SD: 6.64). Hippocampal traces were converted to parametric surface meshes and a radial atrophy mapping technique was used to compute average surface models and local statistics of atrophy. Surface-based statistical maps visualized links between regional atrophy and diagnosis (MCI versus controls: p = 0.008; MCI versus AD: p = 0.001), mini-mental state exam (MMSE) scores, and global and sum-of-boxes clinical dementia rating scores (CDR; all p < 0.0001, corrected). Right but not left hippocampal atrophy was associated with geriatric depression scores (p = 0.004, corrected); hippocampal atrophy was not associated with subsequent decline in MMSE and CDR scores, educational level, ApoE genotype, systolic or diastolic blood pressure measures, or homocysteine. We gradually reduced sample sizes and used false discovery rate curves to examine the method’s power to detect associations with diagnosis and cognition in smaller samples. 40 subjects were sufficient to discriminate AD from normal and correlate atrophy with CDR scores; 104, 200 and 304 subjects, respectively, were required to correlate MMSE with atrophy, to distinguish MCI from normal, and MCI from AD.
In this paper, we propose an automated approach for the joint detection of major sulci on cortical surfaces. By representing sulci as nodes in a graphical model, we incorporate Markovian relations between sulci and formulate their detection as a maximum a posteriori (MAP) estimation problem over the joint space of major sulci. To make the inference tractable, a sample space with a finite number of candidate curves is automatically generated at each node based on the Hamilton–Jacobi skeleton of sulcal regions. Using the AdaBoost algorithm, we learn both individual and pairwise shape priors of sulcal curves from training data, which are then used to define potential functions in the graphical model based on the connection between AdaBoost and logistic regression. Finally belief propagation is used to perform the MAP inference and select the joint detection results from the sample spaces of candidate curves. In our experiments, we quantitatively validate our algorithm with manually traced curves and demonstrate the automatically detected curves can capture the main body of sulci very accurately. A comparison with independently detected results is also conducted to illustrate the advantage of the joint detection approach.
Index Terms; AdaBoost; boosted prior; cortex; graphical model; major sulci; shape prior
In this paper, a hybrid discriminative/generative model for brain anatomical structure segmentation is proposed. The learning aspect of the approach is emphasized. In the discriminative appearance models, various cues such as intensity and curvatures are combined to locally capture the complex appearances of different anatomical structures. A probabilistic boosting tree (PBT) framework is adopted to learn multi-class discriminative models that combine hundreds of features across different scales. On the generative model side, both global and local shape models are used to capture the shape information about each anatomical structure. The parameters to combine the discriminative appearance and generative shape models are also automatically learned. Thus low-level and high-level information is learned and integrated in a hybrid model. Segmentations are obtained by minimizing an energy function associated with the proposed hybrid model. Finally, a grid-face structure is designed to explicitly represent the 3D region topology. This representation handles an arbitrary number of regions and facilitates fast surface evolution. Our system was trained and tested on a set of 3D MRI volumes and the results obtained are encouraging.
Brain anatomical structures; segmentation; probabilistic boosting tree; discriminative models; generative models
We introduce a new method for brain MRI segmentation, called the auto context model (ACM), to segment the hippocampus automatically in 3D T1-weighted structural brain MRI scans of subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI). In a training phase, our algorithm used 21 hand-labeled segmentations to learn a classification rule for hippocampal versus non-hippocampal regions using a modified AdaBoost method, based on ∼18,000 features (image intensity, position, image curvatures, image gradients, tissue classification maps of gray/white matter and CSF, and mean, standard deviation, and Haar filters of size 1×1×1 to 7×7×7). We linearly registered all brains to a standard template to devise a basic shape prior to capture the global shape of the hippocampus, defined as the pointwise summation of all the training masks. We also included curvature, gradient, mean, standard deviation, and Haar filters of the shape prior and the tissue classified images as features. During each iteration of ACM - our extension of AdaBoost - the Bayesian posterior distribution of the labeling was fed back in as an input, along with its neighborhood features, as new features for AdaBoost to use. In validation studies, we compared our results with hand-labeled segmentations by two experts. Using a leave-one-out approach and standard overlap and distance error metrics, our automated segmentations agreed well with human raters; any differences were comparable to differences between trained human raters. Our error metrics compare favorably with those previously reported for other automated hippocampal segmentations, suggesting the utility of the approach for large-scale studies.
The area and volume of brain structural features, as assessed by high-resolution 3D magnetic resonance imaging (MRI), are among the most heritable measures relating to the human central nervous system. We have conducted MRI scanning of all available monkeys over 2 years of age (n=357) from the extended multigenerational pedigree of the Vervet Research Colony (VRC). Using a combination of automated and manual segmentation we have quantified several correlated but distinct brain structural phenotypes. The estimated heritabilities (h2) for these measures in the VRC are higher than those reported previously for such features in humans or in other non human primates (NHP): total brain volume (h2=0.99, standard error (se)=0.06), cerebral volume (h2=0.98, se=0.06), cerebellar volume (h2=0.86, se=0.09), hippocampal volume (h2=0.95, se=0.07) and corpus callosum cross-sectional areas (h2=0.87, se=0.07). These findings indicate that, in the controlled environment and with the inbreeding structure of the VRC, additive genetic factors account for almost all of the observed variance in brain structure, and suggest the potential of the VRC for genetic mapping of quantitative trait loci (QTL) underlying such variance.
Genetics; Primate; Imaging; Hippocampus; Cerebellum; Callosum
As one of the earliest structures to degenerate in Alzheimer’s disease (AD), the hippocampus is the target of many studies of factors that influence rates of brain degeneration in the elderly. In one of the largest brain mapping studies to date, we mapped the 3D profile of hippocampal degeneration over time in 490 subjects scanned twice with brain MRI over a 1-year interval (980 scans). We examined baseline and 1-year follow-up scans of 97 AD subjects (49 males/48 females), 148 healthy control subjects (75 males/73 females), and 245 subjects with mild cognitive impairment (MCI; 160 males/85 females). We used our previously validated automated segmentation method, based on AdaBoost, to create 3D hippocampal surface models in all 980 scans. Hippocampal volume loss rates increased with worsening diagnosis (normal=0.66%/year; MCI=3.12%/year; AD=5.59%/year), and correlated with both baseline and interval changes in Mini-Mental State Examination (MMSE) scores and global and sum-of-boxes Clinical Dementia Rating scale (CDR) scores. Surface-based statistical maps visualized a selective profile of ongoing atrophy in all three diagnostic groups. Healthy controls carrying the ApoE4 gene atrophied faster than non-carriers, while more educated controls atrophied more slowly; converters from MCI to AD showed faster atrophy than non-converters. Hippocampal loss rates can be rapidly mapped, and they track cognitive decline closely enough to be used as surrogate markers of Alzheimer’s disease in drug trials. They also reveal genetically greater atrophy in cognitively intact subjects.
We propose in this paper a new method for the mapping of hippocampal (HC) surfaces to establish correspondences between points on HC surfaces and enable localized HC shape analysis. A novel geometric feature, the intrinsic shape context, is defined to capture the global characteristics of the HC shapes. Based on this intrinsic feature, an automatic algorithm is developed to detect a set of landmark curves that are stable across population. The direct map between a source and target HC surface is then solved as the minimizer of a harmonic energy function defined on the source surface with landmark constraints. For numerical solutions, we compute the map with the approach of solving partial differential equations on implicit surfaces. The direct mapping method has the following properties: 1) it has the advantage of being automatic; 2) it is invariant to the pose of HC shapes. In our experiments, we apply the direct mapping method to study temporal changes of HC asymmetry in Alzheimer disease (AD) using HC surfaces from 12 AD patients and 14 normal controls. Our results show that the AD group has a different trend in temporal changes of HC asymmetry than the group of normal controls. We also demonstrate the flexibility of the direct mapping method by applying it to construct spherical maps of HC surfaces. Spherical harmonics (SPHARM) analysis is then applied and it confirms our results about temporal changes of HC asymmetry in AD.
Hippocampal surface; intrinsic shape context; direct mapping; shape analysis; implicit representation; level set; temporal changes; asymmetry; Alzheimer disease