Phenotypic signatures in clinical data enable systematic identification of patients for genetic testing.

Around 5% of the population is affected by a rare genetic disease, yet most endure years of uncertainty before receiving a genetic test. A common feature of genetic diseases is the presence of multiple rare phenotypes that often span organ systems. Here, we use diagnostic billing information from longitudinal clinical data in the electronic health records (EHRs) of 2,286 patients who received a chromosomal microarray test, and 9,144 matched controls, to build a model to predict who should receive a genetic test. The model achieved high prediction accuracies in a held-out test sample (area under the receiver operating characteristic curve (AUROC), 0.97; area under the precision-recall curve (AUPRC), 0.92), in an independent hospital system (AUROC, 0.95; AUPRC, 0.62), and in an independent set of 172,265 patients in which cases were broadly defined as having an interaction with a genetics provider (AUROC, 0.9; AUPRC, 0.63). Patients carrying a putative pathogenic copy number variant were also accurately identified by the model. Compared with current approaches for genetic test determination, our model could identify more patients for testing while also increasing the proportion of those tested who have a genetic disease. We demonstrate that phenotypic patterns representative of a wide range of genetic diseases can be captured from EHRs to systematize decision-making for genetic testing, with the potential to speed up diagnosis, improve care and reduce costs.

Automated 3D mapping of baseline and 12-month associations between three verbal memory measures and hippocampal atrophy in 490 ADNI subjects.

We used a previously validated automated machine learning algorithm based on adaptive boosting to segment the hippocampi in baseline and 12-month follow-up 3D T1-weighted brain MRIs of 150 cognitively normal elderly (NC), 245 mild cognitive impairment (MCI) and 97 Dementia of the Alzheimer's type (DAT) ADNI subjects. Using the radial distance mapping technique, we examined the hippocampal correlates of delayed recall performance on three well-established verbal memory tests--ADAScog delayed recall (ADAScog-DR), the Rey Auditory Verbal Learning Test -DR (AVLT-DR) and Wechsler Logical Memory II-DR (LM II-DR). We observed no significant correlations between delayed recall performance and hippocampal radial distance on any of the three verbal memory measures in NC. All three measures were associated with hippocampal volumes and radial distance in the full sample and in the MCI group at baseline and at follow-up. In DAT we observed stronger left-sided associations between hippocampal radial distance, LM II-DR and ADAScog-DR both at baseline and at follow-up. The strongest linkage between memory performance and hippocampal atrophy in the MCI sample was observed with the most challenging verbal memory test-the AVLT-DR, as opposed to the DAT sample where the least challenging test the ADAScog-DR showed strongest associations with the hippocampal structure. After controlling for baseline hippocampal atrophy, memory performance showed regionally specific associations with hippocampal radial distance in predominantly CA1 but also in subicular distribution.

Genome-wide analysis reveals novel genes influencing temporal lobe structure with relevance to neurodegeneration in Alzheimer's disease.

In a genome-wide association study of structural brain degeneration, we mapped the 3D profile of temporal lobe volume differences in 742 brain MRI scans of Alzheimer's disease patients, mildly impaired, and healthy elderly subjects. After searching 546,314 genomic markers, 2 single nucleotide polymorphisms (SNPs) were associated with bilateral temporal lobe volume (P<5 x 10(-7)). One SNP, rs10845840, is located in the GRIN2B gene which encodes the N-methyl-d-aspartate (NMDA) glutamate receptor NR2B subunit. This protein - involved in learning and memory, and excitotoxic cell death - has age-dependent prevalence in the synapse and is already a therapeutic target in Alzheimer's disease. Risk alleles for lower temporal lobe volume at this SNP were significantly over-represented in AD and MCI subjects vs. controls (odds ratio=1.273; P=0.039) and were associated with mini-mental state exam scores (MMSE; t=-2.114; P=0.035) demonstrating a negative effect on global cognitive function. Voxelwise maps of genetic association of this SNP with regional brain volumes, revealed intense temporal lobe effects (FDR correction at q=0.05; critical P=0.0257). This study uses large-scale brain mapping for gene discovery with implications for Alzheimer's disease.

Hippocampal, caudate, and ventricular changes in Parkinson's disease with and without dementia.

Parkinson's disease (PD) has been associated with mild cognitive impairment (PDMCI) and with dementia (PDD). Using radial distance mapping, we studied the 3D structural and volumetric differences between the hippocampi, caudates, and lateral ventricles in 20 cognitively normal elderly (NC), 12 cognitively normal PD (PDND), 8 PDMCI, and 15 PDD subjects and examined the associations between these structures and Unified Parkinson's Disease Rating Scale (UPDRS) Part III:motor subscale and Mini-Mental State Examination (MMSE) performance. There were no hippocampal differences between the groups. 3D caudate statistical maps demonstrated significant left medial and lateral and right medial atrophy in the PDD vs. NC, and right medial and lateral caudate atrophy in PDD vs. PDND. PDMCI showed trend-level significant left lateral caudate atrophy vs. NC. Both left and right ventricles were significantly larger in PDD relative to the NC and PDND with posterior (body/occipital horn) predominance. The magnitude of regionally significant between-group differences in radial distance ranged between 20-30% for caudate and 5-20% for ventricles. UPDRS Part III:motor subscale score correlated with ventricular enlargement. MMSE showed significant correlation with expansion of the posterior lateral ventricles and trend-level significant correlation with caudate head atrophy. Cognitive decline in PD is associated with anterior caudate atrophy and ventricular enlargement.

Automated mapping of hippocampal atrophy in 1-year repeat MRI data from 490 subjects with Alzheimer's disease, mild cognitive impairment, and elderly controls.

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.

Disease classification with hippocampal shape invariants.

We present an Alzheimer's detection study based on a global shape description of hippocampal surface models. With global descriptors forming our bag of features, Support Vector Machine classification of 49 Alzheimer (AD) and 63 elderly control subjects yielded 75.5% sensitivity and 87.3% specificity with 82.1% correct overall in a leave-one-out test. We show that our description contributes new information to simpler shape measures. Armed with a rigid shape registration tool, we also present a way to visualize variation in global shape description as a local displacement map, thus clarifying the descriptors' anatomical meaning.

Automated 3D mapping of hippocampal atrophy and its clinical correlates in 400 subjects with Alzheimer's disease, mild cognitive impairment, and elderly controls.

We used a new method we developed for automated hippocampal segmentation, called the auto context model, to analyze brain MRI scans of 400 subjects from the Alzheimer's disease neuroimaging initiative. 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. Forty 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.

Validation of a fully automated 3D hippocampal segmentation method using subjects with Alzheimer's disease mild cognitive impairment, and elderly controls.

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 approximately 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 1x1x1 to 7x7x7). 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.

Effects of ApoE4 and maternal history of dementia on hippocampal atrophy.

We applied an automated hippocampal segmentation technique based on adaptive boosting (AdaBoost) to the 1.5 T magnetic resonance imaging (MRI) baseline and 1-year follow-up data of 243 subjects with mild cognitive impairment (MCI), 96 with Alzheimer's disease (AD), and 145 normal controls (NC) scanned as part of the Alzheimer's Disease Neuroimaging Initiative (ADNI). MCI subjects with positive maternal history of dementia had smaller hippocampal volumes at baseline and at follow-up, and greater 12-month atrophy rates than subjects with negative maternal history. Three-dimensional maps and volumetric multiple regression analyses demonstrated a significant effect of positive maternal history of dementia on hippocampal atrophy in MCI and AD after controlling for age, ApoE4 genotype, and paternal history of dementia, respectively. ApoE4 showed an independent effect on hippocampal atrophy in MCI and AD and in the pooled sample.

Robust surface reconstruction via Laplace-Beltrami eigen-projection and boundary deformation.

In medical shape analysis, a critical problem is reconstructing a smooth surface of correct topology from a binary mask that typically has spurious features due to segmentation artifacts. The challenge is the robust removal of these outliers without affecting the accuracy of other parts of the boundary. In this paper, we propose a novel approach for this problem based on the Laplace-Beltrami (LB) eigen-projection and properly designed boundary deformations. Using the metric distortion during the LB eigen-projection, our method automatically detects the location of outliers and feeds this information to a well-composed and topology-preserving deformation. By iterating between these two steps of outlier detection and boundary deformation, we can robustly filter out the outliers without moving the smooth part of the boundary. The final surface is the eigen-projection of the filtered mask boundary that has the correct topology, desired accuracy and smoothness. In our experiments, we illustrate the robustness of our method on different input masks of the same structure, and compare with the popular SPHARM tool and the topology preserving level set method to show that our method can reconstruct accurate surface representations without introducing artificial oscillations. We also successfully validate our method on a large data set of more than 900 hippocampal masks and demonstrate that the reconstructed surfaces retain volume information accurately.

Comparison of AdaBoost and support vector machines for detecting Alzheimer's disease through automated hippocampal segmentation.

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 MRIs 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 3-D 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.

3D PIB and CSF biomarker associations with hippocampal atrophy in ADNI subjects.

Cerebrospinal fluid (CSF) measures of Ab and tau, Pittsburgh Compound B (PIB) imaging and hippocampal atrophy are promising Alzheimer's disease biomarkers yet the associations between them are not known. We applied a validated, automated hippocampal labeling method and 3D radial distance mapping to the 1.5T structural magnetic resonance imaging (MRI) data of 388 ADNI subjects with baseline CSF Ab(42), total tau (t-tau) and phosphorylated tau (p-tau(181)) and 98 subjects with positron emission tomography (PET) imaging using PIB. We used linear regression to investigate associations between hippocampal atrophy and average cortical, parietal and precuneal PIB standardized uptake value ratio (SUVR) and CSF Ab(42), t-tau, p-tau(181), t-tau/Ab(42) and p-tau(181)/Ab(42). All CSF measures showed significant associations with hippocampal volume and radial distance in the pooled sample. Strongest correlations were seen for p-tau(181), followed by p-tau(181)/Ab(42) ratio, t-tau/Ab(42) ratio, t-tau and Ab(42). p-tau(181) showed stronger correlation in ApoE4 carriers, while t-tau showed stronger correlation in ApoE4 noncarriers. Of the 3 PIB measures the precuneal SUVR showed strongest associations with hippocampal atrophy.

Inverse-consistent surface mapping with Laplace-Beltrami eigen-features.

We propose in this work a novel variational method for computing maps between surfaces by combining informative geometric features and regularizing forces including inverse consistency and harmonic energy. To tackle the ambiguity in defining homologous points on smooth surfaces, we design feature functions in the data term based on the Reeb graph of the Laplace-Beltrami eigenfunctions to quantitatively describe the global geometry of elongated anatomical structures. For inverse consistency and robustness, our method computes simultaneously the forward and backward map by iteratively solving partial differential equations (PDEs) on the surfaces. In our experiments, we successfully mapped 890 hippocampal surfaces and report statistically significant maps of atrophy rates between normal controls and patients with mild cognitive impairment (MCI) and Alzheimer's disease (AD).

Lossless online ensemble learning (LOEL) and its application to subcortical segmentation.

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.

Automatic subcortical segmentation using a contextual model.

Automatically segmenting subcortical structures in brain im ages has the potential to greatly accelerate drug trials and population studies of disease. Here we propose an automatic subcortical segmentation algorithm using the auto context model. Unlike many segmentation algorithms that separately compute a shape prior and an image appearance model, we develop a framework based on machine learning to learn a unified appearance and context model. We trained our algorithm to segment the hippocampus and tested it on 83 brain MRIs (of 35 Alzheimer's disease patients, 22 with mild cognitive impairment, and 26 normal healthy controls). Using standard distance and overlap metrics, the auto context model method significantly outperformed simpler learning-based algorithms (using AdaBoost alone) and the FreeSurfer system. In tests on a public domain dataset designed to validate segmentation [1], our new algorithm also greatly improved upon a recently-proposed hybrid discriminative/generative approach [2], which was among the top three that performed comparably in a recent head-to-head competition.