Exploration of shape variation using localized components analysis

The hippocampi of children with chromosome 22q11.2 deletion syndrome have localized anterior alterations that predict severity of anxiety

BACKGROUND

Individuals with 22q11.2 deletion syndrome (22q11.2DS) have an elevated risk for schizophrenia, which increases with history of childhood anxiety. Altered hippocampal morphology is a common neuroanatomical feature of 22q11.2DS and idiopathic schizophrenia. Relating hippocampal structure in children with 22q11.2DS to anxiety and impaired cognitive ability could lead to hippocampus-based characterization of psychosis-proneness in this at-risk population.

METHODS

We measured hippocampal volume using a semiautomated approach on MRIs collected from typically developing children and children with 22q11.2DS. We then analyzed hippocampal morphology with Localized Components Analysis. We tested the modulating roles of diagnostic group, hippocampal volume, sex and age on local hippocampal shape components. Lastly, volume and shape components were tested as covariates of IQ and anxiety.

RESULTS

We included 48 typically developing children and 69 children with 22q11.2DS in our study. Hippocampal volume was reduced bilaterally in children with 22q11.2DS, and these children showed greater variation in the shape of the anterior hippocampus than typically developing children. Children with 22q11.2DS had greater inward deformation of the anterior hippocampus than typically developing children. Greater inward deformation of the anterior hippocampus was associated with greater severity of anxiety, specifically fear of physical injury, within the 22q11.2DS group.

LIMITATIONS

Shape alterations are not specific to hippocampal subfields.

CONCLUSION

Alterations in the structure of the anterior hippocampus likely affect function and may impact limbic circuitry. We suggest these alterations potentially contribute to anxiety symptoms in individuals with 22q11.2DS through modulatory pathways. Altered hippocampal morphology may be uniquely linked to anxiety risk factors for schizophrenia, which could be a powerful neuroanatomical marker of schizophrenia risk and hence protection.

Explicit shape descriptors: novel morphologic features for histopathology classification

Object morphology, defined as shape and size characteristics, observed on medical imagery is often an important marker for disease presence and/or aggressiveness. In the context of prostate cancer histopathology, gland morphology is an integral component of the Gleason grading system which enables discrimination between low and high grade disease. However, clinicians are often unable to distinguish between subtle differences in object morphology, as evidenced by high inter-observer variability in Gleason grading. Boundary-based morphologic descriptors, such as the variance in the distance from points on the boundary of an object to its center, may not have the requisite discriminability to separate objects with subtle shape differences. In this paper, we present a set of novel explicit shape descriptors (ESDs) which are capable of distinguishing subtle shape differences between prostate glands of intermediate Gleason grades (grades 3 and 4) on prostate cancer histopathology. Calculation of ESDs involves: (1) representing object morphology using an explicit shape model (e.g. medial axis); (2) aligning the shape models via a non-rigid registration scheme with a diffeomorphic constraint and quantifying shape model dissimilarity; and (3) applying a non-linear dimensionality reduction scheme (e.g. Graph Embedding) to learn a low dimensional projection encoding the shape differences between objects. ESDs are hence the principal eigenvectors in the reduced embedding space. In this work we demonstrate that ESDs in conjunction with a Support Vector Machine classifier are able to correctly distinguish between 888 prostate glands corresponding to different Gleason grades (benign, grade 3, or grade 4) of prostate cancer from 58 needle biopsy specimens with a maximum accuracy of 0.89 and corresponding area under the receiver operating characteristic curve of 0.78.

Maximizing power to track Alzheimer's disease and MCI progression by LDA-based weighting of longitudinal ventricular surface features

We propose a new method to maximize biomarker efficiency for detecting anatomical change over time in serial MRI. Drug trials using neuroimaging become prohibitively costly if vast numbers of subjects must be assessed, so it is vital to develop efficient measures of brain change. A popular measure of efficiency is the minimal sample size (n80) needed to detect 25% change in a biomarker, with 95% confidence and 80% power. For multivariate measures of brain change, we can directly optimize n80 based on a Linear Discriminant Analysis (LDA). Here we use a supervised learning framework to optimize n80, offering two alternative solutions. With a new medial surface modeling method, we track 3D dynamic changes in the lateral ventricles in 2065 ADNI scans. We apply our LDA-based weighting to the results. Our best average n80-in two-fold nested cross-validation-is 104 MCI subjects (95% CI: [94,139]) for a 1-year drug trial, and 75AD subjects [64,102]. This compares favorably with other MRI analysis methods. The standard "statistical ROI" approach applied to the same ventricular surfaces requires 165 MCI or 94AD subjects. At 2 years, the best LDA measure needs only 67 MCI and 52AD subjects, versus 119 MCI and 80AD subjects for the stat-ROI method. Our surface-based measures are unbiased: they give no artifactual additive atrophy over three time points. Our results suggest that statistical weighting may boost efficiency of drug trials that use brain maps.

Localized hippocampus measures are associated with Alzheimer pathology and cognition independent of total hippocampal volume

Hippocampal injury in the Alzheimer's disease (AD) pathological process is region-specific and magnetic resonance imaging (MRI)-based measures of localized hippocampus (HP) atrophy are known to detect region-specific changes associated with clinical AD, but it is unclear whether these measures provide information that is independent of that already provided by measures of total HP volume. Therefore, this study assessed the strength of association between localized HP atrophy measures and AD-related measures including cerebrospinal fluid (CSF) amyloid beta and tau concentrations, and cognitive performance, in statistical models that also included total HP volume as a covariate. A computational technique termed localized components analysis (LoCA) was used to identify 7 independent patterns of HP atrophy among 390 semiautomatically delineated HP from baseline magnetic resonance imaging of participants in the Alzheimer's Disease Neuroimaging Initiative (ADNI). Among cognitively normal participants, multiple measures of localized HP atrophy were significantly associated with CSF amyloid concentration, while total HP volume was not. In addition, among all participants, localized HP atrophy measures and total HP volume were both independently and additively associated with CSF tau concentration, performance on numerous neuropsychological tests, and discrimination between normal, mild cognitive impairment (MCI), and AD clinical diagnostic groups. Together, these results suggest that regional measures of hippocampal atrophy provided by localized components analysis may be more sensitive than total HP volume to the effects of AD pathology burden among cognitively normal individuals and may provide information about HP regions whose deficits may have especially profound cognitive consequences throughout the AD clinical course.

Localized component analysis for arthritis detection in the trapeziometacarpal joint

The trapeziometacarpal joint enables the prehensile function of the thumb. Unfortunately, this joint is vulnerable to osteoarthritis (OA) that typically affects the local shape of the trapezium. A novel, local statistical shape model is defined that employs a differentiable locality measure based on the weighted variance of point coordinates per mode. The simplicity of the function and the smooth derivative enable to quickly determine localized components for densely sampled surfaces. The method is employed to assess a set of 60 trapezia (38 healthy, 22 with OA). The localized components predominantly model regions affected by OA, contrary to shape variations found with PCA. Furthermore, identification of pathological trapezia based on the localized modes of variation is improved compared to PCA.