PosturePose: Optimized Posture Analysis for Semi-Supervised Monocular 3D Human Pose Estimation.

One motivation for studying semi-supervised techniques for human pose estimation is to compensate for the lack of variety in curated 3D human pose datasets by combining labeled 3D pose data with readily available unlabeled video data-effectively, leveraging the annotations of the former and the rich variety of the latter to train more robust pose estimators. In this paper, we propose a novel, fully differentiable posture consistency loss that is unaffected by camera orientation and improves monocular human pose estimators trained with limited labeled 3D pose data. Our semi-supervised monocular 3D pose framework combines biomechanical pose regularization with a multi-view posture (and pose) consistency objective function. We show that posture optimization was effective at decreasing pose estimation errors when applied to a 2D-3D lifting network (VPose3D) and two well-studied datasets (H36M and 3DHP). Specifically, the proposed semi-supervised framework with multi-view posture and pose loss lowered the mean per-joint position error (MPJPE) of leading semi-supervised methods by up to 15% (-7.6 mm) when camera parameters of unlabeled poses were provided. Without camera parameters, our semi-supervised framework with posture loss improved semi-supervised state-of-the-art methods by 17% (-15.6 mm decrease in MPJPE). Overall, our pose models compete favorably with other high-performing pose models trained under similar conditions with limited labeled data.

Neuropathologic correlates of cerebral microbleeds in community-based older adults.

Cerebral microbleeds (CMBs) appearing as hypointense foci on T2*-weighted magnetic resonance images are small hemorrhages that have been linked to cognitive decline and increased mortality. However, the neuropathologic correlates of CMBs in community-based older adults are poorly understood. The present study investigated the association of age-related neuropathologies with CMBs in community-based older adults. Cerebral hemispheres from 289 participants of the Rush Memory and Aging Project, Religious Orders Study, Minority Aging Research Study, and Rush Alzheimer's Disease Clinical Core underwent ex vivo MRI and detailed neuropathologic examination. Following Bonferroni correction, CMBs in the cerebrum overall and in the frontal lobe were associated with cerebral amyloid angiopathy, CMBs in the frontal lobe were also associated with arteriolosclerosis, and CMBs in the basal ganglia showed a borderline significant association with microinfarcts. These findings suggest that CMBs can aid in the prediction of small vessel disease in community-based older adults. Finally, CMBs were not associated with dementia, suggesting that CMBs in community-based older adults may not be linked to substantial cognitive impairment.

Weakly Supervised 2D Pose Adaptation and Body Part Segmentation for Concealed Object Detection.

Weakly supervised pose estimation can be used to assist unsupervised body part segmentation and concealed item detection. The accuracy of pose estimation is essential for precise body part segmentation and accurate concealed item detection. In this paper, we show how poses obtained from an RGB pretrained 2D pose detector can be modified for the backscatter image domain. The 2D poses are refined using RANSAC bundle adjustment to minimize the projection loss in 3D. Furthermore, we show how 2D poses can be optimized using a newly proposed 3D-to-2D pose correction network weakly supervised with pose prior regularizers and multi-view pose and posture consistency losses. The optimized 2D poses are used to segment human body parts. We then train a body-part-aware anomaly detection network to detect foreign (concealed threat) objects on segmented body parts. Our work is applied to the TSA passenger screening dataset containing millimeter wave scan images of airport travelers annotated with only binary labels that indicate whether a foreign object is concealed on a body part. Our proposed approach significantly improves the detection accuracy of TSA 2D backscatter images in existing works with a state-of-the-art performance of 97% F1-score, 0.0559 log-loss on the TSA-PSD test-set, and a 74% reduction in 2D pose error.

Exploring the functional impact of alternative splicing on human protein isoforms using available annotation sources.

In recent years, the emphasis of scientific inquiry has shifted from whole-genome analyses to an understanding of cellular responses specific to tissue, developmental stage or environmental conditions. One of the central mechanisms underlying the diversity and adaptability of the contextual responses is alternative splicing (AS). It enables a single gene to encode multiple isoforms with distinct biological functions. However, to date, the functions of the vast majority of differentially spliced protein isoforms are not known. Integration of genomic, proteomic, functional, phenotypic and contextual information is essential for supporting isoform-based modeling and analysis. Such integrative proteogenomics approaches promise to provide insights into the functions of the alternatively spliced protein isoforms and provide high-confidence hypotheses to be validated experimentally. This manuscript provides a survey of the public databases supporting isoform-based biology. It also presents an overview of the potential global impact of AS on the human canonical gene functions, molecular interactions and cellular pathways.

Lynx: a knowledge base and an analytical workbench for integrative medicine.

Lynx (http://lynx.ci.uchicago.edu) is a web-based database and a knowledge extraction engine. It supports annotation and analysis of high-throughput experimental data and generation of weighted hypotheses regarding genes and molecular mechanisms contributing to human phenotypes or conditions of interest. Since the last release, the Lynx knowledge base (LynxKB) has been periodically updated with the latest versions of the existing databases and supplemented with additional information from public databases. These additions have enriched the data annotations provided by Lynx and improved the performance of Lynx analytical tools. Moreover, the Lynx analytical workbench has been supplemented with new tools for reconstruction of co-expression networks and feature-and-network-based prioritization of genetic factors and molecular mechanisms. These developments facilitate the extraction of meaningful knowledge from experimental data and LynxKB. The Service Oriented Architecture provides public access to LynxKB and its analytical tools via user-friendly web services and interfaces.

Disease gene prioritization using network and feature.

Identifying high-confidence candidate genes that are causative for disease phenotypes, from the large lists of variations produced by high-throughput genomics, can be both time-consuming and costly. The development of novel computational approaches, utilizing existing biological knowledge for the prioritization of such candidate genes, can improve the efficiency and accuracy of the biomedical data analysis. It can also reduce the cost of such studies by avoiding experimental validations of irrelevant candidates. In this study, we address this challenge by proposing a novel gene prioritization approach that ranks promising candidate genes that are likely to be involved in a disease or phenotype under study. This algorithm is based on the modified conditional random field (CRF) model that simultaneously makes use of both gene annotations and gene interactions, while preserving their original representation. We validated our approach on two independent disease benchmark studies by ranking candidate genes using network and feature information. Our results showed both high area under the curve (AUC) value (0.86), and more importantly high partial AUC (pAUC) value (0.1296), and revealed higher accuracy and precision at the top predictions as compared with other well-performed gene prioritization tools, such as Endeavour (AUC-0.82, pAUC-0.083) and PINTA (AUC-0.76, pAUC-0.066). We were able to detect more target genes (9/18/19/27) on top positions (1/5/10/20) compared to Endeavour (3/11/14/23) and PINTA (6/10/13/18). To demonstrate its usability, we applied our method to a case study for the prediction of molecular mechanisms contributing to intellectual disability and autism. Our approach was able to correctly recover genes related to both disorders and provide suggestions for possible additional candidates based on their rankings and functional annotations.

An integrative computational approach for prioritization of genomic variants.

An essential step in the discovery of molecular mechanisms contributing to disease phenotypes and efficient experimental planning is the development of weighted hypotheses that estimate the functional effects of sequence variants discovered by high-throughput genomics. With the increasing specialization of the bioinformatics resources, creating analytical workflows that seamlessly integrate data and bioinformatics tools developed by multiple groups becomes inevitable. Here we present a case study of a use of the distributed analytical environment integrating four complementary specialized resources, namely the Lynx platform, VISTA RViewer, the Developmental Brain Disorders Database (DBDB), and the RaptorX server, for the identification of high-confidence candidate genes contributing to pathogenesis of spina bifida. The analysis resulted in prediction and validation of deleterious mutations in the SLC19A placental transporter in mothers of the affected children that causes narrowing of the outlet channel and therefore leads to the reduced folate permeation rate. The described approach also enabled correct identification of several genes, previously shown to contribute to pathogenesis of spina bifida, and suggestion of additional genes for experimental validations. The study demonstrates that the seamless integration of bioinformatics resources enables fast and efficient prioritization and characterization of genomic factors and molecular networks contributing to the phenotypes of interest.

High-throughput translational medicine: challenges and solutions.

Recent technological advances in genomics now allow producing biological data at unprecedented tera- and petabyte scales. Yet, the extraction of useful knowledge from this voluminous data presents a significant challenge to a scientific community. Efficient mining of vast and complex data sets for the needs of biomedical research critically depends on seamless integration of clinical, genomic, and experimental information with prior knowledge about genotype-phenotype relationships accumulated in a plethora of publicly available databases. Furthermore, such experimental data should be accessible to a variety of algorithms and analytical pipelines that drive computational analysis and data mining. Translational projects require sophisticated approaches that coordinate and perform various analytical steps involved in the extraction of useful knowledge from accumulated clinical and experimental data in an orderly semiautomated manner. It presents a number of challenges such as (1) high-throughput data management involving data transfer, data storage, and access control; (2) scalable computational infrastructure; and (3) analysis of large-scale multidimensional data for the extraction of actionable knowledge.We present a scalable computational platform based on crosscutting requirements from multiple scientific groups for data integration, management, and analysis. The goal of this integrated platform is to address the challenges and to support the end-to-end analytical needs of various translational projects.

Development of a human brain diffusion tensor template.

The development of a brain template for diffusion tensor imaging (DTI) is crucial for comparisons of neuronal structural integrity and brain connectivity across populations, as well as for the development of a white matter atlas. Previous efforts to produce a DTI brain template have been compromised by factors related to image quality, the effectiveness of the image registration approach, the appropriateness of subject inclusion criteria, and the completeness and accuracy of the information summarized in the final template. The purpose of this work was to develop a DTI human brain template using techniques that address the shortcomings of previous efforts. Therefore, data containing minimal artifacts were first obtained on 67 healthy human subjects selected from an age-group with relatively similar diffusion characteristics (20-40 years of age), using an appropriate DTI acquisition protocol. Non-linear image registration based on mean diffusion-weighted and fractional anisotropy images was employed. DTI brain templates containing median and mean tensors were produced in ICBM-152 space and made publicly available. The resulting set of DTI templates is characterized by higher image sharpness, provides the ability to distinguish smaller white matter fiber structures, contains fewer image artifacts, than previously developed templates, and to our knowledge, is one of only two templates produced based on a relatively large number of subjects. Furthermore, median tensors were shown to better preserve the diffusion characteristics at the group level than mean tensors. Finally, white matter fiber tractography was applied on the template and several fiber-bundles were traced.

Sampling framework for accurate curvature estimation in discrete surfaces.

Accurate curvature estimation in discrete surfaces is an important problem with numerous applications. Curvature is an indicator of ridges and can be used in applications such as shape analysis and recognition, object segmentation, adaptive smoothing, anisotropic fairing of irregular meshes, and anisotropic texture mapping. In this paper, a new framework is proposed for accurate curvature estimation in discrete surfaces. The proposed framework is based on a local directional curve sampling of the surface where the sampling frequency can be controlled. This local model has a large number of degrees of freedoms compared with known techniques and, so, can better represent the local geometry. The proposed framework is quantitatively evaluated and compared with common techniques for surface curvature estimation. In order to perform an unbiased evaluation in which smoothing effects are factored out, we use a set of randomly generated Bezier surface patches for which the curvature values can be analytically computed. It is demonstrated that, through the establishment of sampling conditions, the error in estimations obtained by the proposed framework is smaller and that the proposed framework is less sensitive to low sampling density, sampling irregularities, and sampling noise.

Vessel tree reconstruction in thoracic CT scans with application to nodule detection.

Vessel tree reconstruction in volumetric data is a necessary prerequisite in various medical imaging applications. Specifically, when considering the application of automated lung nodule detection in thoracic computed tomography (CT) scans, vessel trees can be used to resolve local ambiguities based on global considerations and so improve the performance of nodule detection algorithms. In this study, a novel approach to vessel tree reconstruction and its application to nodule detection in thoracic CT scans was developed by using correlation-based enhancement filters and a fuzzy shape representation of the data. The proposed correlation-based enhancement filters depend on first-order partial derivatives and so are less sensitive to noise compared with Hessian-based filters. Additionally, multiple sets of eigenvalues are used so that a distinction between nodules and vessel junctions becomes possible. The proposed fuzzy shape representation is based on regulated morphological operations that are less sensitive to noise. Consequently, the vessel tree reconstruction algorithm can accommodate vessel bifurcation and discontinuities. A quantitative performance evaluation of the enhancement filters and of the vessel tree reconstruction algorithm was performed. Moreover, the proposed vessel tree reconstruction algorithm reduced the number of false positives generated by an existing nodule detection algorithm by 38%.