Matching Items (34)

127874-Thumbnail Image.png

Metabolic Remodeling of Membrane Glycerolipids in the Microalga Nannochloropsis oceanica under Nitrogen Deprivation

Description

The lack of lipidome analytical tools has limited our ability to gain new knowledge about lipid metabolism in microalgae, especially for membrane glycerolipids. An electrospray ionization mass spectrometry-based lipidomics method

The lack of lipidome analytical tools has limited our ability to gain new knowledge about lipid metabolism in microalgae, especially for membrane glycerolipids. An electrospray ionization mass spectrometry-based lipidomics method was developed for Nannochloropsis oceanica IMET1, which resolved 41 membrane glycerolipids molecular species belonging to eight classes. Changes in membrane glycerolipids under nitrogen deprivation and high-light (HL) conditions were uncovered. The results showed that the amount of plastidial membrane lipids including monogalactosyldiacylglycerol, phosphatidylglycerol, and the extraplastidic lipids diacylglyceryl-O-4′-(N, N, N,-trimethyl) homoserine and phosphatidylcholine decreased drastically under HL and nitrogen deprivation stresses. Algal cells accumulated considerably more digalactosyldiacylglycerol and sulfoquinovosyldiacylglycerols under stresses. The genes encoding enzymes responsible for biosynthesis, modification and degradation of glycerolipids were identified by mining a time-course global RNA-seq data set. It suggested that reduction in lipid contents under nitrogen deprivation is not attributable to the retarded biosynthesis processes, at least at the gene expression level, as most genes involved in their biosynthesis were unaffected by nitrogen supply, yet several genes were significantly up-regulated. Additionally, a conceptual eicosapentaenoic acid (EPA) biosynthesis network is proposed based on the lipidomic and transcriptomic data, which underlined import of EPA from cytosolic glycerolipids to the plastid for synthesizing EPA-containing chloroplast membrane lipids.

Contributors

Agent

Created

Date Created
  • 2017-08-04

128818-Thumbnail Image.png

Multi-Parametric MRI and Texture Analysis to Visualize Spatial Histologic Heterogeneity and Tumor Extent in Glioblastoma

Description

Background
Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor

Background
Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ~60% of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM.
Methods
We recruited primary GBM patients undergoing image-guided biopsies and acquired pre-operative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs <80% tumor nuclei) for corresponding samples. In a training set, we used three texture analysis algorithms and three ML methods to identify MRI-texture features that optimized model accuracy to distinguish tumor content. We confirmed model accuracy in a separate validation set.
Results
We collected 82 biopsies from 18 GBMs throughout ENH and BAT. The MRI-based model achieved 85% cross-validated accuracy to diagnose high- vs low-tumor in the training set (60 biopsies, 11 patients). The model achieved 81.8% accuracy in the validation set (22 biopsies, 7 patients).
Conclusion
Multi-parametric MRI and texture analysis can help characterize and visualize GBM’s spatial histologic heterogeneity to identify regional tumor-rich biopsy targets.

Contributors

Agent

Created

Date Created
  • 2015-11-24

MRI-Based Texture Analysis to Differentiate Sinonasal Squamous Cell Carcinoma from Inverted Papilloma

Description

ABSTRACT BACKGROUND AND PURPOSE: Sinonasal inverted papilloma (IP) can harbor squamous cell carcinoma (SCC). Consequently, differentiating these tumors is important. The objective of this study was to determine if MRI-based

ABSTRACT BACKGROUND AND PURPOSE: Sinonasal inverted papilloma (IP) can harbor squamous cell carcinoma (SCC). Consequently, differentiating these tumors is important. The objective of this study was to determine if MRI-based texture analysis can differentiate SCC from IP and provide supplementary information to the radiologist. MATERIALS AND METHODS: Adult patients who had IP or SCC resected were eligible (coexistent IP and SCC were excluded). Inclusion required tumor size greater than 1.5 cm and a pre-operative MRI with axial T1, axial T2, and axial T1 post-contrast sequences. Five well- established texture analysis algorithms were applied to an ROI from the largest tumor cross- section. For a training dataset, machine-learning algorithms were used to identify the most accurate model, and performance was also evaluated in a validation dataset. Based on three separate blinded reviews of the ROI, isolated tumor, and entire images, two neuroradiologists predicted tumor type in consensus. RESULTS: The IP and SCC cohorts were matched for age and gender, while SCC tumor volume was larger (p=0.001). The best classification model achieved similar accuracies for training (17 SCC, 16 IP) and validation (7 SCC, 6 IP) datasets of 90.9% and 84.6% respectively (p=0.537). The machine-learning accuracy for the entire cohort (89.1%) was better than that of the neuroradiologist ROI review (56.5%, p=0.0004) but not significantly different from the neuroradiologist review of the tumors (73.9%, p=0.060) or entire images (87.0%, p=0.748). CONCLUSION: MRI-based texture analysis has potential to differentiate SCC from IP and may provide incremental information to the neuroradiologist, particularly for small or heterogeneous tumors.

Contributors

Agent

Created

Date Created
  • 2016-12

135788-Thumbnail Image.png

Cost Driven Agent Based Simulation of the Department of Defense Acquisition System

Description

The Department of Defense (DoD) acquisition system is a complex system riddled with cost and schedule overruns. These cost and schedule overruns are very serious issues as the acquisition system

The Department of Defense (DoD) acquisition system is a complex system riddled with cost and schedule overruns. These cost and schedule overruns are very serious issues as the acquisition system is responsible for aiding U.S. warfighters. Hence, if the acquisition process is failing that could be a potential threat to our nation's security. Furthermore, the DoD acquisition system is responsible for proper allocation of billions of taxpayer's dollars and employs many civilians and military personnel. Much research has been done in the past on the acquisition system with little impact or success. One reason for this lack of success in improving the system is the lack of accurate models to test theories. This research is a continuation of the effort on the Enterprise Requirements and Acquisition Model (ERAM), a discrete event simulation modeling research on DoD acquisition system. We propose to extend ERAM using agent-based simulation principles due to the many interactions among the subsystems of the acquisition system. We initially identify ten sub models needed to simulate the acquisition system. This research focuses on three sub models related to the budget of acquisition programs. In this thesis, we present the data collection, data analysis, initial implementation, and initial validation needed to facilitate these sub models and lay the groundwork for a full agent-based simulation of the DoD acquisition system.

Contributors

Agent

Created

Date Created
  • 2016-05

131810-Thumbnail Image.png

mHealth Patient Care Improvement Study Through Statistical Analysis

Description

Technological applications are continually being developed in the healthcare industry as technology becomes increasingly more available. In recent years, companies have started creating mobile applications to address various conditions and

Technological applications are continually being developed in the healthcare industry as technology becomes increasingly more available. In recent years, companies have started creating mobile applications to address various conditions and diseases. This falls under mHealth or the “use of mobile phones and other wireless technology in medical care” (Rouse, 2018). The goal of this study was to identify if data gathered through the use of mHealth methods can be used to build predictive models. The first part of this thesis contains a literature review presenting relevant definitions and several potential studies that involved the use of technology in healthcare applications. The second part of this thesis focuses on data from one study, where regression analysis is used to develop predictive models.

Rouse, M. (2018). mHealth (mobile health). Retrieved from https://searchhealthit.techtarget.com/definition/mHealth

Contributors

Agent

Created

Date Created
  • 2020-05

158093-Thumbnail Image.png

Embedded Feature Selection for Model-based Clustering

Description

Model-based clustering is a sub-field of statistical modeling and machine learning. The mixture models use the probability to describe the degree of the data point belonging to the cluster, and

Model-based clustering is a sub-field of statistical modeling and machine learning. The mixture models use the probability to describe the degree of the data point belonging to the cluster, and the probability is updated iteratively during the clustering. While mixture models have demonstrated the superior performance in handling noisy data in many fields, there exist some challenges for high dimensional dataset. It is noted that among a large number of features, some may not indeed contribute to delineate the cluster profiles. The inclusion of these “noisy” features will confuse the model to identify the real structure of the clusters and cost more computational time. Recognizing the issue, in this dissertation, I propose a new feature selection algorithm for continuous dataset first and then extend to mixed datatype. Finally, I conduct uncertainty quantification for the feature selection results as the third topic.

The first topic is an embedded feature selection algorithm termed Expectation-Selection-Maximization (ESM) model that can automatically select features while optimizing the parameters for Gaussian Mixture Model. I introduce a relevancy index (RI) revealing the contribution of the feature in the clustering process to assist feature selection. I demonstrate the efficacy of the ESM by studying two synthetic datasets, four benchmark datasets, and an Alzheimer’s Disease dataset.

The second topic focuses on extending the application of ESM algorithm to handle mixed datatypes. The Gaussian mixture model is generalized to Generalized Model of Mixture (GMoM), which can not only handle continuous features, but also binary and nominal features.

The last topic is about Uncertainty Quantification (UQ) of the feature selection. A new algorithm termed ESOM is proposed, which takes the variance information into consideration while conducting feature selection. Also, a set of outliers are generated in the feature selection process to infer the uncertainty in the input data. Finally, the selected features and detected outlier instances are evaluated by visualization comparison.

Contributors

Agent

Created

Date Created
  • 2020

152893-Thumbnail Image.png

A computational framework for quality of service measurement, visualization and prediction in mission critical communication networks

Description

Network traffic analysis by means of Quality of Service (QoS) is a popular research and development area among researchers for a long time. It is becoming even more relevant recently

Network traffic analysis by means of Quality of Service (QoS) is a popular research and development area among researchers for a long time. It is becoming even more relevant recently due to ever increasing use of the Internet and other public and private communication networks. Fast and precise QoS analysis is a vital task in mission-critical communication networks (MCCNs), where providing a certain level of QoS is essential for national security, safety or economic vitality. In this thesis, the details of all aspects of a comprehensive computational framework for QoS analysis in MCCNs are provided. There are three main QoS analysis tasks in MCCNs; QoS measurement, QoS visualization and QoS prediction. Definitions of these tasks are provided and for each of those, complete solutions are suggested either by referring to an existing work or providing novel methods.

A scalable and accurate passive one-way QoS measurement algorithm is proposed. It is shown that accurate QoS measurements are possible using network flow data.

Requirements of a good QoS visualization platform are listed. Implementations of the capabilities of a complete visualization platform are presented.

Steps of QoS prediction task in MCCNs are defined. The details of feature selection, class balancing through sampling and assessing classification algorithms for this task are outlined. Moreover, a novel tree based logistic regression method for knowledge discovery is introduced. Developed prediction framework is capable of making very accurate packet level QoS predictions and giving valuable insights to network administrators.

Contributors

Agent

Created

Date Created
  • 2014

155389-Thumbnail Image.png

Scaling Up Large-scale Sparse Learning and Its Application to Medical Imaging

Description

Large-scale $\ell_1$-regularized loss minimization problems arise in high-dimensional applications such as compressed sensing and high-dimensional supervised learning, including classification and regression problems. In many applications, it remains challenging to apply

Large-scale $\ell_1$-regularized loss minimization problems arise in high-dimensional applications such as compressed sensing and high-dimensional supervised learning, including classification and regression problems. In many applications, it remains challenging to apply the sparse learning model to large-scale problems that have massive data samples with high-dimensional features. One popular and promising strategy is to scaling up the optimization problem in parallel. Parallel solvers run multiple cores on a shared memory system or a distributed environment to speed up the computation, while the practical usage is limited by the huge dimension in the feature space and synchronization problems.

In this dissertation, I carry out the research along the direction with particular focuses on scaling up the optimization of sparse learning for supervised and unsupervised learning problems. For the supervised learning, I firstly propose an asynchronous parallel solver to optimize the large-scale sparse learning model in a multithreading environment. Moreover, I propose a distributed framework to conduct the learning process when the dataset is distributed stored among different machines. Then the proposed model is further extended to the studies of risk genetic factors for Alzheimer's Disease (AD) among different research institutions, integrating a group feature selection framework to rank the top risk SNPs for AD. For the unsupervised learning problem, I propose a highly efficient solver, termed Stochastic Coordinate Coding (SCC), scaling up the optimization of dictionary learning and sparse coding problems. The common issue for the medical imaging research is that the longitudinal features of patients among different time points are beneficial to study together. To further improve the dictionary learning model, I propose a multi-task dictionary learning method, learning the different task simultaneously and utilizing shared and individual dictionary to encode both consistent and changing imaging features.

Contributors

Agent

Created

Date Created
  • 2017

155228-Thumbnail Image.png

Structured sparse methods for imaging genetics

Description

Imaging genetics is an emerging and promising technique that investigates how genetic variations affect brain development, structure, and function. By exploiting disorder-related neuroimaging phenotypes, this class of studies provides a

Imaging genetics is an emerging and promising technique that investigates how genetic variations affect brain development, structure, and function. By exploiting disorder-related neuroimaging phenotypes, this class of studies provides a novel direction to reveal and understand the complex genetic mechanisms. Oftentimes, imaging genetics studies are challenging due to the relatively small number of subjects but extremely high-dimensionality of both imaging data and genomic data. In this dissertation, I carry on my research on imaging genetics with particular focuses on two tasks---building predictive models between neuroimaging data and genomic data, and identifying disorder-related genetic risk factors through image-based biomarkers. To this end, I consider a suite of structured sparse methods---that can produce interpretable models and are robust to overfitting---for imaging genetics. With carefully-designed sparse-inducing regularizers, different biological priors are incorporated into learning models. More specifically, in the Allen brain image--gene expression study, I adopt an advanced sparse coding approach for image feature extraction and employ a multi-task learning approach for multi-class annotation. Moreover, I propose a label structured-based two-stage learning framework, which utilizes the hierarchical structure among labels, for multi-label annotation. In the Alzheimer's disease neuroimaging initiative (ADNI) imaging genetics study, I employ Lasso together with EDPP (enhanced dual polytope projections) screening rules to fast identify Alzheimer's disease risk SNPs. I also adopt the tree-structured group Lasso with MLFre (multi-layer feature reduction) screening rules to incorporate linkage disequilibrium information into modeling. Moreover, I propose a novel absolute fused Lasso model for ADNI imaging genetics. This method utilizes SNP spatial structure and is robust to the choice of reference alleles of genotype coding. In addition, I propose a two-level structured sparse model that incorporates gene-level networks through a graph penalty into SNP-level model construction. Lastly, I explore a convolutional neural network approach for accurate predicting Alzheimer's disease related imaging phenotypes. Experimental results on real-world imaging genetics applications demonstrate the efficiency and effectiveness of the proposed structured sparse methods.

Contributors

Agent

Created

Date Created
  • 2017

154086-Thumbnail Image.png

Transfer Learning for BioImaging and Bilingual Applications

Description

Discriminative learning when training and test data belong to different distributions is a challenging and complex task. Often times we have very few or no labeled data from the test

Discriminative learning when training and test data belong to different distributions is a challenging and complex task. Often times we have very few or no labeled data from the test or target distribution, but we may have plenty of labeled data from one or multiple related sources with different distributions. Due to its capability of migrating knowledge from related domains, transfer learning has shown to be effective for cross-domain learning problems. In this dissertation, I carry out research along this direction with a particular focus on designing efficient and effective algorithms for BioImaging and Bilingual applications. Specifically, I propose deep transfer learning algorithms which combine transfer learning and deep learning to improve image annotation performance. Firstly, I propose to generate the deep features for the Drosophila embryo images via pretrained deep models and build linear classifiers on top of the deep features. Secondly, I propose to fine-tune the pretrained model with a small amount of labeled images. The time complexity and performance of deep transfer learning methodologies are investigated. Promising results have demonstrated the knowledge transfer ability of proposed deep transfer algorithms. Moreover, I propose a novel Robust Principal Component Analysis (RPCA) approach to process the noisy images in advance. In addition, I also present a two-stage re-weighting framework for general domain adaptation problems. The distribution of source domain is mapped towards the target domain in the first stage, and an adaptive learning model is proposed in the second stage to incorporate label information from the target domain if it is available. Then the proposed model is applied to tackle cross lingual spam detection problem at LinkedIn’s website. Our experimental results on real data demonstrate the efficiency and effectiveness of the proposed algorithms.

Contributors

Agent

Created

Date Created
  • 2015