Filtering by
- Genre: Academic theses
- Genre: Masters Thesis
- Member of: Theses and Dissertations
Because of its established role in cancer care and its non-invasive nature imaging offers the potential to complement the findings of cancer biology. Over the past decade, a compelling body of literature has emerged suggesting a more pivotal role for imaging in the diagnosis, prognosis, and monitoring of diseases. These advances have facilitated the rise of an emerging practice known as Radiomics: the extraction and analysis of large numbers of quantitative features from medical images to improve disease characterization and prediction of outcome. It has been suggested that radiomics can contribute to biomarker discovery by detecting imaging traits that are complementary or interchangeable with other markers.
This thesis seeks further advancement of imaging biomarker discovery. This research unfolds over two aims: I) developing a comprehensive methodological pipeline for converting diagnostic imaging data into mineable sources of information, and II) investigating the utility of imaging data in clinical diagnostic applications. Four validation studies were conducted using the radiomics pipeline developed in aim I. These studies had the following goals: (1 distinguishing between benign and malignant head and neck lesions (2) differentiating benign and malignant breast cancers, (3) predicting the status of Human Papillomavirus in head and neck cancers, and (4) predicting neuropsychological performances as they relate to Alzheimer’s disease progression. The long-term objective of this thesis is to improve patient outcome and survival by facilitating incorporation of routine care imaging data into decision making processes.
The first part deals with modeling and identification of network dynamics. I study two types of network dynamics arising from social and gene networks. Based on the network dynamics, the proposed network identification method works like a `network RADAR', meaning that interaction strengths between agents are inferred by injecting `signal' into the network and observing the resultant reverberation. In social networks, this is accomplished by stubborn agents whose opinions do not change throughout a discussion. In gene networks, genes are suppressed to create desired perturbations. The steady-states under these perturbations are characterized. In contrast to the common assumption of full rank input, I take a laxer assumption where low-rank input is used, to better model the empirical network data. Importantly, a network is proven to be identifiable from low rank data of rank that grows proportional to the network's sparsity. The proposed method is applied to synthetic and empirical data, and is shown to offer superior performance compared to prior work. The second part is concerned with algorithms on networks. I develop three consensus-based algorithms for multi-agent optimization. The first method is a decentralized Frank-Wolfe (DeFW) algorithm. The main advantage of DeFW lies on its projection-free nature, where we can replace the costly projection step in traditional algorithms by a low-cost linear optimization step. I prove the convergence rates of DeFW for convex and non-convex problems. I also develop two consensus-based alternating optimization algorithms --- one for least square problems and one for non-convex problems. These algorithms exploit the problem structure for faster convergence and their efficacy is demonstrated by numerical simulations.
I conclude this dissertation by describing future research directions.
This thesis develops a unique type of textual features that generalize triplets extracted from text, by clustering them into high-level concepts. These concepts are utilized as features to detect frames in text. Compared to uni-gram and bi-gram based models, classification and clustering using generalized concepts yield better discriminating features and a higher classification accuracy with a 12% boost (i.e. from 74% to 83% F-measure) and 0.91 clustering purity for Frame/Non-Frame detection.
The automatic discovery of complex causal chains among interlinked events and their participating actors has not yet been thoroughly studied. Previous studies related to extracting causal relationships from text were based on laborious and incomplete hand-developed lists of explicit causal verbs, such as “causes" and “results in." Such approaches result in limited recall because standard causal verbs may not generalize well to accommodate surface variations in texts when different keywords and phrases are used to express similar causal effects. Therefore, I present a system that utilizes generalized concepts to extract causal relationships. The proposed algorithms overcome surface variations in written expressions of causal relationships and discover the domino effects between climate events and human security. This semi-supervised approach alleviates the need for labor intensive keyword list development and annotated datasets. Experimental evaluations by domain experts achieve an average precision of 82%. Qualitative assessments of causal chains show that results are consistent with the 2014 IPCC report illuminating causal mechanisms underlying the linkages between climatic stresses and social instability.
The feature extraction processes can be categorized into three groups. The first group contains processes that are hand-crafted for a specific task. Hand-engineering features requires the knowledge of domain experts and manual labor. However, the feature extraction process is interpretable and explainable. Next group contains the latent-feature extraction processes. While the original feature lies in a high-dimensional space, the relevant factors for a task often lie on a lower dimensional manifold. The latent-feature extraction employs hidden variables to expose the underlying data properties that cannot be directly measured from the input. Latent features seek a specific structure such as sparsity or low-rank into the derived representation through sophisticated optimization techniques. The last category is that of deep features. These are obtained by passing raw input data with minimal pre-processing through a deep network. Its parameters are computed by iteratively minimizing a task-based loss.
In this dissertation, I present four pieces of work where I create and learn suitable data representations. The first task employs hand-crafted features to perform clinically-relevant retrieval of diabetic retinopathy images. The second task uses latent features to perform content-adaptive image enhancement. The third task ranks a pair of images based on their aestheticism. The goal of the last task is to capture localized image artifacts in small datasets with patch-level labels. For both these tasks, I propose novel deep architectures and show significant improvement over the previous state-of-art approaches. A suitable combination of feature representations augmented with an appropriate learning approach can increase performance for most visual computing tasks.
text, etc. into feature representations that are convenient for computational process-
ing. Deep neural networks have proven to be very efficient feature extractors for a
variety of machine learning tasks. Generative models based on deep neural networks
introduce constraints on the feature space to learn transferable and disentangled rep-
resentations. Transferable feature representations help in training machine learning
models that are robust across different distributions of data. For example, with the
application of transferable features in domain adaptation, models trained on a source
distribution can be applied to a data from a target distribution even though the dis-
tributions may be different. In style transfer and image-to-image translation, disen-
tangled representations allow for the separation of style and content when translating
images.
This thesis examines learning transferable data representations in novel deep gen-
erative models. The Semi-Supervised Adversarial Translator (SAT) utilizes adversar-
ial methods and cross-domain weight sharing in a neural network to extract trans-
ferable representations. These transferable interpretations can then be decoded into
the original image or a similar image in another domain. The Explicit Disentangling
Network (EDN) utilizes generative methods to disentangle images into their core at-
tributes and then segments sets of related attributes. The EDN can separate these
attributes by controlling the ow of information using a novel combination of losses
and network architecture. This separation of attributes allows precise modi_cations
to speci_c components of the data representation, boosting the performance of ma-
chine learning tasks. The effectiveness of these models is evaluated across domain
adaptation, style transfer, and image-to-image translation tasks.
Synchrotron based X-ray Fluorescence (XRF) and X-ray Beam Induced Current (XBIC) are used to study the effect that compositional variations, between grains and at grain boundaries, have on CIGS device properties. An experimental approach is presented to correcting XRF and XBIC quantification of CIGS thin film solar cells. When applying XRF and XBIC to study low and high gallium CIGS devices, it was determined that increased copper and gallium at grain boundaries leads to increased collection efficiency at grain boundaries in low gallium absorbers. However, composition variations were not correlated with changes in collection efficiency in high gallium absorbers, despite the decreased collection efficiency observed at grain boundaries.
Understanding the nature and impact of these defects is only half the battle; controlling or mitigating their impact is the next challenge. This requires a thorough understanding of the origin of these defects and their kinetics. For such a study, a temperature and atmosphere controlled in situ stage was developed. The stage was utilized to study CIGS films during a rapid thermal growth process. Comparing composition variations across different acquisition times and growth temperatures required the implementation of machine learning techniques, including clustering and classification algorithms. From the analysis, copper was determined to segregate the faster than indium and gallium, and clustering techniques showed consistent elemental segregation into copper rich and copper poor regions. Ways to improve the current framework and new applications are also discussed.
The objective of the research is to test the use of 3D printed thermoplastic to produce fixtures which affix instrumentation to asphalt concrete samples used for Simple Performance Testing (SPT). The testing is done as part of materials characterization to obtain properties that will help in future pavement designs. Currently, these fixtures (mounting studs) are made of expensive brass and cumbersome to clean with or without chemicals.
Three types of thermoplastics were utilized to assess the effect of temperature and applied stress on the performance of the 3D printed studs. Asphalt concrete samples fitted with thermoplastic studs were tested according to AASHTO & ASTM standards. The thermoplastics tested are: Polylactic acid (PLA), the most common 3D printing material; Acrylonitrile Butadiene Styrene (ABS), a typical 3D printing material which is less rigid than PLA and has a higher melting temperature; Polycarbonate (PC), a strong, high temperature 3D printing material.
A high traffic volume Marshal mix design from the City of Phoenix was obtained and adapted to a Superpave mix design methodology. The mix design is dense-graded with nominal maximum aggregate size of ¾” inch and a PG 70-10 binder. Samples were fabricated and the following tests were performed: Dynamic Modulus |E*| conducted at five temperatures and six frequencies; Flow Number conducted at a high temperature of 50°C, and axial cyclic fatigue test at a moderate temperature of 18°C.
The results from SPT for each 3D printed material were compared to results using brass mounting studs. Validation or rejection of the concept was determined from statistical analysis on the mean and variance of collected SPT test data.
The concept of using 3D printed thermoplastic for mounting stud fabrication is a promising option; however, the concept should be verified with more extensive research using a variety of asphalt mixes and operators to ensure no bias in the repeatability and reproducibility of test results. The Polycarbonate (PC) had a stronger layer bonding than ABS and PLA while printing. It was recommended for follow up studies.
Topic 1: Design of super-HIS and tracking of quality of care (QoC). My research developed an information technology that integrates multiple HISs in radiology, and proposed QoC metrics defined upon the data that measure various dimensions of care. The DDD assisted the clinical practices and enabled an effective intervention for reducing lengthy radiologist turnaround times for patients.
Topic 2: Monitoring and change detection of QoC data streams for process improvement. With the super-HIS in place, high-dimensional data streams of QoC metrics are generated. I developed a statistical model for monitoring high- dimensional data streams that integrated Singular Vector Decomposition (SVD) and process control. The algorithm was applied to QoC metrics data, and additionally extended to another application of monitoring traffic data in communication networks.
Topic 3: Deep transfer learning of archive HIS data for computer-aided diagnosis (CAD). The novelty of the CAD system is the development of a deep transfer learning algorithm that combines the ideas of transfer learning and multi- modality image integration under the deep learning framework. Our system achieved high accuracy in breast cancer diagnosis compared with conventional machine learning algorithms.