Matching Items (3)
Filtering by

Clear all filters

155389-Thumbnail Image.png
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 the sparse learning model to large-scale problems that have massive data samples with high-dimensional features. One popular and promising strategy

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.
ContributorsLi, Qingyang (Author) / Ye, Jieping (Thesis advisor) / Xue, Guoliang (Thesis advisor) / He, Jingrui (Committee member) / Wang, Yalin (Committee member) / Li, Jing (Committee member) / Arizona State University (Publisher)
Created2017
157808-Thumbnail Image.png
Description
Deep learning is a sub-field of machine learning in which models are developed to imitate the workings of the human brain in processing data and creating patterns for decision making. This dissertation is focused on developing deep learning models for medical imaging analysis of different modalities for different tasks including

Deep learning is a sub-field of machine learning in which models are developed to imitate the workings of the human brain in processing data and creating patterns for decision making. This dissertation is focused on developing deep learning models for medical imaging analysis of different modalities for different tasks including detection, segmentation and classification. Imaging modalities including digital mammography (DM), magnetic resonance imaging (MRI), positron emission tomography (PET) and computed tomography (CT) are studied in the dissertation for various medical applications. The first phase of the research is to develop a novel shallow-deep convolutional neural network (SD-CNN) model for improved breast cancer diagnosis. This model takes one type of medical image as input and synthesizes different modalities for additional feature sources; both original image and synthetic image are used for feature generation. This proposed architecture is validated in the application of breast cancer diagnosis and proved to be outperforming the competing models. Motivated by the success from the first phase, the second phase focuses on improving medical imaging synthesis performance with advanced deep learning architecture. A new architecture named deep residual inception encoder-decoder network (RIED-Net) is proposed. RIED-Net has the advantages of preserving pixel-level information and cross-modality feature transferring. The applicability of RIED-Net is validated in breast cancer diagnosis and Alzheimer’s disease (AD) staging. Recognizing medical imaging research often has multiples inter-related tasks, namely, detection, segmentation and classification, my third phase of the research is to develop a multi-task deep learning model. Specifically, a feature transfer enabled multi-task deep learning model (FT-MTL-Net) is proposed to transfer high-resolution features from segmentation task to low-resolution feature-based classification task. The application of FT-MTL-Net on breast cancer detection, segmentation and classification using DM images is studied. As a continuing effort on exploring the transfer learning in deep models for medical application, the last phase is to develop a deep learning model for both feature transfer and knowledge from pre-training age prediction task to new domain of Mild cognitive impairment (MCI) to AD conversion prediction task. It is validated in the application of predicting MCI patients’ conversion to AD with 3D MRI images.
ContributorsGao, Fei (Author) / Wu, Teresa (Thesis advisor) / Li, Jing (Committee member) / Yan, Hao (Committee member) / Patel, Bhavika (Committee member) / Arizona State University (Publisher)
Created2019
158670-Thumbnail Image.png
Description
Electromagnetic fields (EMFs) generated by biologically active neural tissue are critical in the diagnosis and treatment of neurological diseases. Biological EMFs are characterized by electromagnetic properties such as electrical conductivity, permittivity and magnetic susceptibility. The electrical conductivity of active tissue has been shown to serve as a biomarker for

Electromagnetic fields (EMFs) generated by biologically active neural tissue are critical in the diagnosis and treatment of neurological diseases. Biological EMFs are characterized by electromagnetic properties such as electrical conductivity, permittivity and magnetic susceptibility. The electrical conductivity of active tissue has been shown to serve as a biomarker for the direct detection of neural activity, and the diagnosis, staging and prognosis of disease states such as cancer. Magnetic resonance electrical impedance tomography (MREIT) was developed to map the cross-sectional conductivity distribution of electrically conductive objects using externally applied electrical currents. Simulation and in vitro studies of invertebrate neural tissue complexes demonstrated the correlation of membrane conductivity variations with neural activation levels using the MREIT technique, therefore laying the foundation for functional MREIT (fMREIT) to detect neural activity, and future in vivo fMREIT studies.



The development of fMREIT for the direct detection of neural activity using conductivity contrast in in vivo settings has been the focus of the research work presented here. An in vivo animal model was developed to detect neural activity initiated changes in neuronal membrane conductivities under external electrical current stimulation. Neural activity was induced in somatosensory areas I (SAI) and II (SAII) by applying electrical currents between the second and fourth digits of the rodent forepaw. The in vivo animal model involved the use of forepaw stimulation to evoke somatosensory neural activations along with hippocampal fMREIT imaging currents contemporaneously applied under magnetic field strengths of 7 Tesla. Three distinct types of fMREIT current waveforms were applied as imaging currents under two inhalants – air and carbogen. Active regions in the somatosensory cortex showed significant apparent conductivity changes as variations in fMREIT phase (φ_d and ∇^2 φ_d) signals represented by fMREIT activation maps (F-tests, p <0.05). Consistent changes in the standard deviation of φ_d and ∇^2 φ_d in cortical voxels contralateral to forepaw stimulation were observed across imaging sessions. These preliminary findings show that fMREIT may have the potential to detect conductivity changes correlated with neural activity.
ContributorsAshok Kumar, Neeta (Author) / Sadleir, Rosalind J (Thesis advisor) / Greger, Bradley (Committee member) / Muthuswamy, Jitendran (Committee member) / Tillery, Stephen H (Committee member) / Sohn, SungMin (Committee member) / Arizona State University (Publisher)
Created2020