東華大學圖書館 |

Kernel and Manifold Framework for Magnetic Resonance Imaging.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Kernel and Manifold Framework for Magnetic Resonance Imaging./
作者:	Nakarmi, Ukash.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2018,
面頁冊數:	123 p.
附註:	Source: Dissertations Abstracts International, Volume: 79-12, Section: B.
Contained By:	Dissertations Abstracts International79-12B.
標題:	Biomedical engineering. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10817180
ISBN:	9780438048218

Kernel and Manifold Framework for Magnetic Resonance Imaging.
Nakarmi, Ukash.

Kernel and Manifold Framework for Magnetic Resonance Imaging. - Ann Arbor : ProQuest Dissertations & Theses, 2018 - 123 p.

Source: Dissertations Abstracts International, Volume: 79-12, Section: B.

Thesis (Ph.D.)--State University of New York at Buffalo, 2018.

This item must not be sold to any third party vendors.

Magnetic resonance imaging (MRI) is one of the most advanced imaging technologies that encompasses both structural and functional imaging paradigm. It allows us to visualize not only qualitative structures but also quantitative and functional properties of cells, tissues and biological process in a body. However, MRI suffers from very slow data acquisition process due to various inherent physical and physiological constraints. Such slow signal acquisition consequences in several limitations and challenges in imaging such as low spatiotemporal resolution, noise and image artifacts, inefficiency in imaging fast temporal dynamics, and patient discomfort. Therefore, fast imaging has been of perennial interest since the emergence of MRI. One way to accelerate MRI is to reconstruct images from reduced signal acquisitions. Reduced acquisitions under-sample MR signals at sub-Nyquist rate and dedicated image reconstruction techniques are applied to reconstruct images. Current trends in image reconstruction from under-sampled signals rely solely on conventional signal reconstruction paradigms such as compressed sensing (CS) with sparsity constraints and low-rank modeling using singular value decomposition and principal component analysis. All these reconstruction methods depend on the signal priors that are based on linear correlation amongst signals. These methods overlook intrinsic nonlinear correlation inhibited by complex MR signals and hence reconstructed images are unable to characterize detail structural and functional properties often demanded in clinical settings. While many nonlinear manifold models have been studied for signal representation outside MR community and much theoretical advancement in signal reconstructions have been made, there is a clear gap between new theoretical developments in signal reconstruction and its application in medical imaging. The use of manifold learning models in MRI image reconstruction is challenging because of several inherent issues such as lack of sufficient training data, computational complexity, and unlike in image processing and other data classification applications, in MRI input and output signals are in different space i.e. the undersampled signal is acquired in k-space domain whereas the output is desired in the image domain. This necessitates dedicated reconstruction strategies for dMRI. Moreover, due to the undersampling of k-space in MRI, an optimization problem of image reconstruction from acquired k-space is highly ill-posed. In this work, we developed two novel manifold frameworks: (i) kernel-based framework and (ii) local geometry preserving joint manifold and sparsity aware framework for MR image representation and reconstruction. The kernel framework maps the original data to a higher dimensional feature space through a nonlinear mapping, such that nonlinear manifold models in the original space can be implemented as linear ones in the feature space. The kernel-based framework allows image reconstruction from the nonlinear model by using sub-Nyquist data. Within this framework, many existing linear algorithms can be extended to kernel framework with nonlinear models. In particular, we have developed a novel algorithm with a kernel-based low-rank (KLR) model generalizing the conventional low-rank formulation. The algorithm consists of manifold learning using kernel, low-rank enforcement in feature space, and preimaging with data consistency. Moreover, the kernel low-rank model is also extended to nonlinear dictionary learning in kernel space. Extensive simulation and experiment results show that the proposed kernel framework surpasses the conventional low-rank-modeled approaches for dMRI. On the other hand, in the joint manifold and sparse framework manifold geometry is learned from the incomplete data. MR images are then represented as points lying on or close to this low dimensional manifold space. Then we capitalize the manifold knowledge and sparsity apriors of MR images to reconstruct high-quality MR images from severely corrupted aliased MR images obtained from compressive measurements. A novel data-driven manifold learning approach that preserves an affine relation among images is developed. Such an approach provides low dimensional embeddings to high dimensional dynamic images. Such manifold modeled embeddings not only preserve the affine relation but also efficiently capture temporal dynamics of dMR image sequence. Furthermore, two sparse loss functions that essentially exploit two well established apriori temporal dynamics, smoothness and periodicity of dMRI are developed. Henceforth, a novel joint manifold and sparsity aware data model and reconstruction framework for dMRI is developed. The superiority of the proposed framework for reconstruction of dMR images from highly undersampled k-space data is verified through extensive tests on numerical phantoms and in-vivo data sets.

ISBN: 9780438048218Subjects--Topical Terms:

535387
Biomedical engineering.

Kernel and Manifold Framework for Magnetic Resonance Imaging.
LDR:06028nmm a2200337 4500 001 2211053
005 20191126114026.5
008 201008s2018 ||||||||||||||||| ||eng d
020 $a 9780438048218
035 $a (MiAaPQ)AAI10817180
035 $a (MiAaPQ)buffalo:15708
035 $a AAI10817180
040 $a MiAaPQ $c MiAaPQ
100 1 $a Nakarmi, Ukash. $3 3438207
245 1 0 $a Kernel and Manifold Framework for Magnetic Resonance Imaging.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2018
300 $a 123 p.
500 $a Source: Dissertations Abstracts International, Volume: 79-12, Section: B.
500 $a Publisher info.: Dissertation/Thesis.
500 $a Advisor: Ying, Leslie.
502 $a Thesis (Ph.D.)--State University of New York at Buffalo, 2018.
506 $a This item must not be sold to any third party vendors.
520 $a Magnetic resonance imaging (MRI) is one of the most advanced imaging technologies that encompasses both structural and functional imaging paradigm. It allows us to visualize not only qualitative structures but also quantitative and functional properties of cells, tissues and biological process in a body. However, MRI suffers from very slow data acquisition process due to various inherent physical and physiological constraints. Such slow signal acquisition consequences in several limitations and challenges in imaging such as low spatiotemporal resolution, noise and image artifacts, inefficiency in imaging fast temporal dynamics, and patient discomfort. Therefore, fast imaging has been of perennial interest since the emergence of MRI. One way to accelerate MRI is to reconstruct images from reduced signal acquisitions. Reduced acquisitions under-sample MR signals at sub-Nyquist rate and dedicated image reconstruction techniques are applied to reconstruct images. Current trends in image reconstruction from under-sampled signals rely solely on conventional signal reconstruction paradigms such as compressed sensing (CS) with sparsity constraints and low-rank modeling using singular value decomposition and principal component analysis. All these reconstruction methods depend on the signal priors that are based on linear correlation amongst signals. These methods overlook intrinsic nonlinear correlation inhibited by complex MR signals and hence reconstructed images are unable to characterize detail structural and functional properties often demanded in clinical settings. While many nonlinear manifold models have been studied for signal representation outside MR community and much theoretical advancement in signal reconstructions have been made, there is a clear gap between new theoretical developments in signal reconstruction and its application in medical imaging. The use of manifold learning models in MRI image reconstruction is challenging because of several inherent issues such as lack of sufficient training data, computational complexity, and unlike in image processing and other data classification applications, in MRI input and output signals are in different space i.e. the undersampled signal is acquired in k-space domain whereas the output is desired in the image domain. This necessitates dedicated reconstruction strategies for dMRI. Moreover, due to the undersampling of k-space in MRI, an optimization problem of image reconstruction from acquired k-space is highly ill-posed. In this work, we developed two novel manifold frameworks: (i) kernel-based framework and (ii) local geometry preserving joint manifold and sparsity aware framework for MR image representation and reconstruction. The kernel framework maps the original data to a higher dimensional feature space through a nonlinear mapping, such that nonlinear manifold models in the original space can be implemented as linear ones in the feature space. The kernel-based framework allows image reconstruction from the nonlinear model by using sub-Nyquist data. Within this framework, many existing linear algorithms can be extended to kernel framework with nonlinear models. In particular, we have developed a novel algorithm with a kernel-based low-rank (KLR) model generalizing the conventional low-rank formulation. The algorithm consists of manifold learning using kernel, low-rank enforcement in feature space, and preimaging with data consistency. Moreover, the kernel low-rank model is also extended to nonlinear dictionary learning in kernel space. Extensive simulation and experiment results show that the proposed kernel framework surpasses the conventional low-rank-modeled approaches for dMRI. On the other hand, in the joint manifold and sparse framework manifold geometry is learned from the incomplete data. MR images are then represented as points lying on or close to this low dimensional manifold space. Then we capitalize the manifold knowledge and sparsity apriors of MR images to reconstruct high-quality MR images from severely corrupted aliased MR images obtained from compressive measurements. A novel data-driven manifold learning approach that preserves an affine relation among images is developed. Such an approach provides low dimensional embeddings to high dimensional dynamic images. Such manifold modeled embeddings not only preserve the affine relation but also efficiently capture temporal dynamics of dMR image sequence. Furthermore, two sparse loss functions that essentially exploit two well established apriori temporal dynamics, smoothness and periodicity of dMRI are developed. Henceforth, a novel joint manifold and sparsity aware data model and reconstruction framework for dMRI is developed. The superiority of the proposed framework for reconstruction of dMR images from highly undersampled k-space data is verified through extensive tests on numerical phantoms and in-vivo data sets.
590 $a School code: 0656.
650 4 $a Biomedical engineering. $3 535387
650 4 $a Electrical engineering. $3 649834
650 4 $a Medical imaging. $3 3172799
690 $a 0541
690 $a 0544
690 $a 0574
710 2 $a State University of New York at Buffalo. $b Electrical Engineering. $3 1019366
773 0 $t Dissertations Abstracts International $g 79-12B.
790 $a 0656
791 $a Ph.D.
792 $a 2018
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10817180