東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Physics-Based Deep Learning Methods ...

Zhang, Jinwei.

Linked to FindBook

Google Book

Amazon

博客來

Physics-Based Deep Learning Methods for Magnetic Resonance Data Sampling, Image Reconstruction and Quantitative Susceptibility Mapping.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Physics-Based Deep Learning Methods for Magnetic Resonance Data Sampling, Image Reconstruction and Quantitative Susceptibility Mapping./
Author:	Zhang, Jinwei.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
Description:	246 p.
Notes:	Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
Contained By:	Dissertations Abstracts International85-03B.
Subject:	Medical imaging. -
Online resource:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30525224
ISBN:	9798380314268

Physics-Based Deep Learning Methods for Magnetic Resonance Data Sampling, Image Reconstruction and Quantitative Susceptibility Mapping.
Zhang, Jinwei.

Physics-Based Deep Learning Methods for Magnetic Resonance Data Sampling, Image Reconstruction and Quantitative Susceptibility Mapping. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 246 p.

Source: Dissertations Abstracts International, Volume: 85-03, Section: B.

Thesis (Ph.D.)--Cornell University, 2023.

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

Improved magnetic resonance (MR) data sampling, under-sampled image reconstruction, and dipole inversion can be achieved using physics-based deep learning methods. These methods leverage the physical models of MR imaging processes to improve the quality and accuracy of MR images.One approach to improving MR data sampling involves optimizing the k-space under-sampling pattern from fully sampled k-space dataset. A pioneering work is called LOUPE which updates the probabilistic density function used to generate binary k-space sampling patterns, and uses a sigmoid approximation to sample from the learned density function.In addition, physics-based deep learning methods can be used for under-sampled image reconstruction by incorporating the imaging physical models into the deep learning architectures. Pioneering works, such as VarNet and MoDL, have incorporated physical models by unrolling iterative reconstruction algorithms with deep learning-based regularizers.Moreover, physics-based deep learning has also improved the ill-posed problem of dipole inversion used to extract tissue susceptibility from magnetic field data. QSMnet and DeepQSM are two pioneering works that have tackled this problem by incorporating physical models either into the training loss function or through simulating the training dataset.This thesis contributes to physics-based deep learning for MRI by: 1) improving LOUPE using a straight-through (ST) estimator and extending the improved LOUPE to multi-echo and multi-contrast scenarios; 2) developing pulse sequence for prospective multi-echo gradient echo under-sampling and customized efficient multi-contrast sampling; 3) designing image reconstruction network architectures aggregating multi-echo and multi-contrast image features; 4) utilizing physical models into the loss function for test time fine-tuning to improve generalization; 5) solving Bayesian posterior estimation of dipole inversion problem using Variational Inference (VI) incorporating physical models.

ISBN: 9798380314268Subjects--Topical Terms:

3172799
Medical imaging.
Subjects--Index Terms:

Improved magnetic resonance

Physics-Based Deep Learning Methods for Magnetic Resonance Data Sampling, Image Reconstruction and Quantitative Susceptibility Mapping.
LDR:03253nmm a2200373 4500 001 2394859
005 20240513061033.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798380314268
035 $a (MiAaPQ)AAI30525224
035 $a AAI30525224
040 $a MiAaPQ $c MiAaPQ
100 1 $a Zhang, Jinwei. $3 3278782
245 1 0 $a Physics-Based Deep Learning Methods for Magnetic Resonance Data Sampling, Image Reconstruction and Quantitative Susceptibility Mapping.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 246 p.
500 $a Source: Dissertations Abstracts International, Volume: 85-03, Section: B.
500 $a Advisor: Wang, Yi.
502 $a Thesis (Ph.D.)--Cornell University, 2023.
506 $a This item must not be sold to any third party vendors.
520 $a Improved magnetic resonance (MR) data sampling, under-sampled image reconstruction, and dipole inversion can be achieved using physics-based deep learning methods. These methods leverage the physical models of MR imaging processes to improve the quality and accuracy of MR images.One approach to improving MR data sampling involves optimizing the k-space under-sampling pattern from fully sampled k-space dataset. A pioneering work is called LOUPE which updates the probabilistic density function used to generate binary k-space sampling patterns, and uses a sigmoid approximation to sample from the learned density function.In addition, physics-based deep learning methods can be used for under-sampled image reconstruction by incorporating the imaging physical models into the deep learning architectures. Pioneering works, such as VarNet and MoDL, have incorporated physical models by unrolling iterative reconstruction algorithms with deep learning-based regularizers.Moreover, physics-based deep learning has also improved the ill-posed problem of dipole inversion used to extract tissue susceptibility from magnetic field data. QSMnet and DeepQSM are two pioneering works that have tackled this problem by incorporating physical models either into the training loss function or through simulating the training dataset.This thesis contributes to physics-based deep learning for MRI by: 1) improving LOUPE using a straight-through (ST) estimator and extending the improved LOUPE to multi-echo and multi-contrast scenarios; 2) developing pulse sequence for prospective multi-echo gradient echo under-sampling and customized efficient multi-contrast sampling; 3) designing image reconstruction network architectures aggregating multi-echo and multi-contrast image features; 4) utilizing physical models into the loss function for test time fine-tuning to improve generalization; 5) solving Bayesian posterior estimation of dipole inversion problem using Variational Inference (VI) incorporating physical models.
590 $a School code: 0058.
650 4 $a Medical imaging. $3 3172799
650 4 $a Biophysics. $3 518360
653 $a Improved magnetic resonance
653 $a Probabilistic density function
653 $a Deep learning architectures
690 $a 0574
690 $a 0786
690 $a 0800
710 2 $a Cornell University. $b Biomedical Engineering. $3 3174073
773 0 $t Dissertations Abstracts International $g 85-03B.
790 $a 0058
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30525224