서브메뉴
검색
Solving Poisson Inverse Problems in Phase Retrieval and Single Photon Emission Computerized Tomography
Solving Poisson Inverse Problems in Phase Retrieval and Single Photon Emission Computerized Tomography
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152055
- ISBN
- 9798382738871
- DDC
- 004
- 저자명
- Li, Zongyu.
- 서명/저자
- Solving Poisson Inverse Problems in Phase Retrieval and Single Photon Emission Computerized Tomography
- 발행사항
- [Sl] : University of Michigan, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 161 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
- 주기사항
- Advisor: Dewaraja, Yuni K.;Fessler, Jeffrey A.
- 학위논문주기
- Thesis (Ph.D.)--University of Michigan, 2024.
- 초록/해제
- 요약We live in a world where many objects cannot be imaged directly and hence rely on reconstruction algorithms to solve the corresponding inverse imaging problems. However, lots of information is contaminated or even lost when samples are collected by imaging devices, so that the resulting inverse problem is ill-posed and challenging to solve. As the recorded photon arrivals by the sensor are often assumed to follow Poisson distributions, algorithms for solving Poisson inverse problems are crucial. This thesis tackles two applications where Poisson inverse problems arise: phase retrieval and single photon emission computerized tomography (SPECT).For phase retrieval, we propose novel optimization algorithms working in low-count regimes, including a novel majorize-minimize (MM) algorithm, a modified Wirtinger flow algorithm using the observed Fisher information for step size and a generative image prior based on score matching. Our proposed algorithms lead to faster convergence rate and improved reconstruction quality evaluated both qualitatively and quantitatively.For SPECT imaging, we focus on deep learning (DL) solutions including: 1) We propose end-to-end training of unrolled iterative convolutional neural network (CNN) using our memory efficient Julia toolbox for SPECT image reconstruction. 2) We propose a dl algorithm for joint dosimetry estimation and image deblurring for estimating patient's absorbed dose-rate distribution in radionuclide therapy. 3) We propose unsupervised coordinate-based learning for predicting missing SPECT projection views.
- 일반주제명
- Computer science
- 일반주제명
- Medical imaging
- 일반주제명
- Electrical engineering
- 일반주제명
- Computer engineering
- 키워드
- Phase retrieval
- 키워드
- Deep learning
- 키워드
- Imaging devices
- 기타저자
- University of Michigan Electrical and Computer Engineering
- 기본자료저록
- Dissertations Abstracts International. 85-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017162789
■00520250211152055
■006m o d
■007cr#unu||||||||
■020 ▼a9798382738871
■035 ▼a(MiAaPQ)AAI31348902
■035 ▼a(MiAaPQ)umichrackham005563
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a004
■1001 ▼aLi, Zongyu.
■24510▼aSolving Poisson Inverse Problems in Phase Retrieval and Single Photon Emission Computerized Tomography
■260 ▼a[Sl]▼bUniversity of Michigan▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a161 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: B.
■500 ▼aAdvisor: Dewaraja, Yuni K.;Fessler, Jeffrey A.
■5021 ▼aThesis (Ph.D.)--University of Michigan, 2024.
■520 ▼aWe live in a world where many objects cannot be imaged directly and hence rely on reconstruction algorithms to solve the corresponding inverse imaging problems. However, lots of information is contaminated or even lost when samples are collected by imaging devices, so that the resulting inverse problem is ill-posed and challenging to solve. As the recorded photon arrivals by the sensor are often assumed to follow Poisson distributions, algorithms for solving Poisson inverse problems are crucial. This thesis tackles two applications where Poisson inverse problems arise: phase retrieval and single photon emission computerized tomography (SPECT).For phase retrieval, we propose novel optimization algorithms working in low-count regimes, including a novel majorize-minimize (MM) algorithm, a modified Wirtinger flow algorithm using the observed Fisher information for step size and a generative image prior based on score matching. Our proposed algorithms lead to faster convergence rate and improved reconstruction quality evaluated both qualitatively and quantitatively.For SPECT imaging, we focus on deep learning (DL) solutions including: 1) We propose end-to-end training of unrolled iterative convolutional neural network (CNN) using our memory efficient Julia toolbox for SPECT image reconstruction. 2) We propose a dl algorithm for joint dosimetry estimation and image deblurring for estimating patient's absorbed dose-rate distribution in radionuclide therapy. 3) We propose unsupervised coordinate-based learning for predicting missing SPECT projection views.
■590 ▼aSchool code: 0127.
■650 4▼aComputer science
■650 4▼aMedical imaging
■650 4▼aElectrical engineering
■650 4▼aComputer engineering
■653 ▼aPoisson inverse problems
■653 ▼aPhase retrieval
■653 ▼aDeep learning
■653 ▼aImaging devices
■690 ▼a0544
■690 ▼a0984
■690 ▼a0574
■690 ▼a0464
■71020▼aUniversity of Michigan▼bElectrical and Computer Engineering.
■7730 ▼tDissertations Abstracts International▼g85-12B.
■790 ▼a0127
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162789▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
