서브메뉴
검색
Generative Models for Problems in Imaging Science
Generative Models for Problems in Imaging Science
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260209102848
- ISBN
- 9798291563731
- DDC
- 610
- 서명/저자
- Generative Models for Problems in Imaging Science
- 발행사항
- [Sl] : University of Illinois at Urbana-Champaign, 2023
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2023
- 형태사항
- 189 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
- 주기사항
- Advisor: Anastasio, Mark A.
- 학위논문주기
- Thesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2023.
- 초록/해제
- 요약In recent years, generative models have risen to the forefront of machine learning research. Modern generative models such as generative adversarial networks (GANs) and invertible generative models (IGMs) are capable of approximating high-dimensional image distributions and synthesizing images with high perceptual quality. In imaging science, they are being investigated for several potential applications, such as inverse problems and image reconstruction, image-to-image translation, and dataset augmentation. In the first part of this thesis, generative models are investigated for solving inverse problems in imaging. Specifically, we first developed a new image reconstruction method using a multiscale IGM as a prior, which demonstrated high performance on image reconstruction from stylized, simulated magnetic resonance imaging measurements, and was robust to test-time distribution shifts. Next, a style-based GAN was employed as a prior in a framework for estimating an object of interest that is closely related to a known prior image. The approach accurately captured difficult-to-model semantic differences between the sought-after and prior images and estimated the object accurately in terms of conventional metrics. Third, variational Bayesian methods were employed to learn an IGM of objects directly from a dataset of noisy and incomplete images. The second part of this thesis focuses on evaluating generative models and data-driven priors in imaging. Specifically, the concept of "hallucinations" in the context of image reconstruction was formally defined and utilized to illustrate the effects of an incorrect data-driven prior on the image estimate. Lastly, a framework for evaluating GANs in terms of medically relevant statistics was developed. Perceptual measures for evaluating the GAN did not always correlate with the relevant measures developed, highlighting the urgent need to assess generative models in terms of relevant, task-informed statistics. Our findings directly inspired an ongoing large-scale competition on deep generative modeling for learning medical image statistics.
- 일반주제명
- Biomedical engineering
- 일반주제명
- Computer science
- 일반주제명
- Electrical engineering
- 일반주제명
- Medical imaging
- 키워드
- Imaging science
- 키워드
- Inverse problems
- 키워드
- Tomography
- 키워드
- Diffusion models
- 기타저자
- University of Illinois at Urbana-Champaign Electrical & Computer Eng
- 기본자료저록
- Dissertations Abstracts International. 87-03B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260203s2023 us c eng d■001000017365887
■00520260209102848
■006m o d
■007cr#unu||||||||
■020 ▼a9798291563731
■035 ▼a(MiAaPQ)AAI32271350
■035 ▼a(MiAaPQ)httphdlhandlenet2142121447
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a610
■1001 ▼aKelkar, Varun Ajit.
■24510▼aGenerative Models for Problems in Imaging Science
■260 ▼a[Sl]▼bUniversity of Illinois at Urbana-Champaign▼c2023
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2023
■300 ▼a189 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-03, Section: B.
■500 ▼aAdvisor: Anastasio, Mark A.
■5021 ▼aThesis (Ph.D.)--University of Illinois at Urbana-Champaign, 2023.
■520 ▼aIn recent years, generative models have risen to the forefront of machine learning research. Modern generative models such as generative adversarial networks (GANs) and invertible generative models (IGMs) are capable of approximating high-dimensional image distributions and synthesizing images with high perceptual quality. In imaging science, they are being investigated for several potential applications, such as inverse problems and image reconstruction, image-to-image translation, and dataset augmentation. In the first part of this thesis, generative models are investigated for solving inverse problems in imaging. Specifically, we first developed a new image reconstruction method using a multiscale IGM as a prior, which demonstrated high performance on image reconstruction from stylized, simulated magnetic resonance imaging measurements, and was robust to test-time distribution shifts. Next, a style-based GAN was employed as a prior in a framework for estimating an object of interest that is closely related to a known prior image. The approach accurately captured difficult-to-model semantic differences between the sought-after and prior images and estimated the object accurately in terms of conventional metrics. Third, variational Bayesian methods were employed to learn an IGM of objects directly from a dataset of noisy and incomplete images. The second part of this thesis focuses on evaluating generative models and data-driven priors in imaging. Specifically, the concept of "hallucinations" in the context of image reconstruction was formally defined and utilized to illustrate the effects of an incorrect data-driven prior on the image estimate. Lastly, a framework for evaluating GANs in terms of medically relevant statistics was developed. Perceptual measures for evaluating the GAN did not always correlate with the relevant measures developed, highlighting the urgent need to assess generative models in terms of relevant, task-informed statistics. Our findings directly inspired an ongoing large-scale competition on deep generative modeling for learning medical image statistics.
■590 ▼aSchool code: 0090.
■650 4▼aBiomedical engineering
■650 4▼aComputer science
■650 4▼aElectrical engineering
■650 4▼aMedical imaging
■653 ▼aImaging science
■653 ▼aGenerative models
■653 ▼aInverse problems
■653 ▼aGenerative adversarial networks
■653 ▼aInvertible networks
■653 ▼aTomography
■653 ▼aDiffusion models
■690 ▼a0544
■690 ▼a0984
■690 ▼a0541
■690 ▼a0574
■71020▼aUniversity of Illinois at Urbana-Champaign▼bElectrical & Computer Eng.
■7730 ▼tDissertations Abstracts International▼g87-03B.
■790 ▼a0090
■791 ▼aPh.D.
■792 ▼a2023
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17365887▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


