본문

서브메뉴

Generative Models for Problems in Imaging Science
Generative Models for Problems in Imaging Science
Generative Models for Problems in Imaging Science

Detailed Information

자료유형  
 학위논문 서양
최종처리일시  
20260209102848
ISBN  
9798291563731
DDC  
610
저자명  
Kelkar, Varun Ajit.
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  
Generative models
키워드  
Inverse problems
키워드  
Generative adversarial networks
키워드  
Invertible networks
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.

Preview

Export

ChatGPT Discussion

AI Recommended Related Books


    New Books MORE
    Statistics for the past 3 years. Go to brief

    detalle info

    • Reserva
    • No existe
    • Mi carpeta
    • Primera solicitud
    • Non-Book Loan Application
    • Nighttime Book Loan Application
    Material
    número de libro número de llamada Ubicación estado Prestar info
    TF18993 전자도서 대출가능 My Folder 부재도서신고 비도서대출신청 야간 도서대출신청

    * Las reservas están disponibles en el libro de préstamos. Para hacer reservaciones, haga clic en el botón de reserva

    Books borrowed together with this book

    Related Popular Books

    Available after logging in.