본문

서브메뉴

Weak Supervision in Deep Learning for Medical Imaging and Astrophysics
Weak Supervision in Deep Learning for Medical Imaging and Astrophysics
Weak Supervision in Deep Learning for Medical Imaging and Astrophysics

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211151414
ISBN  
9798382761831
DDC  
621.3
저자명  
Wu, Yunan.
서명/저자  
Weak Supervision in Deep Learning for Medical Imaging and Astrophysics
발행사항  
[Sl] : Northwestern University, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
227 p
주기사항  
Source: Dissertations Abstracts International, Volume: 85-11, Section: B.
주기사항  
Advisor: Katsaggelos, Aggelos K.
학위논문주기  
Thesis (Ph.D.)--Northwestern University, 2024.
초록/해제  
요약Traditional supervised learning pipelines heavily rely on high-quality, extensively annotated datasets. These datasets, however, are often costly to produce and prone to errors, leading to inaccurate or insufficient labels. As a remedy, weakly supervised learning (WSL) emerges as a robust alternative by leveraging weaker forms of supervision-such as incomplete, inexact, and inaccurate supervision-to effectively train deep learning models. Chapter 1 provides a foundational overview of WSL, highlighting its necessity and exploring its various methods, including multiple instance learning, transfer learning, crowdsourcing, and multi-modal fusion.This thesis explores the domain of WSL with a particular focus on medical imaging and astrophysics. The first part addresses WSL in medical imaging, a critical domain for disease diagnosis, treatment planning, and monitoring. The major challenge in medical imaging arises from the difficulty in obtaining large, accurately labeled datasets, which are time-consuming and expensive to produce and require expert annotation. The variability inherent in medical subjects further complicates the annotation process. Therefore, the first goal of this work is to develop and apply WSL methods across various medical imaging applications, including classification, detection, and segmentation. Chapter 2 introduces an attention-based multiple instance learning (Att-MIL) approach by combining an attention-based convolutional neural network (Att-CNN) with a variational Gaussian process (VGPMIL). This method efficiently uses hemorrhage labels at scan-level to enhance predictive accuracy at both slice and scan levels, significantly outperforming other methods trained similarly and achieving comparable results to those requiring more detailed slice-level annotations. Chapter 3 builds on this by implementing a Smooth Attention Deep MIL (SA-DMIL) model that incorporates first and second order constraints on the attention mechanism to capture spatial dependencies between slices within a scan. Chapter 4 proposes a novel integration of CNN and Long Short-Term Memory (LSTM) networks for image-level CT hemorrhage localization. This method achieves performance comparable to senior neuroradiologists and provides clinically useful attention weights and heatmaps to facilitate rapid diagnostic decisions. Chapter 5 progresses to pixel-level segmentation of CT hemorrhage using conditioned diffusion models, which trained on image-level labels to generate anomaly maps and reconstruct images, thus minimizing the reliance on extensive pixel-level annotations. Chapter 6 explores the use of multi-modal data to assess the health status and predict outcomes of critically ill COVID-19 patients. It demonstrates that a fusion of chest X-rays, respiratory sounds, and ICU clinical variables significantly enhances the prediction accuracy for indirect outcomes. Finally, Chapter 7 introduces DeepCOVID-Fuse, a deep learning fusion model that combines chest x-rays and clinical variables to predict risk levels in COVID-19 patients, effectively managing outcomes even with missing modalities during testing.The second part of the thesis focuses on WSL in astrophysics, particularly analyzing large-scale astronomical datasets. In this field, expert analysis is crucial for understanding the phenomena of space. However, acquiring labeled datasets is particularly challenging due to the complex and dynamic nature of space, which means that labels must be continuously updated as new discoveries are made and understandings evolve. To address this, crowdsourcing becomes an essential tool, leveraging the efforts of volunteers to annotate data and machine learning to guide these efforts. Therefore, the second goal of this work is to apply WSL methods with crowdsourcing. Chapter 8 introduces the crowdsourcing project Gravity Spy, detailing its workflow and its development from version 1.0 to 2.0. Gravity Spy 1.0 primarily focuses on classifying glitches in the main channel, while Gravity Spy 2.0 extends to include glitches in the auxiliary channels, exploring the underlying correlations between glitches across these channels. Chapter 9 presents a multi-view fusion network with attention mechanisms in Gravity Spy 1.0 for classifying glitches during the new O4 observing run. Finally, Chapter 10 describes the Cross-Temporal Spectrogram Autoencoder (CTSAE), an innovative unsupervised model that identifies correlations between main and auxiliary channel glitches through a novel integration of CNN and Vision Transformers.
일반주제명  
Electrical engineering
일반주제명  
Computer science
일반주제명  
Medical imaging
키워드  
Deep learning
키워드  
Gravity Spy
키워드  
CT hemorrhage
키워드  
Weakly supervised learning
기타저자  
Northwestern University Electrical and Computer Engineering
기본자료저록  
Dissertations Abstracts International. 85-11B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017161571
■00520250211151414
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798382761831
■035    ▼a(MiAaPQ)AAI31293247
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a621.3
■1001  ▼aWu,  Yunan.▼0(orcid)0000-0001-6980-9746
■24510▼aWeak  Supervision  in  Deep  Learning  for  Medical  Imaging  and  Astrophysics
■260    ▼a[Sl]▼bNorthwestern  University▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a227  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  85-11,  Section:  B.
■500    ▼aAdvisor:  Katsaggelos,  Aggelos  K.
■5021  ▼aThesis  (Ph.D.)--Northwestern  University,  2024.
■520    ▼aTraditional  supervised  learning  pipelines  heavily  rely  on  high-quality,  extensively  annotated  datasets.  These  datasets,  however,  are  often  costly  to  produce  and  prone  to  errors,  leading  to  inaccurate  or  insufficient  labels.  As  a  remedy,  weakly  supervised  learning  (WSL)  emerges  as  a  robust  alternative  by  leveraging  weaker  forms  of  supervision-such  as  incomplete,  inexact,  and  inaccurate  supervision-to  effectively  train  deep  learning  models.  Chapter  1  provides  a  foundational  overview  of  WSL,  highlighting  its  necessity  and  exploring  its  various  methods,  including  multiple  instance  learning,  transfer  learning,  crowdsourcing,  and  multi-modal  fusion.This  thesis  explores  the  domain  of  WSL  with  a  particular  focus  on  medical  imaging  and  astrophysics.  The  first  part  addresses  WSL  in  medical  imaging,  a  critical  domain  for  disease  diagnosis,  treatment  planning,  and  monitoring.  The  major  challenge  in  medical  imaging  arises  from  the  difficulty  in  obtaining  large,  accurately  labeled  datasets,  which  are  time-consuming  and  expensive  to  produce  and  require  expert  annotation.  The  variability  inherent  in  medical  subjects  further  complicates  the  annotation  process.  Therefore,  the  first  goal  of  this  work  is  to  develop  and  apply  WSL  methods  across  various  medical  imaging  applications,  including  classification,  detection,  and  segmentation.  Chapter  2  introduces  an  attention-based  multiple  instance  learning  (Att-MIL)  approach  by  combining  an  attention-based  convolutional  neural  network  (Att-CNN)  with  a  variational  Gaussian  process  (VGPMIL).  This  method  efficiently  uses  hemorrhage  labels  at  scan-level  to  enhance  predictive  accuracy  at  both  slice  and  scan  levels,  significantly  outperforming  other  methods  trained  similarly  and  achieving  comparable  results  to  those  requiring  more  detailed  slice-level  annotations.  Chapter  3  builds  on  this  by  implementing  a  Smooth  Attention  Deep  MIL  (SA-DMIL)  model  that  incorporates  first  and  second  order  constraints  on  the  attention  mechanism  to  capture  spatial  dependencies  between  slices  within  a  scan.  Chapter  4  proposes  a  novel  integration  of  CNN  and  Long  Short-Term  Memory  (LSTM)  networks  for  image-level  CT  hemorrhage  localization.  This  method  achieves  performance  comparable  to  senior  neuroradiologists  and  provides  clinically  useful  attention  weights  and  heatmaps  to  facilitate  rapid  diagnostic  decisions.  Chapter  5  progresses  to  pixel-level  segmentation  of  CT  hemorrhage  using  conditioned  diffusion  models,  which  trained  on  image-level  labels  to  generate  anomaly  maps  and  reconstruct  images,  thus  minimizing  the  reliance  on  extensive  pixel-level  annotations.  Chapter  6  explores  the  use  of  multi-modal  data  to  assess  the  health  status  and  predict  outcomes  of  critically  ill  COVID-19  patients.  It  demonstrates  that  a  fusion  of  chest  X-rays,  respiratory  sounds,  and  ICU  clinical  variables  significantly  enhances  the  prediction  accuracy  for  indirect  outcomes.  Finally,  Chapter  7  introduces  DeepCOVID-Fuse,  a  deep  learning  fusion  model  that  combines  chest  x-rays  and  clinical  variables  to  predict  risk  levels  in  COVID-19  patients,  effectively  managing  outcomes  even  with  missing  modalities  during  testing.The  second  part  of  the  thesis  focuses  on  WSL  in  astrophysics,  particularly  analyzing  large-scale  astronomical  datasets.  In  this  field,  expert  analysis  is  crucial  for  understanding  the  phenomena  of  space.  However,  acquiring  labeled  datasets  is  particularly  challenging  due  to  the  complex  and  dynamic  nature  of  space,  which  means  that  labels  must  be  continuously  updated  as  new  discoveries  are  made  and  understandings  evolve.  To  address  this,  crowdsourcing  becomes  an  essential  tool,  leveraging  the  efforts  of  volunteers  to  annotate  data  and  machine  learning  to  guide  these  efforts.  Therefore,  the  second  goal  of  this  work  is  to  apply  WSL  methods  with  crowdsourcing.  Chapter  8  introduces  the  crowdsourcing  project  Gravity  Spy,  detailing  its  workflow  and  its  development  from  version  1.0  to  2.0.  Gravity  Spy  1.0  primarily  focuses  on  classifying  glitches  in  the  main  channel,  while  Gravity  Spy  2.0  extends  to  include  glitches  in  the  auxiliary  channels,  exploring  the  underlying  correlations  between  glitches  across  these  channels.  Chapter  9  presents  a  multi-view  fusion  network  with  attention  mechanisms  in  Gravity  Spy  1.0  for  classifying  glitches  during  the  new  O4  observing  run.  Finally,  Chapter  10  describes  the  Cross-Temporal  Spectrogram  Autoencoder  (CTSAE),  an  innovative  unsupervised  model  that  identifies  correlations  between  main  and  auxiliary  channel  glitches  through  a  novel  integration  of  CNN  and  Vision  Transformers.
■590    ▼aSchool  code:  0163.
■650  4▼aElectrical  engineering
■650  4▼aComputer  science
■650  4▼aMedical  imaging
■653    ▼aDeep  learning
■653    ▼aGravity  Spy
■653    ▼aCT  hemorrhage
■653    ▼aWeakly  supervised  learning
■690    ▼a0544
■690    ▼a0984
■690    ▼a0574
■690    ▼a0800
■71020▼aNorthwestern  University▼bElectrical  and  Computer  Engineering.
■7730  ▼tDissertations  Abstracts  International▼g85-11B.
■790    ▼a0163
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161571▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF10919 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.