본문

서브메뉴

Enhancing Accuracy and Plausibility of Unsupervised Deep-Learning-Based Deformable Image Registration With Registration-Specific Designs and Anatomical Priors
Enhancing Accuracy and Plausibility of Unsupervised Deep-Learning-Based Deformable Image R...
Enhancing Accuracy and Plausibility of Unsupervised Deep-Learning-Based Deformable Image Registration With Registration-Specific Designs and Anatomical Priors

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20260202103618
ISBN  
9798315754503
DDC  
616
저자명  
Liu, Hengjie.
서명/저자  
Enhancing Accuracy and Plausibility of Unsupervised Deep-Learning-Based Deformable Image Registration With Registration-Specific Designs and Anatomical Priors
발행사항  
[Sl] : University of California, Los Angeles, 2025
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2025
형태사항  
206 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-11, Section: B.
주기사항  
Advisor: Sheng, Ke;Ruan, Dan.
학위논문주기  
Thesis (Ph.D.)--University of California, Los Angeles, 2025.
초록/해제  
요약Deformable image registration (DIR) is the computational process of aligning different images to a unified coordinate system through locally varying, non-linear (hence deformable) displacement fields. It is fundamental to many medical image analysis workflows where images from different time points, modalities, or patients need to be compared after spatial alignment. Conventional optimization-based DIR methods have seen limited clinical adoption due to persistent challenges in accuracy and efficiency. Recently, deep-learning-based deformable image registration (DL-DIR) has attracted interest for its speed and ability to leverage rich, data-driven feature representation. Unsupervised and weakly supervised approaches have become the main paradigms of DL-DIR.DIR faces three core challenges: the absence of ground truth, the problem's inherent ill-posedness, and its non-convexity. These intrinsic limitations not only complicate the evaluation of registration accuracy but also hinder the assessment of deformation plausibility. The most common accuracy surrogate for DIR is segmentation label matching (e.g., Dice score) due to its wide availability. As such, weak supervision via contour matching losses becomes popular to boost the Dice metric. Despite improving the apparent accuracy, this strategy often leads to unrealistic deformations and compromises generalizability, especially when applied to datasets with different labeling protocols. Consequently, unsupervised DL-DIR has regained prominence. However, current literature lacks fair, standardized comparisons among unsupervised DL-DIR methods, and offers little consensus on best practices for unsupervised DL-DIR. It is even unclear whether unsupervised DL-DIR truly outperforms conventional methods, and if so, what drives that advantage. Moreover, most DL-DIR methods remain intensity-driven with only simple smoothness regularization, neglecting rich physiological priors in human anatomy. This oversight not only limits accuracy but can yield anatomically implausible deformation fields, significantly hindering clinical translation.To address these challenges, we propose three specific aims. We first conduct a comprehensive ablation-type study to identify the true drivers for accurate unsupervised DL-DIR, which highlights the importance of registration-specific designs. Building upon that, we then tailor DL-DIR to two radiation-therapy applications at two distinct anatomical sites, enhancing accuracy and anatomical plausibility by integrating relevant anatomical information into the registration framework. The three aims are:Specific Aim 1: Enhance accuracy of unsupervised DL-DIR with registration-specific designs. We hypothesize that registration-specific designs such as the multi-resolution pyramid, correlation calculation, and inverse-consistency constraints are more important than complex network architectures. We propose a comprehensive ablation-type study to identify the key modules for unsupervised mono-modal DL-DIR and demonstrate that simple models, when properly equipped with these design choices, can achieve state-of-the-art performance.Specific Aim 2: Improve bladder trigone MRI registration by integrating anatomical context through multi-task learning. We hypothesize that the features learned in landmark prediction and segmentation tasks will improve registration accuracy. We propose a multi-task learning framework for joint landmark regression, segmentation, and deformation registration for the bladder trigone and demonstrate improved registration accuracy.Specific Aim 3: Improve accuracy and plausibility in head-and-neck CT registration using a MUsculo-Skeleton-Aware (MUSA) framework. We hypothesize registration of the complex and heterogeneous head-and-neck deformations can benefit from distinguishing the tissue types and motion types. We propose to decompose such complex deformations into bulk posture changes and residual fine deformations and distinguish between the rigidity of bone structures and the flexibility of soft tissues. With such anatomical knowledge incorporated into the DIR optimization process, we demonstrate both enhanced accuracy and markedly better plausibility of deformation fields.
일반주제명  
Medical imaging
일반주제명  
Biophysics
일반주제명  
Biomedical engineering
일반주제명  
Computer science
키워드  
Deep learning
키워드  
Deformable image registration
키워드  
Medical image analysis
키워드  
Radiation therapy
키워드  
Unsupervised learning
기타저자  
University of California, Los Angeles Physics and Biology in Medicine 009Y
기본자료저록  
Dissertations Abstracts International. 86-11B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008260126s2025        us                              c    eng  d
■001000017357923
■00520260202103618
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798315754503
■035    ▼a(MiAaPQ)AAI32045025
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a616
■1001  ▼aLiu,  Hengjie.
■24510▼aEnhancing  Accuracy  and  Plausibility  of  Unsupervised  Deep-Learning-Based  Deformable  Image  Registration  With  Registration-Specific  Designs  and  Anatomical  Priors
■260    ▼a[Sl]▼bUniversity  of  California,  Los  Angeles▼c2025
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2025
■300    ▼a206  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-11,  Section:  B.
■500    ▼aAdvisor:  Sheng,  Ke;Ruan,  Dan.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Los  Angeles,  2025.
■520    ▼aDeformable  image  registration  (DIR)  is  the  computational  process  of  aligning  different  images  to  a  unified  coordinate  system  through  locally  varying,  non-linear  (hence  deformable)  displacement  fields.  It  is  fundamental  to  many  medical  image  analysis  workflows  where  images  from  different  time  points,  modalities,  or  patients  need  to  be  compared  after  spatial  alignment.  Conventional  optimization-based  DIR  methods  have  seen  limited  clinical  adoption  due  to  persistent  challenges  in  accuracy  and  efficiency.  Recently,  deep-learning-based  deformable  image  registration  (DL-DIR)  has  attracted  interest  for  its  speed  and  ability  to  leverage  rich,  data-driven  feature  representation.  Unsupervised  and  weakly  supervised  approaches  have  become  the  main  paradigms  of  DL-DIR.DIR  faces  three  core  challenges:  the  absence  of  ground  truth,  the  problem's  inherent  ill-posedness,  and  its  non-convexity.  These  intrinsic  limitations  not  only  complicate  the  evaluation  of  registration  accuracy  but  also  hinder  the  assessment  of  deformation  plausibility.  The  most  common  accuracy  surrogate  for  DIR  is  segmentation  label  matching  (e.g.,  Dice  score)  due  to  its  wide  availability.  As  such,  weak  supervision  via  contour  matching  losses  becomes  popular  to  boost  the  Dice  metric.  Despite  improving  the  apparent  accuracy,  this  strategy  often  leads  to  unrealistic  deformations  and  compromises  generalizability,  especially  when  applied  to  datasets  with  different  labeling  protocols.  Consequently,  unsupervised  DL-DIR  has  regained  prominence.  However,  current  literature  lacks  fair,  standardized  comparisons  among  unsupervised  DL-DIR  methods,  and  offers  little  consensus  on  best  practices  for  unsupervised  DL-DIR.  It  is  even  unclear  whether  unsupervised  DL-DIR  truly  outperforms  conventional  methods,  and  if  so,  what  drives  that  advantage.  Moreover,  most  DL-DIR  methods  remain  intensity-driven  with  only  simple  smoothness  regularization,  neglecting  rich  physiological  priors  in  human  anatomy.  This  oversight  not  only  limits  accuracy  but  can  yield  anatomically  implausible  deformation  fields,  significantly  hindering  clinical  translation.To  address  these  challenges,  we  propose  three  specific  aims.  We  first  conduct  a  comprehensive  ablation-type  study  to  identify  the  true  drivers  for  accurate  unsupervised  DL-DIR,  which  highlights  the  importance  of  registration-specific  designs.  Building  upon  that,  we  then  tailor  DL-DIR  to  two  radiation-therapy  applications  at  two  distinct  anatomical  sites,  enhancing  accuracy  and  anatomical  plausibility  by  integrating  relevant  anatomical  information  into  the  registration  framework.  The  three  aims  are:Specific  Aim  1:  Enhance  accuracy  of  unsupervised  DL-DIR  with  registration-specific  designs.  We  hypothesize  that  registration-specific  designs  such  as  the  multi-resolution  pyramid,  correlation  calculation,  and  inverse-consistency  constraints  are  more  important  than  complex  network  architectures.  We  propose  a  comprehensive  ablation-type  study  to  identify  the  key  modules  for  unsupervised  mono-modal  DL-DIR  and  demonstrate  that  simple  models,  when  properly  equipped  with  these  design  choices,  can  achieve  state-of-the-art  performance.Specific  Aim  2:  Improve  bladder  trigone  MRI  registration  by  integrating  anatomical  context  through  multi-task  learning.  We  hypothesize  that  the  features  learned  in  landmark  prediction  and  segmentation  tasks  will  improve  registration  accuracy.  We  propose  a  multi-task  learning  framework  for  joint  landmark  regression,  segmentation,  and  deformation  registration  for  the  bladder  trigone  and  demonstrate  improved  registration  accuracy.Specific  Aim  3:  Improve  accuracy  and  plausibility  in  head-and-neck  CT  registration  using  a  MUsculo-Skeleton-Aware  (MUSA)  framework.  We  hypothesize  registration  of  the  complex  and  heterogeneous  head-and-neck  deformations  can  benefit  from  distinguishing  the  tissue  types  and  motion  types.  We  propose  to  decompose  such  complex  deformations  into  bulk  posture  changes  and  residual  fine  deformations  and  distinguish  between  the  rigidity  of  bone  structures  and  the  flexibility  of  soft  tissues.  With  such  anatomical  knowledge  incorporated  into  the  DIR  optimization  process,  we  demonstrate  both  enhanced  accuracy  and  markedly  better  plausibility  of  deformation  fields.
■590    ▼aSchool  code:  0031.
■650  4▼aMedical  imaging
■650  4▼aBiophysics
■650  4▼aBiomedical  engineering
■650  4▼aComputer  science
■653    ▼aDeep  learning
■653    ▼aDeformable  image  registration
■653    ▼aMedical  image  analysis
■653    ▼aRadiation  therapy
■653    ▼aUnsupervised  learning
■690    ▼a0574
■690    ▼a0786
■690    ▼a0541
■690    ▼a0984
■71020▼aUniversity  of  California,  Los  Angeles▼bPhysics  and  Biology  in  Medicine  009Y.
■7730  ▼tDissertations  Abstracts  International▼g86-11B.
■790    ▼a0031
■791    ▼aPh.D.
■792    ▼a2025
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17357923▼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
    TF17097 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.