서브메뉴
검색
Analyzing Disease Heterogeneity via Weakly-Supervised Deep Learning
Analyzing Disease Heterogeneity via Weakly-Supervised Deep Learning
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151315
- ISBN
- 9798382830476
- DDC
- 610
- 저자명
- Yang, Zhijian.
- 서명/저자
- Analyzing Disease Heterogeneity via Weakly-Supervised Deep Learning
- 발행사항
- [Sl] : University of Pennsylvania, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 143 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
- 주기사항
- Advisor: Davatzikos, Christos.
- 학위논문주기
- Thesis (Ph.D.)--University of Pennsylvania, 2024.
- 초록/해제
- 요약Heterogeneity of brain diseases poses significant challenges for precision medicine. While a plethora of machine learning methods have been applied to imaging data, enabling the construction of clinically relevant imaging signatures for neurological and neuropsychiatric diseases, they often overlook explicit modeling of disease heterogeneity. Moreover, unsupervised methods may inadvertently capture heterogeneity driven by nuisance confounding factors that affect brain structure or function, rather than heterogeneity relevant to the pathology or condition of interest.In this thesis, we have proposed a series of weakly-supervised deep learning approaches that utilize normal control data as reference, specifically characterizing disease effects on brain changes through deep generative modeling. Following this principle, we first proposed, Smile-GAN, a clustering method that estimates dominant subtypes and categorizes patients' imaging data according to disease-related imaging patterns. Second, built upon the foundation established by Smile-GAN, we introduced an improved representation learning approach, Surreal-GAN, which not only captures disease effects, but further disentangles spatial and temporal variations in brain changes, producing concise representation indices directly indicating the severity of different brain change patterns. While Smile-GAN and Surreal-GAN focus solely on capturing disease heterogeneity from neuroimaging data, they may overlook valuable information from other modalities, such as genetics. Therefore, we further developed the multi-view method Gene-SGAN. By effectively distilling information from both imaging and genetic data, Gene-SGAN separates brain changes with and without genetic associations through multi-modal learning, thereby deriving disease endophenotypes closer to the underlying biology.All three methods were first extensively validated through synthetic experiments with known simulated ground truth. More importantly, their applications to different cohorts of real participants' data enhanced our understanding of heterogeneous brain changes related to Alzheimer's disease and the general brain aging process. The derived clusters or indices of these methods demonstrate significant associations with distinct biomedical, lifestyle, and genetic factors, providing insights into the etiology of observed variances. Moreover, they show predictive value for future neurodegeneration, disease progression, and mortality. Consequently, these methods hold promise for more personalized patient management and more optimal clinical trial design.
- 일반주제명
- Biomedical engineering
- 일반주제명
- Computer science
- 일반주제명
- Bioinformatics
- 일반주제명
- Medical imaging
- 키워드
- Heterogeneity
- 키워드
- Brain changes
- 기타저자
- University of Pennsylvania Applied Mathematics and Computational Science
- 기본자료저록
- Dissertations Abstracts International. 85-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161137
■00520250211151315
■006m o d
■007cr#unu||||||||
■020 ▼a9798382830476
■035 ▼a(MiAaPQ)AAI31238186
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a610
■1001 ▼aYang, Zhijian.
■24510▼aAnalyzing Disease Heterogeneity via Weakly-Supervised Deep Learning
■260 ▼a[Sl]▼bUniversity of Pennsylvania▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a143 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: B.
■500 ▼aAdvisor: Davatzikos, Christos.
■5021 ▼aThesis (Ph.D.)--University of Pennsylvania, 2024.
■520 ▼aHeterogeneity of brain diseases poses significant challenges for precision medicine. While a plethora of machine learning methods have been applied to imaging data, enabling the construction of clinically relevant imaging signatures for neurological and neuropsychiatric diseases, they often overlook explicit modeling of disease heterogeneity. Moreover, unsupervised methods may inadvertently capture heterogeneity driven by nuisance confounding factors that affect brain structure or function, rather than heterogeneity relevant to the pathology or condition of interest.In this thesis, we have proposed a series of weakly-supervised deep learning approaches that utilize normal control data as reference, specifically characterizing disease effects on brain changes through deep generative modeling. Following this principle, we first proposed, Smile-GAN, a clustering method that estimates dominant subtypes and categorizes patients' imaging data according to disease-related imaging patterns. Second, built upon the foundation established by Smile-GAN, we introduced an improved representation learning approach, Surreal-GAN, which not only captures disease effects, but further disentangles spatial and temporal variations in brain changes, producing concise representation indices directly indicating the severity of different brain change patterns. While Smile-GAN and Surreal-GAN focus solely on capturing disease heterogeneity from neuroimaging data, they may overlook valuable information from other modalities, such as genetics. Therefore, we further developed the multi-view method Gene-SGAN. By effectively distilling information from both imaging and genetic data, Gene-SGAN separates brain changes with and without genetic associations through multi-modal learning, thereby deriving disease endophenotypes closer to the underlying biology.All three methods were first extensively validated through synthetic experiments with known simulated ground truth. More importantly, their applications to different cohorts of real participants' data enhanced our understanding of heterogeneous brain changes related to Alzheimer's disease and the general brain aging process. The derived clusters or indices of these methods demonstrate significant associations with distinct biomedical, lifestyle, and genetic factors, providing insights into the etiology of observed variances. Moreover, they show predictive value for future neurodegeneration, disease progression, and mortality. Consequently, these methods hold promise for more personalized patient management and more optimal clinical trial design.
■590 ▼aSchool code: 0175.
■650 4▼aBiomedical engineering
■650 4▼aComputer science
■650 4▼aBioinformatics
■650 4▼aMedical imaging
■653 ▼aHeterogeneity
■653 ▼aWeakly-supervised deep learning
■653 ▼aBrain changes
■653 ▼aMild Cognitive Impairment
■653 ▼aBrain aging process
■690 ▼a0800
■690 ▼a0541
■690 ▼a0984
■690 ▼a0574
■690 ▼a0715
■71020▼aUniversity of Pennsylvania▼bApplied Mathematics and Computational Science.
■7730 ▼tDissertations Abstracts International▼g85-12B.
■790 ▼a0175
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161137▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
