서브메뉴
검색
Science and Technology of Extracellular Vesicles in Medical Applications Utilizing SERS and Machine Learning
Science and Technology of Extracellular Vesicles in Medical Applications Utilizing SERS and Machine Learning
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20260202105153
- ISBN
- 9798293839667
- DDC
- 620.11
- 서명/저자
- Science and Technology of Extracellular Vesicles in Medical Applications Utilizing SERS and Machine Learning
- 발행사항
- [Sl] : University of California, Los Angeles, 2025
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2025
- 형태사항
- 188 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 87-03, Section: B.
- 주기사항
- Advisor: Xie, Ya-Hong.
- 학위논문주기
- Thesis (Ph.D.)--University of California, Los Angeles, 2025.
- 초록/해제
- 요약Extracellular vesicles (EVs), particularly exosomes, show significant promise in biomedical diagnostics and therapeutics due to their rich biochemical content. However, precisely characterizing individual exosomes remains challenging for conventional analytical methods. This thesis explores Surface Enhanced Raman Spectroscopy (SERS) combined with advanced machine learning techniques to robustly analyze individual exosomes and provide deeper biochemical insights.The thesis begins by detailing the fundamental principles and physics underlying SERS, emphasizing its sensitivity and specificity for biomolecular diagnostics. It addresses practical considerations in spectral analysis and the challenges involved in accurately interpreting complex, high dimensional SERS data biochemically. The research highlights machine learning integration, particularly neural networks, for effectively overcoming these analytical hurdles. Additionally, the biochemical relevance of SERS signals is explored, where deep learning models were used to predict protein compositions from amino acid SERS profiles.Next, this work focuses on improving on the challenge of the throughput, which significantly restricts the practical application of SERS. This thesis tackles this challenge through innovative approaches, including plasmonic precipitation and surface functionalization strategies. We experimentally validate the potential of this improved platform in clinically relevant scenarios. For instance, early diagnosis of gastric cancer using exosomes derived from tissue and plasma and exploring therapeutic efficacy in ocular treatments using exosomes derived from eyes.This research advances the integration of SERS and machine learning, providing practical pathways toward diagnostic and therapeutic applications.
- 일반주제명
- Materials science
- 일반주제명
- Biomedical engineering
- 일반주제명
- Engineering
- 키워드
- Biosensing
- 키워드
- Exosomes
- 키워드
- Machine learning
- 키워드
- Neural networks
- 기타저자
- University of California, Los Angeles Materials Science and Engineering 0328
- 기본자료저록
- Dissertations Abstracts International. 87-03B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008260126s2025 us c eng d■001000017359656
■00520260202105153
■006m o d
■007cr#unu||||||||
■020 ▼a9798293839667
■035 ▼a(MiAaPQ)AAI32242626
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a620.11
■1001 ▼aSrivastava, Siddharth.
■24510▼aScience and Technology of Extracellular Vesicles in Medical Applications Utilizing SERS and Machine Learning
■260 ▼a[Sl]▼bUniversity of California, Los Angeles▼c2025
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2025
■300 ▼a188 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 87-03, Section: B.
■500 ▼aAdvisor: Xie, Ya-Hong.
■5021 ▼aThesis (Ph.D.)--University of California, Los Angeles, 2025.
■520 ▼aExtracellular vesicles (EVs), particularly exosomes, show significant promise in biomedical diagnostics and therapeutics due to their rich biochemical content. However, precisely characterizing individual exosomes remains challenging for conventional analytical methods. This thesis explores Surface Enhanced Raman Spectroscopy (SERS) combined with advanced machine learning techniques to robustly analyze individual exosomes and provide deeper biochemical insights.The thesis begins by detailing the fundamental principles and physics underlying SERS, emphasizing its sensitivity and specificity for biomolecular diagnostics. It addresses practical considerations in spectral analysis and the challenges involved in accurately interpreting complex, high dimensional SERS data biochemically. The research highlights machine learning integration, particularly neural networks, for effectively overcoming these analytical hurdles. Additionally, the biochemical relevance of SERS signals is explored, where deep learning models were used to predict protein compositions from amino acid SERS profiles.Next, this work focuses on improving on the challenge of the throughput, which significantly restricts the practical application of SERS. This thesis tackles this challenge through innovative approaches, including plasmonic precipitation and surface functionalization strategies. We experimentally validate the potential of this improved platform in clinically relevant scenarios. For instance, early diagnosis of gastric cancer using exosomes derived from tissue and plasma and exploring therapeutic efficacy in ocular treatments using exosomes derived from eyes.This research advances the integration of SERS and machine learning, providing practical pathways toward diagnostic and therapeutic applications.
■590 ▼aSchool code: 0031.
■650 4▼aMaterials science
■650 4▼aBiomedical engineering
■650 4▼aEngineering
■653 ▼aBiosensing
■653 ▼aExosomes
■653 ▼aMachine learning
■653 ▼aNeural networks
■653 ▼aSurface Enhanced Raman Spectroscopy
■690 ▼a0794
■690 ▼a0541
■690 ▼a0537
■71020▼aUniversity of California, Los Angeles▼bMaterials Science and Engineering 0328.
■7730 ▼tDissertations Abstracts International▼g87-03B.
■790 ▼a0031
■791 ▼aPh.D.
■792 ▼a2025
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17359656▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
