서브메뉴
검색
Auditing the Reasoning Processes of Medical-Image AI
Auditing the Reasoning Processes of Medical-Image AI
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211150956
- ISBN
- 9798382212128
- DDC
- 610
- 저자명
- DeGrave, Alex.
- 서명/저자
- Auditing the Reasoning Processes of Medical-Image AI
- 발행사항
- [Sl] : University of Washington, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 94 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-10, Section: B.
- 주기사항
- Advisor: Lee, Su-In.
- 학위논문주기
- Thesis (Ph.D.)--University of Washington, 2024.
- 초록/해제
- 요약While medical artificial intelligence (AI) systems are achieving regulatory approval and clinical deployment across the world, the reasoning processes of these systems remain opaque to all stakeholders, including physicians, patients, regulators, and even the developers of these systems. Since the modern wave of medical AI relies on automatic learning of statistical patterns from large datasets-via 'machine-learning' techniques such as neural networks-they are prone to learning unexpected and potentially undesirable patterns, which may lead to pathological behavior in deployment. Here, we investigate the 'reasoning processes' of medical-image AI systems, that is, by forming a human-understandable, medically grounded conception of that mechanisms by which they generate predictions. Along the way, we develop new tools and frameworks as necessary to do so. Via these investigations, we uncover severe flaws in the reasoning of medical AI systems, and we build the first thorough, medically grounded picture of machine-learning-based medical-image AI reasoning processes.
- 일반주제명
- Medicine
- 일반주제명
- Medical imaging
- 일반주제명
- Computer science
- 일반주제명
- Dermatology
- 키워드
- Medical-images
- 키워드
- Machine learning
- 키워드
- Radiology
- 기타저자
- University of Washington Computer Science and Engineering
- 기본자료저록
- Dissertations Abstracts International. 85-10B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017160318
■00520250211150956
■006m o d
■007cr#unu||||||||
■020 ▼a9798382212128
■035 ▼a(MiAaPQ)AAI30993617
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a610
■1001 ▼aDeGrave, Alex.
■24510▼aAuditing the Reasoning Processes of Medical-Image AI
■260 ▼a[Sl]▼bUniversity of Washington▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a94 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-10, Section: B.
■500 ▼aAdvisor: Lee, Su-In.
■5021 ▼aThesis (Ph.D.)--University of Washington, 2024.
■520 ▼aWhile medical artificial intelligence (AI) systems are achieving regulatory approval and clinical deployment across the world, the reasoning processes of these systems remain opaque to all stakeholders, including physicians, patients, regulators, and even the developers of these systems. Since the modern wave of medical AI relies on automatic learning of statistical patterns from large datasets-via 'machine-learning' techniques such as neural networks-they are prone to learning unexpected and potentially undesirable patterns, which may lead to pathological behavior in deployment. Here, we investigate the 'reasoning processes' of medical-image AI systems, that is, by forming a human-understandable, medically grounded conception of that mechanisms by which they generate predictions. Along the way, we develop new tools and frameworks as necessary to do so. Via these investigations, we uncover severe flaws in the reasoning of medical AI systems, and we build the first thorough, medically grounded picture of machine-learning-based medical-image AI reasoning processes.
■590 ▼aSchool code: 0250.
■650 4▼aMedicine
■650 4▼aMedical imaging
■650 4▼aComputer science
■650 4▼aDermatology
■653 ▼aMedical-images
■653 ▼aMachine learning
■653 ▼aRadiology
■653 ▼aClinical deployment
■653 ▼aReasoning processes
■690 ▼a0564
■690 ▼a0574
■690 ▼a0984
■690 ▼a0800
■690 ▼a0757
■71020▼aUniversity of Washington▼bComputer Science and Engineering.
■7730 ▼tDissertations Abstracts International▼g85-10B.
■790 ▼a0250
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17160318▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
