서브메뉴
검색
Augmenting Medical Image Classifiers With Synthetic Data Across Populations
Augmenting Medical Image Classifiers With Synthetic Data Across Populations
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211151446
- ISBN
- 9798382776552
- DDC
- 574
- 서명/저자
- Augmenting Medical Image Classifiers With Synthetic Data Across Populations
- 발행사항
- [Sl] : Harvard University, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 125 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
- 주기사항
- Advisor: Manrai, Arjun K.
- 학위논문주기
- Thesis (Ph.D.)--Harvard University, 2024.
- 초록/해제
- 요약Rapid improvements in the capabilities of generative artificial intelligence (AI) models to produce and interpret images have created new possibilities to address persistent challenges in medical machine learning including data scarcity, annotation costs, and model biases. This dissertation primarily explores the potential opportunities and limitations of using synthetic images created by large generative AI models to improve the performance and generalizability of medical image classifiers across populations. We also evaluate the ability of consumer-facing vision-language models to classify dermatology and chest X-ray images under different prompts.We designed an image-generation pipeline by fine-tuning diffusion-based models to create synthetic skin disease images using both generative fill and text-to-image methods. With this pipeline, we generated 500,000 synthetic dermatology images (which we publicly released for future research) representing 12 diseases across diverse skin tones. We then systematically evaluated the performance of AI disease classifiers when including or excluding synthetic images in model training. We show that in data-limited settings (in which there are few real images of a disease or skin-tone), synthetic data can improve classifier performance, but that these gains saturate once sufficient quantities of real images are available. We find that the biggest driver of model improvements is the quantity of real images. We also observed a correlation between the physician-assessed photorealism of synthetic images and gains in model performance. Collectively, these findings suggest that synthetic data presents a complementary tool to training disease classifiers and can be useful as an advanced augmentation method or a way to share features of a data distribution without sharing the data itself. However, efforts must still be focused on collecting more high quality, diverse, real data to train the next generation of fair, robust, and generalizable AI systems. We also evaluated the capabilities of consumer-facing and general-purpose vision-language AI models in interpreting chest X-rays and dermatology images. We found that these systems, which have not been specifically trained for medical image diagnoses, can perform at or near-human level on selected metrics, and that model performance and behavior can be influenced using the text prompt and task formulation. Our analysis suggests that evaluations of large language and vision-language models should carefully consider the prompt context and other inputs. Overall, this dissertation provides a systematic analysis of the opportunities, pitfalls, and open challenges regarding the use of synthetic data and generative AI for improving medical imaging across all populations.
- 일반주제명
- Bioinformatics
- 일반주제명
- Dermatology
- 일반주제명
- Medicine
- 일반주제명
- Medical imaging
- 키워드
- Diffusion models
- 키워드
- Generative AI
- 키워드
- Synthetic data
- 기타저자
- Harvard University Medical Sciences
- 기본자료저록
- Dissertations Abstracts International. 85-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017161793
■00520250211151446
■006m o d
■007cr#unu||||||||
■020 ▼a9798382776552
■035 ▼a(MiAaPQ)AAI31296447
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a574
■1001 ▼aSagers, Luke William.▼0(orcid)0000-0002-5024-7314
■24510▼aAugmenting Medical Image Classifiers With Synthetic Data Across Populations
■260 ▼a[Sl]▼bHarvard University▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a125 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: B.
■500 ▼aAdvisor: Manrai, Arjun K.
■5021 ▼aThesis (Ph.D.)--Harvard University, 2024.
■520 ▼aRapid improvements in the capabilities of generative artificial intelligence (AI) models to produce and interpret images have created new possibilities to address persistent challenges in medical machine learning including data scarcity, annotation costs, and model biases. This dissertation primarily explores the potential opportunities and limitations of using synthetic images created by large generative AI models to improve the performance and generalizability of medical image classifiers across populations. We also evaluate the ability of consumer-facing vision-language models to classify dermatology and chest X-ray images under different prompts.We designed an image-generation pipeline by fine-tuning diffusion-based models to create synthetic skin disease images using both generative fill and text-to-image methods. With this pipeline, we generated 500,000 synthetic dermatology images (which we publicly released for future research) representing 12 diseases across diverse skin tones. We then systematically evaluated the performance of AI disease classifiers when including or excluding synthetic images in model training. We show that in data-limited settings (in which there are few real images of a disease or skin-tone), synthetic data can improve classifier performance, but that these gains saturate once sufficient quantities of real images are available. We find that the biggest driver of model improvements is the quantity of real images. We also observed a correlation between the physician-assessed photorealism of synthetic images and gains in model performance. Collectively, these findings suggest that synthetic data presents a complementary tool to training disease classifiers and can be useful as an advanced augmentation method or a way to share features of a data distribution without sharing the data itself. However, efforts must still be focused on collecting more high quality, diverse, real data to train the next generation of fair, robust, and generalizable AI systems. We also evaluated the capabilities of consumer-facing and general-purpose vision-language AI models in interpreting chest X-rays and dermatology images. We found that these systems, which have not been specifically trained for medical image diagnoses, can perform at or near-human level on selected metrics, and that model performance and behavior can be influenced using the text prompt and task formulation. Our analysis suggests that evaluations of large language and vision-language models should carefully consider the prompt context and other inputs. Overall, this dissertation provides a systematic analysis of the opportunities, pitfalls, and open challenges regarding the use of synthetic data and generative AI for improving medical imaging across all populations.
■590 ▼aSchool code: 0084.
■650 4▼aBioinformatics
■650 4▼aDermatology
■650 4▼aMedicine
■650 4▼aMedical imaging
■653 ▼aDiffusion models
■653 ▼aGenerative AI
■653 ▼aImage classification
■653 ▼aSynthetic data
■653 ▼aVision-language models
■653 ▼aSkin disease images
■690 ▼a0715
■690 ▼a0574
■690 ▼a0564
■690 ▼a0800
■690 ▼a0757
■71020▼aHarvard University▼bMedical Sciences.
■7730 ▼tDissertations Abstracts International▼g85-12B.
■790 ▼a0084
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17161793▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.
