서브메뉴
검색
Advances in Image Reconstruction for Digital Breast Tomosynthesis
Advances in Image Reconstruction for Digital Breast Tomosynthesis
상세정보
- 자료유형
- 학위논문 서양
- 최종처리일시
- 20250211152102
- ISBN
- 9798382739755
- DDC
- 610
- 저자명
- Gao, Mingjie.
- 서명/저자
- Advances in Image Reconstruction for Digital Breast Tomosynthesis
- 발행사항
- [Sl] : University of Michigan, 2024
- 발행사항
- Ann Arbor : ProQuest Dissertations & Theses, 2024
- 형태사항
- 171 p
- 주기사항
- Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
- 주기사항
- Advisor: Chan, Heang-Ping;Fessler, Jeffrey A.
- 학위논문주기
- Thesis (Ph.D.)--University of Michigan, 2024.
- 초록/해제
- 요약Digital breast tomosynthesis (DBT) is an important imaging modality for breast cancer screening and diagnosis. It acquires a sequence of projection views within a limited angle and provides quasi-three-dimensional images of the breasts, allowing for improved lesion visualization and reduced false positives compared with two-dimensional mammography. Despite its advantages, DBT suffers from noise and blur problems that can compromise image quality and reduce its sensitivity in detecting subtle signs of breast cancer such as microcalcifications (MCs). The primary objective of this thesis is to push the state-of-the-art of DBT imaging by developing advanced DBT image reconstruction and processing methods. By reducing image noise, enhancing spatial resolution, optimizing reconstruction methods and evaluating them based on clinical tasks, our ultimate goal is to make DBT an even more effective tool for breast cancer screening and diagnosis. In this thesis, we first developed a deep convolutional neural network (DCNN) for denoising reconstructed DBT images. We trained the DCNN using a weighted combination of mean squared error loss and the adversarial loss based on generative adversarial network (GAN), and therefore called it DNGAN. The DNGAN improved the contrast-to-noise ratio, detectability index, and human observer detection sensitivity of the MCs in DBT images of breast simulating phantoms. Promising denoising results were also observed on a small test set of human subject DBTs. Then, we introduced a model-based DCNN-regularized reconstruction (MDR) method for DBT. It combined a model-based iterative reconstruction method with the DNGAN denoiser. To facilitate task-based image quality assessment, we also proposed two DCNN tools: CNN-NE for noise estimation, and CNN-MC as a model observer for MC cluster detectability measure. We demonstrated the effectiveness of CNN-NE and CNN-MC using phantom DBTs. The MDR method achieved low noise and the highest detection rankings on a test set of human subject DBTs. Finally, we presented our work on modeling the x-ray source motion blur of the DBT imaging system. We derived an analytical in-plane source blur kernel for DBT images based on imaging geometry and showed that it could be approximated by a shift-invariant kernel over the DBT slice at a given height above the detector. We proposed a post-processing image deblurring method with a generative diffusion model as an image prior and successfully enhanced spatial resolution of the reconstructed DBT images.
- 일반주제명
- Biomedical engineering
- 일반주제명
- Computer science
- 일반주제명
- Electrical engineering
- 일반주제명
- Computer engineering
- 키워드
- Deep learning
- 키워드
- Image processing
- 기타저자
- University of Michigan Electrical and Computer Engineering
- 기본자료저록
- Dissertations Abstracts International. 85-12B.
- 전자적 위치 및 접속
- 로그인 후 원문을 볼 수 있습니다.
MARC
008250123s2024 us c eng d■001000017162844
■00520250211152102
■006m o d
■007cr#unu||||||||
■020 ▼a9798382739755
■035 ▼a(MiAaPQ)AAI31349036
■035 ▼a(MiAaPQ)umichrackham005418
■040 ▼aMiAaPQ▼cMiAaPQ
■0820 ▼a610
■1001 ▼aGao, Mingjie.
■24510▼aAdvances in Image Reconstruction for Digital Breast Tomosynthesis
■260 ▼a[Sl]▼bUniversity of Michigan▼c2024
■260 1▼aAnn Arbor▼bProQuest Dissertations & Theses▼c2024
■300 ▼a171 p
■500 ▼aSource: Dissertations Abstracts International, Volume: 85-12, Section: B.
■500 ▼aAdvisor: Chan, Heang-Ping;Fessler, Jeffrey A.
■5021 ▼aThesis (Ph.D.)--University of Michigan, 2024.
■520 ▼aDigital breast tomosynthesis (DBT) is an important imaging modality for breast cancer screening and diagnosis. It acquires a sequence of projection views within a limited angle and provides quasi-three-dimensional images of the breasts, allowing for improved lesion visualization and reduced false positives compared with two-dimensional mammography. Despite its advantages, DBT suffers from noise and blur problems that can compromise image quality and reduce its sensitivity in detecting subtle signs of breast cancer such as microcalcifications (MCs). The primary objective of this thesis is to push the state-of-the-art of DBT imaging by developing advanced DBT image reconstruction and processing methods. By reducing image noise, enhancing spatial resolution, optimizing reconstruction methods and evaluating them based on clinical tasks, our ultimate goal is to make DBT an even more effective tool for breast cancer screening and diagnosis. In this thesis, we first developed a deep convolutional neural network (DCNN) for denoising reconstructed DBT images. We trained the DCNN using a weighted combination of mean squared error loss and the adversarial loss based on generative adversarial network (GAN), and therefore called it DNGAN. The DNGAN improved the contrast-to-noise ratio, detectability index, and human observer detection sensitivity of the MCs in DBT images of breast simulating phantoms. Promising denoising results were also observed on a small test set of human subject DBTs. Then, we introduced a model-based DCNN-regularized reconstruction (MDR) method for DBT. It combined a model-based iterative reconstruction method with the DNGAN denoiser. To facilitate task-based image quality assessment, we also proposed two DCNN tools: CNN-NE for noise estimation, and CNN-MC as a model observer for MC cluster detectability measure. We demonstrated the effectiveness of CNN-NE and CNN-MC using phantom DBTs. The MDR method achieved low noise and the highest detection rankings on a test set of human subject DBTs. Finally, we presented our work on modeling the x-ray source motion blur of the DBT imaging system. We derived an analytical in-plane source blur kernel for DBT images based on imaging geometry and showed that it could be approximated by a shift-invariant kernel over the DBT slice at a given height above the detector. We proposed a post-processing image deblurring method with a generative diffusion model as an image prior and successfully enhanced spatial resolution of the reconstructed DBT images.
■590 ▼aSchool code: 0127.
■650 4▼aBiomedical engineering
■650 4▼aComputer science
■650 4▼aElectrical engineering
■650 4▼aComputer engineering
■653 ▼aDigital breast tomosynthesis
■653 ▼aImage reconstruction
■653 ▼aDeep learning
■653 ▼aImage processing
■653 ▼aMicrocalcification
■653 ▼aImage quality evaluation
■690 ▼a0544
■690 ▼a0541
■690 ▼a0984
■690 ▼a0464
■71020▼aUniversity of Michigan▼bElectrical and Computer Engineering.
■7730 ▼tDissertations Abstracts International▼g85-12B.
■790 ▼a0127
■791 ▼aPh.D.
■792 ▼a2024
■793 ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17162844▼nKERIS▼z이 자료의 원문은 한국교육학술정보원에서 제공합니다.


