DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 박현욱 | - |
dc.contributor.author | 이종연 | - |
dc.contributor.author | Lee, Jongyeon | - |
dc.date.accessioned | 2024-07-26T19:30:51Z | - |
dc.date.available | 2024-07-26T19:30:51Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1047235&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320942 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 전기및전자공학부, 2023.8,[vi, 70 p. :] | - |
dc.description.abstract | In magnetic resonance imaging (MRI), motion artifacts can significantly degrade image quality. To reduce motion artifacts in brain MRI, we propose deep learning-based motion correction methods. The first study is the motion correction network for multi-contrast MRI. The proposed method consists of two parts: image alignment and motion correction. Alignment of multi-contrast MR images is performed in an unsupervised manner by a convolutional neural network, yielding transformation parameters to align input images. The motion correction network corrects motion artifacts in the aligned multi-contrast images. The proposed method successfully corrected artifacts of simulated motion and real motion. The second study is the unsupervised motion correction method using deep image prior. This approach takes advantage of the high impedance to noise offered by the neural network parameterization to remove motion artifacts in MR images. The proposed method synthesizes motion-simulated images from the motion-corrected images generated by the convolutional neural network, where an optimization process minimizes the objective function between the synthesized images and the acquired images. Furthermore, k-space segments are clustered based on their estimated motion parameters. The proposed method exhibits significant quantitative and qualitative improvements in correcting rigid and in-plane motion artifacts in MR images acquired using turbo spin-echo sequence. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 자기 공명 영상▼a움직임 보정▼a다중 대조도 MRI▼a비지도 학습▼a딥 이미지 프라이어 | - |
dc.subject | Magnetic resonance imaging▼amotion correction▼amulti-contrast MRI▼aunsupervised learning▼adeep image prior | - |
dc.title | Motion correction methods for brain MRI using deep learning | - |
dc.title.alternative | 딥 러닝을 이용한 뇌 자기 공명 영상 움직임 보정 방법 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | Park, Hyun-Wook | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.