DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Park, Jinah | - |
dc.contributor.advisor | 박진아 | - |
dc.contributor.author | Kang, Inha | - |
dc.date.accessioned | 2023-06-26T19:31:29Z | - |
dc.date.available | 2023-06-26T19:31:29Z | - |
dc.date.issued | 2022 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1008394&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/309536 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2022.8,[iv, 29 p. :] | - |
dc.description.abstract | Obtaining ground truth data in medical imaging has difficulties due to the fact that it requires a lot of annotating time from the experts in the field. Also, when trained with supervised learning, it detects only the cases included in the labels. In real practice, we want to also open to other possibilities than the named cases while examining the medical images. As a solution, the need for anomaly detection that can detect and localize abnormalities by learning the normal characteristics using only normal images is emerging. With medical image data, we can design either 2D or 3D networks of self-supervised learning for ‘Anomaly Detection’ task. Although 3D networks, which learns 3D structures of the human body, show good performance in 3D medical image anomaly detection, they cannot be stacked in deeper layers due to memory problems. While 2D networks have advantage in feature detection, they lack 3D context information. In this paper, we develop a method for combining the strength of the 3D network and the strength of the 2D network through joint embedding. We also propose the pretask of self-supervised learning to make it possible for the networks to learn efficiently. Through the experiments, we show that the proposed method achieves better performance in both classification and segmentation tasks compared to the SoTA method. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Joint Embedding▼aSelf-supervised Learning▼aAnomaly Detection▼a3D Medical Image | - |
dc.subject | 조인트 임베딩▼a자기 지도 학습▼a이상 탐지▼a3차원 의료영상 | - |
dc.title | Joint embedding of 2D and 3D networks for medical image anomaly detection | - |
dc.title.alternative | 의료 영상 이상 탐지를 위한 2차원 및 3차원 네트워크 조인트 임베딩 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 강인하 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.