DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Kim, Daeyoung | - |
dc.contributor.advisor | 김대영 | - |
dc.contributor.author | Jun, Tae Joon | - |
dc.date.accessioned | 2021-05-11T19:39:09Z | - |
dc.date.available | 2021-05-11T19:39:09Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=871500&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/283325 | - |
dc.description | 학위논문(박사) - 한국과학기술원 : 전산학부, 2019.8,[vi, 103 p. :] | - |
dc.description.abstract | In this dissertation, we address the deep-learning approaches for classification and semantic segmentation of medical image data. We propose a Transferable Ranking Convolutional Neural Network to consider the inter-class relationship, and applied it to glaucoma detection in fundus images. Also, we propose an encoder-decoder in encoder-decoder Convolutional Neural Network architecture where precise segmentation is possible from the beginning of decoding by transmitting all levels of features extracted from every encoder block, and applied it to three types of main vessel segmentation in coronary angiography. The proposed classification and semantic segmentation methods showed higher classification accuracy and Dice Similarity Coefficient score compared to existing methods and it can be effectively applied to other medical image data with similar data characteristics. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep learning▼aconvolutional neural network▼aclassification▼asemantic segmentation▼amedical image data | - |
dc.subject | 딥 러닝▼a컨볼루셔널 뉴럴 네트워크▼a분류▼a시맨틱 분할▼a의료 영상 데이터 | - |
dc.title | Deep learning approaches for classification and semantic segmentation of medical image data | - |
dc.title.alternative | 의료 영상 데이터의 분류 및 시맨틱 분할을 위한 딥러닝 접근법 | - |
dc.type | Thesis(Ph.D) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 전태준 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.