DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Jang, In Gwun | - |
dc.contributor.advisor | 장인권 | - |
dc.contributor.author | Sin, Sang Min | - |
dc.date.accessioned | 2021-05-13T19:42:12Z | - |
dc.date.available | 2021-05-13T19:42:12Z | - |
dc.date.issued | 2020 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=947955&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/285217 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 조천식녹색교통대학원, 2020.2,[iv, 35 p. :] | - |
dc.description.abstract | As our society is aging, osteoporosis is becoming prevalent. Accurate diagnosis of osteoporosis needs a high-resolution skeletal image. Resolution enhancement for skeletal images using topology optimization is successful but the problem is that its computational time is too long for clinical application. Recently, deep learning receives attention due to its high accuracy and fast computational time, therefore, resolution enhancement using deep learning has been researched. However, a lack of large-scale datasets is a major problem for deep learning in medical images. The patchwise approach can solve this problem to augment many data, however, this approach causes disconnected patches, which degrades image quality and structural behavior. This paper introduces quilting algorithm, which is used in texture synthesis, to solve this discontinuity problem. In addition, ResNet and SRGAN, which are commonly used in resolution enhancement problem, are compared in image quality and structural behavior. The proposed method reconstructs high-resolution skeletal images faster than topology optimization and improves image quality and structural behavior. However, the accuracy is still a lot lower, so further works are needed. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Medical image▼aDeep learning▼aResolution enhancement▼aFinite element analysis▼aBone microstructure | - |
dc.title | Patchwise-connected resolution enhancement for healthy weight-bearing bones using deep learning | - |
dc.title.alternative | 패치 간 연속성을 보장하는 딥 러닝을 이용한 골격계 영상 고해상화 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :조천식녹색교통대학원, | - |
dc.contributor.alternativeauthor | 신상민 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.