Unsupervised low dose CT denoising using cycle consistent generative adversarial networks on wavelet sub-band images순환 생성적 적대 신경망을 이용한 비대응 웨이블릿 변환 저선량 컴퓨터 단층영상의 비지도적 잡음 제거

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 354
  • Download : 0
DC FieldValueLanguage
dc.contributor.advisorYe, Jong Chul-
dc.contributor.advisor예종철-
dc.contributor.authorLee, Joonhyung-
dc.date.accessioned2021-05-13T19:37:09Z-
dc.date.available2021-05-13T19:37:09Z-
dc.date.issued2020-
dc.identifier.urihttp://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=925091&flag=dissertationen_US
dc.identifier.urihttp://hdl.handle.net/10203/284932-
dc.description학위논문(석사) - 한국과학기술원 : 바이오및뇌공학과, 2020.8,[vi, 38 p. :]-
dc.description.abstractIn this work, we propose a novel method for denoising unpaired low-dose computed tomography (CT) images using a cycle-consistent generative adversarial network (CycleGAN) model trained on wavelet sub-band images. A primary goal of CT imaging research is to reduce the amount of X-ray radiation exposure during a scan. However, CT image quality deteriorates with reduced radiation doses, making accurate diagnosis difficult. Denoising algorithms are necessary to reduce the X-ray dose while maintaining adequate visual quality. Deep learning methods, especially convolutional neural networks (CNNs), have recently come to prominence due to their superior performance and much faster inference times compared to previous medical image reconstruction techniques. However, supervised learning is challenging for CT because acquiring paired scans with different doses would expose patients to unnecessary radiation. Unpaired CT scans of different dosages can, however, be used for unsupervised learning. However, we find that naïve image domain learning produces mean shifting artifacts, especially in air filled regions. Thus, we use wavelet sub-band images, which have had low-frequency structural information removed from them via the wavelet transform, as CycleGAN inputs. The CycleGAN translates the wavelet sub-band images from low-dose images to high-dose images. Cycle consistency preserves the remaining structural information. Our method thereby allows the neural network to focus on learning how to alter the noise distribution. Moreover, it further prevents the model from introducing structural artifacts. We evaluate our method through extensive experimentation on temporal CT scans acquired in clinical settings.-
dc.languageeng-
dc.publisher한국과학기술원-
dc.subjectcycle consistency▼adenoising▼alow-dose computed tomography▼awavelet sub-band image▼aunsupervised learning-
dc.subject순환 일관성▼a잡음 제거▼a저선량 컴퓨터 단층 촬영▼a웨이블릿 부대역 영상▼a비지도 학습-
dc.titleUnsupervised low dose CT denoising using cycle consistent generative adversarial networks on wavelet sub-band images-
dc.title.alternative순환 생성적 적대 신경망을 이용한 비대응 웨이블릿 변환 저선량 컴퓨터 단층영상의 비지도적 잡음 제거-
dc.typeThesis(Master)-
dc.identifier.CNRN325007-
dc.description.department한국과학기술원 :바이오및뇌공학과,-
dc.contributor.alternativeauthor이준형-
Appears in Collection
BiS-Theses_Master(석사논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0