[논문]AdaIN-Based Tunable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising

Gu, Jawook; Ye, Jong Chul

doi:10.1109/tci.2021.3050266

[해외논문] AdaIN-Based Tunable CycleGAN for Efficient Unsupervised Low-Dose CT Denoising

IEEE transactions on computational imaging, v.7, 2021년, pp.73 - 85

Gu, Jawook (Korea Advanced Institute of Science, and Technology, Department of Bio and Brain Engineering, Daejeon, Korea) , Ye, Jong Chul (Korea Advanced Institute of Science, and Technology, Department of Bio and Brain Engineering, Daejeon, Korea)

Abstract ▼ AI-Helper

Recently, deep learning approaches using CycleGAN have been demonstrated as a powerful unsupervised learning scheme for low-dose CT denoising. Unfortunately, one of the main limitations of the CycleGAN approach is that it requires two deep neural network generators at the training phase, although only one of them is used at the inference phase. The secondary auxiliary generator is needed to enforce the cycle-consistency, but the additional memory requirements and the increase in the number of learnable parameters are major hurdles for successful CycleGAN training. Despite the use of additional generator, CycleGAN only translates between two domains, so it is not possible to investigate the intermediate level of denoising. To address this issue, here we propose a novel tunable CycleGAN architecture using a single generator. In particular, a single generator is implemented using adaptive instance normalization (AdaIN) layers so that the baseline generator converting a low-dose CT image to a routine-dose CT image can be switched to a generator converting high-dose to low-dose by simply changing the AdaIN code. Thanks to the shared baseline network, the additional memory requirement and weight increases are minimized, and the training can be done more stably even with small training data. Furthermore, by interpolating the AdaIN codes between the two domains, we can investigate various intermediate level of denoising results. Experimental results show that the proposed method outperforms the previous CycleGAN approaches while using only about half the parameters, and provide tunable denoising features that may be potentially useful in clinical environment.

참고문헌 (35)

TensorFlow: Large-scale machine learning on heterogeneous systems abadi 2015
Proc 13th Int Conf Artif Intell Statist Understanding the difficulty of training deep feedforward neural networks glorot 0 249
Proc 3rd Int Conf Learn Representations Adam: A method for stochastic optimization kingma 0
10.1109/CVPR.2017.632
Wang, Zhou, Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing : a publication of the IEEE Signal Processing Society, vol.13, no.4, 600-612.

상세보기
Proc Adv Neural Inf Process Syst Adversarial self-defense for cycle-consistent gans bashkirova 0 637
Comput Vis Pattern Recognit Optimal transport driven CycleGAN for unsupervised learning in inverse problems sim 0
10.1561/9781680835519
Optimal Transport Old and New villani 2008 338
Song, Joonyoung, Jeong, Jae-Heon, Park, Dae-Soon, Kim, Hyun-Ho, Seo, Doo-Chun, Ye, Jong Chul. Unsupervised Denoising for Satellite Imagery Using Wavelet Directional CycleGAN. IEEE transactions on geoscience and remote sensing : a publication of the IEEE Geoscience and Remote Sensing Society, vol.59, no.8, 6823-6839.

상세보기
Unsupervised speech domain adaptation based on disentangled representation learning for robust speech recognition park 2019
Zhang, Fengquan, Gao, Huaming, Lai, Yuping. Detail-Preserving CycleGAN-AdaIN Framework for Image-to-Ink Painting Translation. IEEE access : practical research, open solutions, vol.8, 132002-132011.

상세보기
Proc Int Conf Learn Representations U-GAT-IT: Unsupervised generative attentional networks with adaptive layer-instance normalization for image-to-image translation kim 0
Wolterink, Jelmer M., Leiner, Tim, Viergever, Max A., Isgum, Ivana. Generative Adversarial Networks for Noise Reduction in Low-Dose CT. IEEE transactions on medical imaging, vol.36, no.12, 2536-2545.

상세보기
Proc IEEE Int Conf Image Process Nonsubsampled contourlet transform: Construction and application in enhancement zhou 0 i
10.1109/ICCV.2017.167
Low dose CT image and projection data [data set] mccollough 0
Kang, Eunhee, Min, Junhong, Ye, Jong Chul. A deep convolutional neural network using directional wavelets for low‐dose X‐ray CT reconstruction. Medical physics, vol.44, no.10,

상세보기
Clark, Kenneth, Vendt, Bruce, Smith, Kirk, Freymann, John, Kirby, Justin, Koppel, Paul, Moore, Stephen, Phillips, Stanley, Maffitt, David, Pringle, Michael, Tarbox, Lawrence, Prior, Fred. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. Journal of digital imaging : the official journal of the Society for Computer Applications in Radiology, vol.26, no.6, 1045-1057.

상세보기
Renker, M., Nance, J.W., Schoepf, U.J., O Brien, T.X., Zwerner, P.L., Meyer, M., Kerl, J.M., Bauer, R.W., Fink, C., Vogl, T.J.. Evaluation of Heavily Calcified Vessels with Coronary CT Angiography: Comparison of Iterative and Filtered Back Projection Image Reconstruction. Radiology, vol.260, no.2, 390-399.

상세보기
Chen, Hu, Zhang, Yi, Kalra, Mannudeep K., Lin, Feng, Chen, Yang, Liao, Peixi, Zhou, Jiliu, Wang, Ge. Low-Dose CT With a Residual Encoder-Decoder Convolutional Neural Network. IEEE transactions on medical imaging, vol.36, no.12, 2524-2535.

상세보기
Chen, Baiyu, Duan, Xinhui, Yu, Zhicong, Leng, Shuai, Yu, Lifeng, McCollough, Cynthia. Technical Note: Development and validation of an open data format for CT projection data. Medical physics, vol.42, no.12, 6964-6972.

상세보기
Kang, Eunhee, Chang, Won, Yoo, Jaejun, Ye, Jong Chul. Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network. IEEE transactions on medical imaging, vol.37, no.6, 1358-1369.

상세보기
10.1109/ICCV.2017.244
Yang, Qingsong, Yan, Pingkun, Zhang, Yanbo, Yu, Hengyong, Shi, Yongyi, Mou, Xuanqin, Kalra, Mannudeep K., Zhang, Yi, Sun, Ling, Wang, Ge. Low-Dose CT Image Denoising Using a Generative Adversarial Network With Wasserstein Distance and Perceptual Loss. IEEE transactions on medical imaging, vol.37, no.6, 1348-1357.

상세보기
Leipsic, Jonathon, LaBounty, Troy M., Heilbron, Brett, Min, James K., Mancini, G. B. John, Lin, Fay Y., Taylor, Carolyn, Dunning, Allison, Earls, James P.. Adaptive Statistical Iterative Reconstruction: Assessment of Image Noise and Image Quality in Coronary CT Angiography. AJR : American journal of roentgenology, vol.195, no.3, 649-654.

상세보기
Kang, Eunhee, Koo, Hyun Jung, Yang, Dong Hyun, Seo, Joon Bum, Ye, Jong Chul. Cycle‐consistent adversarial denoising network for multiphase coronary CT angiography. Medical physics, vol.46, no.2, 550-562.

상세보기
Beister, M., Kolditz, D., Kalender, W.A.. Iterative reconstruction methods in X-ray CT. Physica medica : European journal of medical physics, vol.28, no.2, 94-108.

상세보기
Instance normalization: The missing ingredient for fast stylization ulyanov 2016
Proc Int Conf Artif Intell Statist Wasserstein style transfer mroueh 0 108 842
10.1109/CVPR.2019.00453
10.1109/ICCV.2017.304
Proc Int Conf Med Image Comput Comput -Assist Interv U-net: Convolutional networks for biomedical image segmentation ronneberger 0 234
Yang, Dong Hyun, Kim, Young-Hak, Roh, Jae-Hyung, Kang, Joon-Won, Han, Dongjin, Jung, Joonho, Kim, Namkug, Lee, Jung Bok, Ahn, Jung-Min, Lee, Jong-Young. Stress Myocardial Perfusion CT in Patients Suspected of Having Coronary Artery Disease: Visual and Quantitative Analysis—Validation by Using Fractional Flow Reserve. Radiology, vol.276, no.3, 715-723.

상세보기
Koo, Hyun Jung, Yang, Dong Hyun, Oh, Sang Young, Kang, Joon-Won, Kim, Dae-Hee, Song, Jae-Kwan, Lee, Jae Won, Chung, Cheol Hyun, Lim, Tae-Hwan. Demonstration of Mitral Valve Prolapse with CT for Planning of Mitral Valve Repair. Radiographics : a review publication of the Radiological Society of North America, Inc, vol.34, no.6, 1537-1552.

상세보기

LOADING...

활용도 분석정보

상세보기

다운로드

내보내기

활용도 Top5 논문

해당 논문의 주제분야에서 활용도가 높은 상위 5개 콘텐츠를 보여줍니다.
더보기 버튼을 클릭하시면 더 많은 관련자료를 살펴볼 수 있습니다.

원문 URL 링크

DOI : 10.1109/TCI.2021.3050266
IEEE : 저널 > 논문

*원문 PDF 파일 및 링크정보가 존재하지 않을 경우 KISTI DDS 시스템에서 제공하는 원문복사서비스를 사용할 수 있습니다.

저작권 관리 안내

내보내기 메뉴

내보내기 구분

파일저장
인쇄
메일전송

구성항목

기본정보
상세정보

관리번호, 논문명, 저널/프로시딩명, 저자 , 발행년, 권, 호, 시작페이지, 끝페이지, 발행기관

저장형식

Text(ASCII format)
Excel format
RefWorks Direct Export
RIS format (for Reference Manager, ProCite, EndNote), Scholar's Aids, Mendeley

메일정보

받는사람 (필수): @
보내는사람 (선택): @
제목
내용: KISTI 검색결과 이메일 서비스

안내

총 건의 자료가 검색되었습니다.

다운받으실 자료의 인덱스를 입력하세요. (1-10,000)

검색결과의 순서대로 최대 10,000건 까지 다운로드가 가능합니다.

데이타가 많을 경우 속도가 느려질 수 있습니다.(최대 2~3분 소요)

다운로드 파일은 UTF-8 형태로 저장됩니다.
파일의 내용이 제대로 보이지 않을실 때는 웹브라우저 상단의 보기 -> 인코딩 -> 자동선택 여부를 확인하십시오.

Text(ASCII format)
Excel format

표제어: PCR

동의어: Packet Collision Rate

용어 설명 출처 목록 (6)

용어 설명: PCR은 세균 특이성이 있는 primer를 이용하여 적은 수의 세균이 있을지라도 쉽게 검출할 수 있는 유용한 방법이며, 이를 이용하여 구강 내 치면세균막이나 타액에서 직접 세균을 검출할 수 있게 되었다[8].

AI-Helper ※ AI-Helper는 을 사용합니다.

AI-Helper

안녕하세요, AI-Helper입니다. 좌측 "선택된 텍스트"에서 텍스트를 선택하여 요약, 번역, 용어설명을 실행하세요.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.

연합인증