자기 지도 학습훈련 기반의 Noise2Void 네트워크를 이용한 PET 영상의 잡음 제거 평가 : 팬텀 실험 = The Evaluation of Denoising PET Image Using Self Supervised Noise2Void Learning Training: A Phantom Study

다국어 초록 (Multilingual Abstract)

Positron emission tomography (PET) images is affected by acquisition time, short acquisition times results in low gamma counts leading to degradation of image quality by statistical noise. Noise2Void(N2V) is self supervised denoising model that is convolutional neural network (CNN) based deep learning. The purpose of this study is to evaluate denoising performance of N2V for PET image with a short acquisition time. The phantom was scanned as a list mode for 10 min using Biograph mCT40 of PET/CT (Siemens Healthcare, Erlangen, Germany). We compared PET images using NEMA image-quality phantom for standard acquisition time (10 min), short acquisition time (2min) and simulated PET image (S2 min). To evaluate performance of N2V, the peak signal to noise ratio (PSNR), normalized root mean square error (NRMSE), structural similarity index (SSIM) and radio-activity recovery coefficient (RC) were used. The PSNR, NRMSE and SSIM for 2 min and S2 min PET images compared to 10min PET image were 30.983, 33.936, 9.954, 7.609 and 0.916, 0.934 respectively. The RC for spheres with S2 min PET image also met European Association of Nuclear Medicine Research Ltd. (EARL) FDG PET accreditation program. We confirmed generated S2 min PET image from N2V deep learning showed improvement results compared to 2 min PET image and The PET images on visual analysis were also comparable between 10 min and S2 min PET images. In conclusion, noisy PET image by means of short acquisition time using N2V denoising network model can be improved image quality without underestimation of radioactivity.

목차 (Table of Contents)

• Ⅰ. 서론 Ⅱ. 대상 및 방법 Ⅲ. 결과 Ⅳ. 고찰 Ⅴ. 결론

참고문헌 (Reference)

1 정의환, "핵의학 감마카메라 정도관리의 딥러닝 적용" 대한방사선과학회 43 (43): 461-467, 2020

2 김영재, "의료 영상에 최적화된 딥러닝 모델의 개발" 대한영상의학회 81 (81): 1274-1289, 2020

3 허광해, "영상에서 패치기반 CNN 모형을 이용한 잡음제거" 한국데이터정보과학회 30 (30): 349-363, 2019

4 Chen KT, "Ultra low dose 18F-flor-betaben amyloid PET imaging using deep learning with multi contrast MRI inputs" 290 (290): 649-656, 2019

5 Ronneberger O, "U-net:Convolutional networks for biomedical image segmentation" Springer 234-241, 2015

6 Chen Y, "Trainable nonlinear reaction diffusion : A flexible framework for fast and effective image restoration" 39 (39): 1256-1272, 2017

7 Hofheinz F, "Suitability of bilateral filtering for edge-preserving noise reduction in PET" 1 : 23-, 2011

8 Jeong YJ, "Restoration of amyloid PET images obtained with short time data using a generative adversarial networks framework" 11 : 4825-, 2021

9 Anwar SM, "Real image denoising with feature attention" 2019

10 조영현, "PET/MR 영상에서의 팬텀을 활용한 노이즈 감소를 위한 변형된 중간값 위너필터의 적용 효율성 연구" 대한방사선과학회 44 (44): 225-229, 2021

11 Krull A, "Noise2void-learning denoising from single noisy images" 2019

12 Lehtinen J, "Noise2Nois : Learning image restoration without clean data" 80 : 2965-2974, 2018

13 Jain V, "Natural image denoising with convolutional networks" 769-776, 2009

14 Anwar SM, "Medical image analysis using convolutional neural networks : A review" 42 : 226-, 2018

15 Zhao H, "Loss function for Image restoration with neural networks" 3 (3): 47-57, 2017

16 Leonard J, "Improvement of the backpropagation algorithm for training neural networks" 14 (14): 337-341, 1990

17 Burger HC, "Image denoising:Can plain neural networks compete with BM3D?" 2012

18 LeCun Y, "Gradientbased learning applied to document recognition" 86 (86): 2278-2324, 1998

19 Aide N, "EANM/EARL harmonization strategies in PET quantification : From daily practice to multicenter oncological studies" 44 : 17-31, 2017

20 Tajbakhsh N, "Convolution neural networks for medical image analysis: Full training or fine tuning?" 35 : 1299-1312, 2016

21 Zhang K, "Beyond a Gaussian denoiser : Residual learning of deep cnn for image denoising" 26 (26): 3142-3155, 2017

22 Lu W, "An investigation of quantitative accuracy for deep learning based denosing in oncological PET" (64) : 165019-, 2019

23 Chen J, "An ensemble of convolution neural networks for image classification based on LSTM" 217-222, 2017

24 Buades A, "A Non-local algorithm for image denoising" 60-65, 2005