Self-supervised PET Denoising

Si Young Yie; Seung Kwan Kang; Donghwi Hwang; Jae Sung Lee

doi:10.1007/s13139-020-00667-2

Self-supervised PET Denoising

Nucl Med Mol Imaging. 2020 Dec;54(6):299-304. doi: 10.1007/s13139-020-00667-2. Epub 2020 Oct 20.

Authors

Si Young Yie^{1

2}, Seung Kwan Kang^{1

3}, Donghwi Hwang^{1

3}, Jae Sung Lee^{1

3

4

5}

Affiliations

¹ Department of Nuclear Medicine, Seoul National University College of Medicine, 103 Daehak-ro, Jongno-gu, Seoul, 03080 South Korea.
² Department of Mechanical Engineering, Seoul National University College of Engineering, Seoul, 08826 South Korea.
³ Department of Biomedical Sciences, Seoul National University College of Medicine, Seoul, 03080 South Korea.
⁴ Institute of Radiation Medicine, Medical Research Center, Seoul National University College of Medicine, Seoul, 03080 South Korea.
⁵ Brightonix Imaging Inc, Seoul, 03080 South Korea.

Abstract

Purpose: Early deep-learning-based image denoising techniques mainly focused on a fully supervised model that learns how to generate a clean image from the noisy input (noise2clean: N2C). The aim of this study is to explore the feasibility of the self-supervised methods (noise2noise: N2N and noiser2noise: Nr2N) for PET image denoising based on the measured PET data sets by comparing their performance with the conventional N2C model.

Methods: For training and evaluating the networks, ¹⁸F-FDG brain PET/CT scan data of 14 patients was retrospectively used (10 for training and 4 for testing). From the 60-min list-mode data, we generated a total of 100 data bins with 10-s duration. We also generated 40-s-long data by adding four non-overlapping 10-s bins and 300-s-long reference data by adding all list-mode data. We employed U-Net that is widely used for various tasks in biomedical imaging to train and test proposed denoising models.

Results: All the N2C, N2N, and Nr2N were effective for improving the noisy inputs. While N2N showed equivalent PSNR to the N2C in all the noise levels, Nr2N yielded higher SSIM than N2N. N2N yielded denoised images similar to reference image with Gaussian filtering regardless of input noise level. Image contrast was better in the N2N results.

Conclusion: The self-supervised denoising method will be useful for reducing the PET scan time or radiation dose.

Keywords: Artificial neural network; Deep learning; Denoising filter; Positron emission tomography (PET).