Parameter-Transferred Wasserstein Generative Adversarial Network (PT-WGAN) for Low-Dose PET Image Denoising

• Published in: IEEE transactions on radiation and plasma medical sciences Vol. 5; no. 2; pp. 213 - 223
• Main Authors: Gong, Yu, Shan, Hongming, Teng, Yueyang, Tu, Ning, Li, Ming, Liang, Guodong, Wang, Ge, Wang, Shanshan
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Biomedical imaging; Convolution; Deconvolution; Deep learning; Generative adversarial networks; image quality; low-dose positron emission tomography (PET); Medical imaging; Noise reduction; Parameters; Positron emission; Positron emission tomography; Radiation; Radiation dosage; task-specific initialization; Three-dimensional displays; Tomography; Transfer learning; Two dimensional displays; Deep learning; image quality; transfer learning; task-specific initialization; low-dose PET
• ISSN: 2469-7311; 2469-7303
• DOI: 10.1109/TRPMS.2020.3025071

Due to the widespread of positron emission tomography (PET) in clinical practice, the potential risk of PET-associated radiation dose to patients needs to be minimized. However, with the reduction in the radiation dose, the resultant images may suffer from noise and artifacts that compromise diagnostic performance. In this article, we propose a parameter-transferred Wasserstein generative adversarial network (PT-WGAN) for low-dose PET image denoising. The contributions of this article are twofold: 1) a PT-WGAN framework is designed to denoise low-dose PET images without compromising structural details and 2) a task-specific initialization based on transfer learning is developed to train PT-WGAN using trainable parameters transferred from a pretrained model, which significantly improves the training efficiency of PT-WGAN. The experimental results on clinical data show that the proposed network can suppress image noise more effectively while preserving better image fidelity than recently published state-of-the-art methods. We make our code available at https://github.com/90n9-yu/PT-WGAN.