DPIR-Net: Direct PET Image Reconstruction Based on the Wasserstein Generative Adversarial Network

• Published in: IEEE transactions on radiation and plasma medical sciences Vol. 5; no. 1; pp. 35 - 43
• Main Authors: Hu, Zhanli, Xue, Hengzhi, Zhang, Qiyang, Gao, Juan, Zhang, Na, Zou, Sijuan, Teng, Yueyang, Liu, Xin, Yang, Yongfeng, Liang, Dong, Zhu, Xiaohua, Zheng, Hairong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.01.2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Biomedical imaging; Comparative studies; Deep learning; Direct image reconstruction; Feature extraction; Generative adversarial networks; Image enhancement; Image processing; Image quality; Image reconstruction; Imaging techniques; Machine learning; Medical imaging; Neural networks; Noise reduction; Positron emission; Positron emission tomography; positron emission tomography (PET); Radiation; Radiation effects; Radioactive tracers; Regularization; small animal PET; Smoothness; Tomography; Wasserstein generative adversarial network (WGAN)

Positron emission tomography (PET) is an advanced medical imaging technique widely used in various clinical applications, such as tumor detection and neurologic disorders. Reducing the radiotracer dose is desirable in PET imaging because it decreases the patient's radiation exposure. However, r...