Journal Article

Adaptive 3D noise level‐guided restoration network for low‐dose positron emission tomography imaging

Huang, Zhenxing, Zhang, Xu, Zhou, Chao, Fan, Wei, Liang, Dong, Hu, Zhanli, Li, Wenbo

2023

Overview

Many deep learning methods have been proposed to improve the quality of low‐dose PET images (LPET), which usually construct end‐to‐end networks with certain radiation dose inputs. However, these approaches have omitted the noise disparity in PET images, which may differ among manufacturers or populations. Therefore, we tend to exploit these noise differences among PET images to achieve adaptive restoration. We proposed a 3D noise level‐guided PET restoration network for LPET including (1) adaptive noise level‐aware subnetwork and (2) LPET restoration subnetwork. The first subnetwork aims to predict the noise level of the given LPET, while the second subnetwork treats the estimated noise level as a priori information to guide the restoration process from LPET to standard‐dose PET images. Experiments were performed on real human head and neck datasets while the peak signal‐to‐noise ratio and structural similarity index measure were used to evaluate LPET recovery performance. Moreover, we also compared the proposed network with several deep‐learning approaches. Experimental results demonstrate that our network with dual‐stage design can perform adaptive restoration for LPET, yielding better visual and quantitative results. In future work, we attempt to apply our method to other imaging tasks and adapt it for clinical practice. This flowchart illustrates a 3D noise level‐guided positron emission tomography (PET) restoration network for low‐dose PET (LPET) images to reduce radiation risk. The proposed method consists of an adaptive noise level‐aware subnetwork and a LPET restoration subnetwork, which generate high‐quality standard‐dose PET images from LPET images. Considering the noise differences that may occur among different populations and manufacturers, the proposed method could be applied on PET images with different noise intensities.

• Publisher: John Wiley & Sons, Inc,Wiley-VCH
• Subject: Algorithms / Artificial intelligence / deep learning / image restoration / low‐dose PET / Machine learning / Medical equipment / Neural networks / noise estimation / Radiation / Tomography